method and system

专利摘要:
It is a system and method for linking human activity observed on video to a user account of a preferred modality that includes: through a computer vision monitoring system, detecting and tracking a human being as a person modeled by vision of computer within an environment, and the computer vision monitoring system is part of a computing platform that manages a user interaction experience; through at least one associative mechanism, establish an association between the person modeled by computer vision and at least one associative element and thus associate, the person modeled by computer vision and a user record linked through the associative element; and target the user interaction experience based, at least in part, on the combination of the modeled person and at least the user record.
公开号:BR112019027120A2
申请号:R112019027120-1
申请日:2018-06-21
公开日:2020-07-07
发明作者:William Glaser；Brian Van Osdol
申请人:Grabango Co.；
IPC主号:

专利说明:

[001] [001] This application claims the benefit of the provisional application in U.S. 62 / 523,183, filed on June 21, 2017, which is incorporated in its entirety for reference. TECHNICAL FIELD
[002] [002] This invention relates, in general, to the field of computer vision and, more specifically, to a new and useful system and method for personalized interactivity with a shared computer vision system. BACKGROUND
[003] [003] Surveillance systems applied basic object detection and facial recognition to primitive forms of functionality. However, current surveillance systems use a primitive understanding of detected people. If a recognition system is capable of detecting people, it will usually only identify a person's location as a generic person. Facial recognition can be used in limited situations, but due to the reliability of recognition, only a small number of people can be detected through it. In addition, facial recognition is currently vulnerable to adversary attacks and is therefore not suitable for use in many situations. This inability to understand the individuals observed provides a significant number of limitations to the uses of such systems.
[004] [004] Additionally, large-scale applications involving computer vision are not in active use at scale. The existing solutions described above are unsuitable for such applications. This contributes, in part, to the lack of advanced user interactions triggered by computer vision.
[005] [005] Thus, there is a need in the field of computer vision to create a new and useful system and method for linking human activity observed on video to a user account. This invention provides such a new and useful system and method. BRIEF DESCRIPTION OF THE FIGURES
[006] [006] Figure 1 is a schematic representation of an exemplary implementation of a preferred mode system;
[007] [007] Figures 2 to 4 are schematic representations of exemplary forms of associations;
[008] [008] Figure 5 is a schematic representation of an exemplary implementation of the system applied through multiple human beings in an environment;
[009] [009] Figure 6 is a flowchart representation of a method of a preferred modality;
[010] [010] Figure 7 is a flowchart representation of a variation in the establishment of associations;
[011] [011] Figures 8 and 9 are schematic representations of exemplary variations in the establishment of an association with an instance of the device;
[012] [012] Figures 10A to 10F are schematic representations of exemplary variations of the establishment of an association during a pairing process of an instance of the device;
[013] [013] Figure 11 is a schematic representation of a sequence of association mechanisms;
[014] [014] Figure 12 is a flowchart representation of the attachment of the validation to an associative element;
[015] [015] Figures 13 to 15 are schematic representations of coordination with a secondary device; and
[016] [016] Figure 16 is a flowchart representation of a variation of the method applied across multiple human beings. DESCRIPTION OF THE MODALITIES
[017] [017] The following description of the modalities of the invention is not intended to limit the invention to those modalities, but rather to enable an individual skilled in the art to produce and use this invention.
[018] [018] A system and method for linking human activity observed on video to a user account of a preferred mode works to pair, synchronize or otherwise associate a person or object detected and monitored by computer vision (CV) ) to some other representative construct related to that person or object. The system and method can enable innovative interaction capabilities and / or improved user privacy and data control for advanced CV-based applications. The system
[019] [019] The system and method can be applied to trigger personalized interactivity in a shared CV monitoring system. This can enable rich user interaction experiences that are individually focused, but triggered, in part, by CV monitoring systems distributed in a shared environment.
[020] [020] The association (or associations) established by the system and method can occur between a CV person, a user registry and / or a user account and then, preferably, to some other associative element. The additional membership element can be a human being (where a person's direct or indirect properties can be used to identify a person) and / or a computing device (for example, a physical computing device and / or some application instance on a computing device). These associations can, in addition, have a defined scope for a specific environment or space and a specific period of time. The system and method can additionally support the operation with different types of association “topologies”.
[021] [021] A CV person (ie, a computer modeled person), as used in this document, characterizes a detected and optionally tracked individual, modeled and represented by a CV monitoring system. A person's CV may or may not have any personally identifiable information or metadata associated with the person. The CV person will generally represent the presence of a person in an environment and, optionally, the location, actions, activity, CV-derived properties and / or other information based on image processing. For example, a CV person could have a location or position, bodily properties (for example, pose, clothing or other visual properties) and / or other tracked properties. Events, gestures and states detected by CV can additionally be detected in relation to the CV person and are part of the model / data representation of that individual. Here, a CV monitoring system features an imaging system and / or processing system that uses computer vision to facilitate the detection and tracking of objects, the detection of actions and the performance of other CV-based operations. In this document, the system and method are described in the way that they apply to modeling based on people's CVs, but a CV monitoring system can, additionally or alternatively, model other entities or objects, such as animals, vehicles, automated devices / robots or other suitable objects.
[022] [022] A user registry, as used in this document, features a computer registry that is associated with a single human being or being. A user record can preferably be associated with a CV person to uniquely identify, track and record the CV person's status. A user registry will preferably include several properties. The properties of a user registry may include personally identifiable information, but alternatively, they may not include any personally identifiable information. A user registry, in some implementations, may also include payment information, user settings, user history, privilege settings / permissions and / or other information. The properties of a user registry can initially use default settings that are used as replacements until these properties can be updated. Properties can be updated as a result of associating with other elements or through CV-based monitoring of the CV person.
[023] [023] A user registry can additionally be used in modeling the state of an entity in a system, which will, in part, direct an interactive digital experience. ** For example, in a variation of the system and method applied for automatic verification activated by CV, the user registration can be the registration used to register the items selected for purchase, forming some
[024] [024] A user registry can be an internal model of a human being. As an internal model of a human being, the user record could be an ephemeral user record that is essentially preserved during the period that the CV person is detected in the environment. For example, a user record can be created and updated during the time that a buyer is present in a store. Additionally, a user registry can connect a person's CV modeling through a person's non-continuous CV monitoring. For example, a first instance of a CV person monitored at a location in a specific time period and a second instance of a CV person
[025] [025] A user account, as used in this document, features an account in the system that can be accessed and manipulated by a user. A user account will generally be accompanied by an authorization process, such as a username and password or other credentials or authentication process. The user account can refer to a user account from an external system, such as a social media platform. In the example case of using the system applied to automatic verification, a user account can be used to enable a user to register an application instance, edit payment methods, change account settings, view purchase history, edit lists purchases and / or perform other actions. These actions can be synchronized with the user account and can be performed outside of a CV system, but can preferably be used by a CV system when the system and method associate a CV person and a user account. . In some variations, a user account could be implemented as an optional membership element for humans in the environment. CV-powered applications can handle humans with only ephemeral user registries, as well as humans with user accounts.
[026] [026] In some variations, a user registry can optionally include or reference (through a link or association) a user account. In situations where the system and method can optionally use a user account, some humans will have only one user record used in the internal modeling state and which references CV-related data. These humans may not have a user account. In this exemplary situation, some other human beings will have a user registration that is associated with or is the user account. In other implementations, only humans with explicitly created user accounts can be stored. Support for both ephemeral / anonymous user registries and user accounts can have the benefit of enabling ad hoc association of a new user account with an existing user registry. For example, a user who creates a user account in the middle of a shopping tour can gain access to their CV-based modeling (for example, a checklist for automatic or accelerated verification) that has been tracked through a registration previously anonymous user.
[027] [027] As will be understood by one skilled in the art, the exact architecture of the data model of such records can take many forms. In this document, a user registry will generally be used to refer to the generic user registry, which may or may not be associated with a user account with authentication credentials, the user account will generally be used in situations where there is a registry created by user that the user can authenticate to, unless otherwise specified.
[028] [028] A human being, as used in this document, characterizes a human being with a unique identity. A human being is sometimes called a user, customer, worker or other human identification, when appropriate. In the exemplary case of using the system applied for automatic verification, a human being may be someone who is a buyer, a worker in the store or is otherwise present in the environment. A human being could similarly generalize to other living or non-living entities, such as farm animals, domestic animals, vehicles, robots and the like. In this document, reference will be made mainly to humans, but one skilled in the art would understand that the system and method are not limited to use with humans.
[029] [029] An instance of the device, as used in this document, features an exclusive instantiation of a dynamic device present in the environment. An instance of the device in many cases is a computing device, such as a smart phone, a wearable computer, a tablet computer, a personal computer, or a computing kiosk / station. An instance of the device is preferably uniquely identifiable. In some cases, the device instance is more specifically an application instance on a device, such as an application installed by a user. Here, the instance is used to distinguish a unique installation and instantiation of an application on a specific device. Continuing with the system use case applied for automatic verification, the application instance can be an application of the automatic verification service that a buyer can use to observe their currently selected items, to complete the verification, to modify the settings and / or perform other tasks. In some instances, the system and method may facilitate synchronization of the state of the application instance with the user registry. An instance of the device may additionally be computing devices accessible in the environment, such as a point of sale (POS) payment kiosk, an aid kiosk or any suitable type of computing device.
[030] [030] An association, as used in this document, is some variation of connection or symbolic connection of at least two associative elements selected from a person's CV set, a user registry, a user account, an instance of the device and / or a human being. Most preferably, the association is an association of three elements of a CV person and a user record with at least one among a user account, an instance of the device and / or a human being. A CV person is preferably detected and then correlated to a corresponding associative identification element. The associative identification element can be an instance of the device, a human being or an identifier of a user account. The associative identification element can then be linked to a user record. Complex arbitrary association topologies can be established as shown in Figure 1
[031] [031] An association that includes a human association as shown in Figure 2 can provide positive confirmation of that human being. An association with a human being can occur through biometric detection of the human being through the CV monitoring system. A human association could also be indirectly established through biometric identification through a device / application. A human association could additionally use other properties of identification of a human being, such as interaction patterns (for example, shopping patterns), dress patterns, accompanying human patterns and / or other properties.
[032] [032] An association that includes a device instance association as shown in Figure 3 can establish state synchronization with the device and / or application. Interactions with an application can influence the CV monitoring system, and information detected in a similar way from the CV monitoring system can be sent to the device or application instance.
[033] [033] An association that includes a user account as shown in Figure 4 can establish state synchronization with the user account to take advantage of stored data and settings associated with the user. The stored settings of an account can influence the CV monitoring system, and information detected in a similar way from the CV monitoring system can be used to update the user account.
[034] [034] An association to a user registry preferably provides a level of indirectness between the CV person and associative identification elements so that CV modeling updates can be resilient to delays in establishing an identification association or changes in associations.
[035] [035] An association is preferably maintained for the duration of the CV person (for example, duration of a buyer shopping at a store). The association is preferably maintained through multiple visits to multiple stores - the association will generally be reestablished for each visit. The system and method can facilitate the establishment and / or reestablishment of the association. An association can additionally be expanded to include other associative elements. Elements of an association could, however, suffer permanent disassociation (for example, removing an instance of the device) or temporary disassociation (for example, disassociating a user account for anonymous purchases during a single visit).
[036] [036] An association topology generally describes a collection of associations for different associative elements. Different topologies can be used for different capacities. Different interaction experiences can also depend on or benefit from specific types of topologies. The association topology can additionally involve the type of association that has been established. The type of association can be linked to different levels of trust, privileges or other aspects of identification. For example, the identification of a computing device using one technique can be treated differently from identification using another technique. Additionally, associations can be reinforced or occur at different times and / or locations to affirm the correct association. In addition, the understanding of associations can be applied longitudinally with the monitoring of a person, that is, an association established at a point in time could be applied to future occurrences or applied retroactively, changing to the previous state based on the new information from Association. In view of the interaction experience as being based around an association topology, the system and method could additionally be extended to provide shared digital experiences and interactions for the groups. In this way, multiple human beings and / or multiple devices can be a shared digital experience. For example, a family who buys together would be represented as multiple CV people, but these modeled interactions can all be linked to a shared family user account.
[037] [037] The environment, as used in this document, characterizes the site where a CV monitoring system is installed and operational. The system and method can be produced to work in a wide variety of environments. In a preferred implementation, the environment is a shopping environment, such as a grocery store, convenience store, micro-business and unmanaged store, bulk item store, pharmacy, bookstore, warehouse, shopping center, market and / or any suitable environment that promotes trade and exchange of goods or services. In alternative use cases, the environment may include a residence, an office, a school, an airport, a public / urban space, a gym and / or any suitable location. The environment can be a locally confined environment, but it can alternatively be a distributed system with wide coverage.
[038] [038] The system and method can be used for any suitable video monitoring application. In particular, the system and method are for CV-based computing applications, which may include automated self-checking, inventory tracking, security surveillance, detection and tracking of environmental events and / or other suitable applications.
[039] [039] In this document, automatic self-checking is used as the main example application of the system and method, but any suitable application can be used. Automatic self-checking is mainly characterized by a system or method that generates or maintains a checklist (that is, a virtual cart) during the purchase process of a customer (or group of customers) in order to know the items owned when a customer leaves a store. An automatic verification system can additionally automatically charge a customer's account for the total of a checklist (for example, expected list of items selected for purchase). The automatic verification system could alternatively be used to speed up the entry of items for payment. The system and method, as described in this document, can be used to synchronize a person's CV and a resulting generated checklist (as detected, in part or in whole, through the CV monitoring system) with a user registry , a user account, a device instance, and / or a human. This could then be used to enable automatic charging of a stored payment method, authorizing the purchase of restricted items (for example, alcoholic beverages and the like), or performing other tasks.
[040] [040] The system and method can alternatively be used to represent the removal of a commodity by a customer, such as in a library, rental store, warehouse, or any suitable item storage facility and update an element associative. The system and method can, alternatively, be used to allow or restrict access to locations, charge for such access, enable authentication with shared computing devices or for any use case. The system can be produced to work in a wide variety of shopping environments, such as grocery stores, convenience stores, micro commerce and unmanaged stores, bulk goods stores, pharmacies, bookstores, warehouses, commercial centers, markets and / or any appropriate environment that promotes trade or exchange of goods or services. The system and method can also be used in other situations or environments.
[041] [041] The system is mainly described as employing a network of multiple video monitoring nodes. The system could additionally be applied to a single camera and, optionally, audio monitoring and can additionally include other forms of capture that can be used independently or in combination with video monitoring. These can include dealing, sonar, infrared, ultraviolet, radiofrequency, capacitance, magnetic, scales, pressure, volume, climate sensing and the like.
[042] [042] As a potential use, the system and method can be applied for managing permissions in a CV-based computing application. The type of association and the method of establishing associations can be used to enable or disable different permissions. For example, establishing an association to a user account with payment information can enable permissions for automatic self-verification, where the user can simply leave a store. In another example, establishing an association with a confirmed age-verified human can enable permissions to purchase alcohol or other restricted products. Permissions can be used to manage other connected devices. For example, the system and method could be used as an authentication mechanism that mitigates the need for a user to provide access name credentials when using a shared device. In another example, the system and method could use permissions to automatically unlock a door for allowed humans.
[043] [043] As another potential use, the system and method can be applied to synchronize user account data or application state for CV-based monitoring of a person's CV.
[044] [044] As a potential benefit, the system and method can enable dynamic permission management for CV-based computing applications. Similarly, the system and method can additionally provide multiple factors for establishing and validating associations useful in defining permissions and identity authentication. As shown in Figure 1, a complex association topology could be formed using different associative mechanisms. A CV identification system could identify a human being as "Bob". A phone and a smart watch could be detected in one or more ways. The devices can be correlated to a user record that is associated with a CV person. A user account could be identified and linked based on the user account established in the application instances. And a fingerprint scanner on a smart phone can be used to provide association of human identity with the use of a second form of biometric identification. Other suitable topologies can similarly be formed.
[045] [045] As another potential benefit, the system and method can enable more elaborate applications in CV-based computing applications, by synchronizing state and data between a CV monitoring system, accounts, devices and applications. In some ways, this may make it possible for public funding systems such as the CV monitoring system to be used for private computing interactions on a personal device. In another related potential benefit, this state and data sharing coordinated through the CV monitoring system can enable the personalized use of public computing devices or smart devices. These potentially personalized digital interactions in real time can occur as a result of the system, while CV monitoring systems also simultaneously offer such interactions across multiple humans as shown in Figure 5.
[046] [046] As an isolated example of the elaborate interactions enabled by the system and method, a buyer without having installed any application or setting up an account can enter a store activated by an automatic CV-based verification system. Upon entering the store, a CV person is established and a checklist can be created based on the buyer's actions. During the shopping experience, the buyer can be aware of and install the application of this automatic verification system. The system and method could automatically establish an association with that application instance and synchronize that buyer's checklist with your application. The buyer could then use the app to complete an automatic check even if the buyer only knew about the system in the middle of purchases. This example can exemplify a potential benefit of improved integration.
[047] [047] As a potential benefit, the system and method can probably scale the number of people monitored CVs. The number of people with CV can be staggered indefinitely or staggered to a number high enough to support the human beings present in the environment. This can be particularly important for shopping environments where hundreds of customers pass through the environment daily.
[048] [048] As another potential benefit, the system and method can provide improved privacy and customization. The system and method can accommodate customization of user settings and data management.
[049] [049] As a related benefit, the system and method can be flexible to elegantly handle a variety of forms of association. Different forms of associations can enable or direct different experiences in a CV-based computing application.
[050] [050] In a store's CV-based computing application, the system and method could establish different forms of associations that accommodate a variety of types of users ranging from customers with low participation, customers with moderate participation and customers with high participation participation.
[051] [051] As an example of a customer with low participation, Bob does not have a phone and does not want to create an account. The system and method can also be used to create a checklist for Bob and then synchronize the checklist with a self-service checkout kiosk or POS station where Bob can pay by card, cash or another mechanism . From Bob's perspective, the verification process is speeded up, as a checklist was transparently used to automatically update the verification kiosk / POS station.
[052] [052] As an example of a medium-sized customer, Ellen can install an application and / or set up a payment mechanism with a user account. However, Ellen, who prefers a simple experience, does not use the app in the store. The system and method can facilitate the creation of a checklist for Ellen, associating the checklist with her application instance and / or user account and then automatically charging the configured payment method when she leaves the store. Device instance association can be established transparently from Ellen's point of view when associating your device and thus your user account with the user registry. Ellen may receive a verification confirmation message after completing her purchases.
[053] [053] As an example of a high participation customer, Angela can have a large user of the application and set up a shopping list before entering the store. Inside the store, Angela likes to review the current total of selected items, consult the items on her shopping list not yet selected, and get information on where her next items on the shopping list are located. Information from the CV monitoring system can be synchronized in real time to Angela's application, and interactions in the application can similarly be synchronized with the CV monitoring system. Like Ellen, she can also have a payment engine setup so that she can be automatically charged. The system and method can assist in coordinating these interactions for Angela.
[054] [054] The system and method can be applied to a variety of user experience and resources. These examples are not intended to limit the system and method, which can be understood by the person skilled in the art.
[055] [055] 2. System
[056] [056] As shown in Figure 1, a system for personalized interactivity with a shared computer vision system of a preferred modality can include a CV 110 monitoring system integrated with a 112 imaging system. The CV 110 monitoring system it is preferably used on a 100 computing platform that manages a user interaction experience. The computing platform 100 will preferably include a data management system 130 and other supplementary system elements of a computing platform 100, service or application. The system can additionally include or interface with a user application and / or connected computing devices. In some variations, the system may include a proxy interface device 140.
[057] [057] A CV 110 monitoring system works to process and generate conclusions from one or more sources of image data. The CV 110 monitoring system can provide: person detection; person identification; person tracking; object detection; object tracking; extracting information from device interface sources; gesture, event or interaction detection; and / or any appropriate form of information collection using computer vision and, optionally, other processing techniques. The CV 110 monitoring system is preferably used to trigger CV-based applications, such as generating a checklist during purchases, tracking inventory status, tracking user interactions with objects, tracking devices in coordination with CV-derived observations and / or other interactions.
[058] [058] The CV 110 monitoring system operates,
[059] [059] A computing platform 100 works to coordinate or otherwise run an application, service or workflow. In a preferred implementation, computing platform 100 facilitates the execution of a digital user interaction experience. For example, computing platform 100 can facilitate a user interaction experience around or related to automated verification and / or accelerated verification for customers. The computing platform 100 may include local computing resources in the environment for coordination with the devices present in the environment. The computing platform 100 can, additionally or alternatively, be remote computing resources, in which local computing systems in the environment communicate and coordinate over the Internet (or other communication channel) with the resources of the computing platform 100.
[060] [060] The computing platform 100 preferably includes or otherwise interfaces with the CV monitoring system 110, which works to detect and model CV people and / or other CV-based information. The computing platform 100 may additionally include or otherwise interface with one or more associative element monitoring systems, which function to establish an association with one or more associative elements. The computing platform 100 may additionally include a data management system 130, which functions to manage and maintain user records and / or user accounts or other data modeling features to support the objectives of the system.
[061] [061] The association monitoring system 120 functions as an associative or synchronization mechanism to establish one or more forms of association with a human being and / or a computing device. In some variations, the association monitoring system 120 is part of another system element, such as the CV monitoring system 110 and / or for a computing platform application service 100 for coordination with an instance of the reporting device. computing (for example, a user application). In other variations, the association monitoring system 120 can be an active pickup or inquiry system, such as a wireless communication system, an RF / NFC interrogator, Bluetooth beacon, an audio sensor system, an audio submodule specialized CV monitoring, specialized application service or other suitable type of system. In variations that use an application instance to detect a device, the system may include an application service that works to manage, substantially in real time, communication and interaction with installed application instances that operate on a user's device. The system may include an identification system, but may additionally include multiple types of association monitoring systems 120 that can be used in a redundant and cooperative manner.
[062] [062] A wireless communication system can work to monitor and detect the presence of device signatures in the environment. Multiple wireless communication units (for example, Wi-Fi routers, RF / NFC interrogators and the like) can be positioned throughout the store. Its distributed location can be used to correlate the detection of a device signature with at least one approximate location. Bluetooth flags could be used in a similar way.
[063] [063] A specialized CV monitoring sub-module can perform some form of CV-based analysis to assist in detection. In a variation, this may include performing biometric identification or CV person classification. A specialized CV submodule could perform activity classification or modeling for a CV person that could be correlated to the movement patterns detected from a special motion detection application service enabled on a device. In a similar way, a CV monitoring sub-module could detect specific gestures performed by a user. Another specialized CV monitoring sub-module could detect visual patterns displayed by a computing device. A variety of types of CV monitoring submodules can be used.
[064] [064] An audio sensor system can work to detect audible signals in the environment. In one variation, audio signals detected by a computing device could be mapped to audio signals detected by microphones installed throughout the store. This could be used in determining the approximate location. In some instances, specialized and potentially almost inaudible signals could be emitted by the computing device and / or speakers in the environment. The detection of these unique signals by the device and / or microphones distributed in the environment could work to determine the location and thereby select a candidate group of CV people for a computing device.
[065] [065] The data management system 130 works to store user records and / or user account information. The system will generally include other elements to support the CV-based computing application and / or to provide a platform for CV-based computing applications deployed in multiple stores and / or for different use cases. User records and / or user accounts may be linked or otherwise pre-associated with one or more types of associative identification elements. For example, an individual's CV-based identification can generate an identity signature that is associated with a user record. In another example, an identifier for a specific device instance can be associated with a user record so that when that device instance is detected in the store, the mapped user record can be identified and accessed.
[066] [066] User applications and / or connected computing devices function as client devices that can participate in CV-based computing applications. In a preferred implementation, a store user application and / or the CV 110 monitoring system operator can be made accessible to users of the CV 110 monitoring system (for example, customers of a store). The user application can facilitate the association of a user account, the provision of biometric authentication through the device (for example, fingerprint, speech recognition, facial identification or other forms of biometric authentication), the collection of user input and / or performing other tasks. A connected computing device can be computing devices that can be installed or delivered to the environment. The connected computing devices can be kiosks or customer service stations, smart networked devices (for example, smart lock, smart lights, etc.), a workstation and / or any suitable computing devices.
[067] [067] A user application instance or a connected computing device is preferably addressable terminals in the system, so that the CV system or an alternative component can transmit data or information can be communicated to the instance user application or connected computing device. An SDK and / or API can be provided so that third party applications can establish such integration with a CV 110 monitoring system and / or platform.
[068] [068] The system may additionally include computing devices installed in the environment. In a variation, the computing devices installed in the environment are configured and directly integrated with the computing system and platform, so that they can be accessed and controlled at least partially. In another variation, the system may include a proxy interface device that functions as a communication port or edge device that facilitates communication and interactions with external devices. In this variation, existing computing devices such as a POS system could be used with the system without making direct changes to existing computing devices.
[069] [069] The preferred interface proxy device 140 functions as a device / resource controllable by the system that interfaces with the environmentally installed computing infrastructure. In some variations, the proxy interface device 140 represents an expected form of data entry. A preferred variation of the proxy interface device 140 is used to interface and extend an existing payment system. In a variation, the proxy interface device 140 is used to speed up the verification process by assisting in entering product information into an existing POS station. In another variation, the proxy interface device 140 can be used to assist the provision of pre-authorized payment mechanisms, so that a user can possibly pay without any explicit action (in addition to perhaps confirming the payment / purchase).
[070] [070] The interface with a computing device installed in the environment and / or a proxy interface device 140 would also have applications in other areas. For example, in a restaurant, a digital ordering kiosk could automatically display a custom ordering interface (for example, showing customer order history, starred items, personalized recommendations, loyalty reward options) based on identification based on the user's CV. At a gym, a user can approach a device distributed through the gym, and a personalized user interface can be automatically presented based on the user's CV-based identification and / or the activity previously tracked at the gym. In an airport configuration, a check-in kiosk could be controlled to automatically enter ticket information. These and other applications could be implemented through the system and method using a proxy interface device 140 and / or by connecting directly to the appropriate computing device.
[071] [071] A proxy interface device 140 preferably emulates an input device for a target computing device. For example, the proxy interface device 140 may be a keyboard emulator or barcode scanner (i.e., product entry emulator). The proxy interface device 140 can alternatively communicate data which then uses an installed service to communicate or otherwise interact with a target computing device.
[072] [072] A proxy interface device 140 preferably includes a communication module and a device interface module. The proxy interface device 140 can additionally be delivered as an attachment device enclosed in a body structure. The proxy interface device 140 may additionally include additional ports. In the case of use of the verification station, the proxy interface device 140 may include a product input interface module, so that the proxy interface device 140 can be connected between a barcode scanner and a verification station .
[073] [073] The proxy interface device 140 communicatively couples the system (more specifically, the CV-based monitoring system) to a computing device. A preferred implementation, the computing device is a point of sale verification station, but the communicatively coupled computing device could be any suitable type of computing device, such as an informational computing kiosk or computing devices for others. purposes.
[074] [074] The communication module works to allow the device to be remotely controlled. The communication module can preferably be communicatively coupled to the CV-based monitoring system. The communication module is preferably a wireless communication module, where the wireless communication module can include a Wi-Fi communication module, a Bluetooth or RF communication module, a cellular communication module or any suitable type of communication module. The communication module could additionally be a wired communication module, in which the proxy interface device 140 communicates via a wired or physical connection.
[075] [075] The communication module is preferably registered in the CV-based monitoring system. The communication module can additionally be registered in association with a target computing device. The location and / or target association can be registered during a registration period. As part of the registration process, the proxy interface device 140 could be registered and manually, automatically or semi-automatically associated with that location and the connected computing device (for example, a POS station). In a variation, the proxy interface device 140 could include an active or passive identifier to advertise itself to the CV monitoring system for registration and location determination.
[076] [076] The device interface module, which works to connect communicatively or interface with one or more computing devices. In one variation, this could be a wired connection. In one example, the proxy interface device 140 connects to a POS station via a port typically used by a barcode scanner. In some implementations, it can replace a connection from a barcode scanner. In other implementations, it can be connected to the POS in addition to one or more barcode scanners. In another variation, the proxy interface device 140 and / or the computing platform more generally can communicate wirelessly with a computing device such as a verification station.
[077] [077] The proxy interface device 140 can connect to a verification station via the device interface module using a standard electrical interface such as a USB interface or another data port. The proxy interface device 140 and, more specifically, the device interface module can generate and transmit the electrical signals suitable for communication with the verification station. The product entry module, in a preferred implementation, can transfer universal product codes (UPCs) from the modeled checklist. For some POS stations, this can be reported as UPCs as simulated keyboard inputs. These can be transferred in some sequence in series, so that, from the POS station, they appear as products inserted quickly. The product input emulator can additionally include an interface for one or more product input devices (such as a barcode scanner or keyboard), so that the product input emulator can be used in line with such devices input, as shown in Figure 17.
[078] [078] The product input interface module can be a communication port corresponding to that used in the device interface module. This is preferably used in such a way that the use of the proxy interface device 140 preserves the option of the verification station to use the existing infrastructure as a barcode scanner. Consequently, the product input interface module could be a female USB port. Data received through that port can be automatically relayed through the device interface module to the connected computing device. In addition or alternatively, the data received through the product input interface module can be captured and / or optionally processed. In a preferred implementation, the UPC data collected through the product input interface module can be relayed to the connected verification station, but also communicated to the computing platform. This can be used as training data for CV, AI and / or machine learning algorithms. Especially since the product information received through the product entry interface module will generally occur when there is an exception or problem with the generation of a checklist.
[079] [079] The proxy interface device 140 can preferably be enclosed in a rigid structure. The proxy interface device 140 will additionally include a microprocessor or other form of processing unit together with the memory, power supply and / or other suitable elements. Proxy interface devices 140 can be used for each verification station. Alternatively, a single proxy interface device 140 can interface and manage multiple scan stations.
[080] [080] The proxy interface device preferably includes user interface elements. The user interface elements are preferably provided to communicate with a user of the connected computing device. For example, user interface elements can work to facilitate the transmission of the system state and optionally the collection of user input from a worker who manages a POS station. User interface elements can, additionally or alternatively, be configured for use by other users, such as a customer.
[081] [081] In a preferred variation, user interface elements include one or more forms of a user interface output. A user interface output could be a visual output, an audio output, a tactile output and / or any suitable type of output.
[082] [082] A visual output could be some form of visual indicators (for example, lights or LED meters) or even a graphical display. In an implementation, an indicator light (or indicator lights) could signal when a checklist is transferred / received for updating a POS system. For example, the screen could flash green when items selected by a customer are automatically inserted into a POS station, thereby signaling the worker that he does not need to scan items for input and proceed to finalize payment. In addition or alternatively, the visual output could indicate when a checklist cannot be automatically inserted, if part of the checklist can / has been inserted and / or any other suitable exception. In another implementation, a graphical display could visually display the virtual verification items that have been retransmitted or suggested for retransmission to a POS station. The worker may also be asked to check the list and select an option to insert it at the POS station. Changes can be made if a mistake is made. These changes could be relayed back to the CV-based monitoring system as feedback for improvements in quality control and monitoring.
[083] [083] An audio output could be used together with a visual output or by itself. An audio could be an audible tone or signal that triggers different events. For example, there could be a tone or ring that plays when a customer with a valid checklist approaches the POS station's “primary position” (ie, the person / group ready for verification) that can indicate to the worker that he you can skip scanning / inserting items. Similarly, a tone can be played when a checklist is not available or is not valid for input, which can indicate to the worker that he must manually enter the items selected by the customer.
[084] [084] User interface elements could similarly include user input elements such as buttons, dials, touch screens, microphone (for audio commands) and the like. They can be used in various ways to allow the worker to enter information or communicate with the system. In an implementation, items are not automatically inserted into a POS station until a worker positively confirms the items for entry.
[085] [085] A preferred variation of the proxy interface device is one that interfaces with a POS station for the purpose of relaying item information based on a checklist generated by the CV-based monitoring system.
[086] [086] 3. Method
[087] [087] As shown in Figure 6, a method of linking observed human activity on video to a user record on a computing platform used to manage a preferred user experience of interaction can include the detection and tracking of a human being as a CV person in an S110 environment, the establishment of an association between the CV person and at least one S120 associative element and the direction of the user interaction experience based, at least in part, on the person's combination computer system and at least the S130 user registry. The establishment of an association between the CV person and at least one associative element S120 further comprises that the association with the associative element is, therefore, used in the association of the CV person and a user record linked through the associative element. One or more association mechanisms can be used to detect the associative element. The method can be applied to define and enforce permissions in the context of the CV monitoring system S132, to synchronize the state in an instance of the device with the CV monitoring system S134 and / or to control a connected device within the coordinating environment with a CV person and at least the associated element S136. The method is preferably implemented by a system as described above, but any suitable system can implement the method.
[088] [088] Block S110, which includes the detection and tracking of a human being as a CV person in an environment, works to establish a CV person in an environment. The S110 block is preferably implemented through or in connection with a CV monitoring system, which could be part of a computing platform, as described above. The detection and tracking of a human being as a CV person preferably includes the collection of image data and the application of person detection computer vision processing to the image data.
[089] [089] Image data is preferably collected and then processed by the CV monitoring system. When a human being enters an environment with a CV monitoring system in operation, the CV monitoring system can acquire the human being as a CV person. This CV person can be tracked during human time in the environment. Continuous tracking can be maintained, but the system could additionally handle discontinuous tracking when a person's CV tracking can be temporarily lost and then regained. The modeling of a CV person is preferably abandoned, expired, or disabled after the CV person leaves an environment.
[090] [090] Detection and tracking are preferably facilitated through various computer vision approaches. In an implementation, tracking can be achieved through visual "blocking", and the movement between the frames of a detectable CV person can be tracked. A physical or modeling system can be introduced to facilitate tracking the CV person through the frames and for recovery when a user is temporarily or partially occluded.
[091] [091] Detection and tracking can additionally use human identification. Human identification can include biometric identification, such as facial identification, locomotion identification, voice identification and the like. Human identification may additionally include more general characterizations of a human being, such as visual properties, clothing properties, height and weight estimates, age and / or possession properties (for example, holding a purse, using a stroller) identifiable purchases, etc.). Human identification can be used to uniquely identify a human being, but it can additionally be used to reduce potential candidates, if not uniquely identify them, from the identifications of human beings in an environment. Tracking a CV person could use human identification to assist in the acquisition of that CV person.
[092] [092] In addition to detecting and tracking a person's CV, the CV system can additionally provide additional CV-based analysis of image data, such as object detection, detection / classification of human-human interaction, detection human gesture and / or other suitable forms of modeling based on CV, based, in part, on image data. For example, in a shopping environment, items selected by a CV person and / or added to a CV person's cart can be added to a checklist, which can be modeled and stored in association with that person. CV. The CV monitoring system can capture and generate predictive models based on image data and supplementary data sets (for example, purchase history, user profile information, product information, etc.). The CV monitoring system can additionally work in combination with other capture systems, such as a smart shelf system with sensors, an RFID capture system,
[093] [093] Block S120, which includes establishing an association between the CV person and at least the associative element, works to synchronize and / or link a model derived from a human's computer vision to at least one other model of human-related data. Preferably, at least one association is established with an associative element. This associative element can function as a human being identifier or entity identifier. In some variations, this human or entity identifier can be based on the symbol (for example, as a device associated with human beings), biological based or on the pattern (for example, behavioral pattern detection). In general, the method is preferably carried out in order to establish an association with a user registry and / or user account.
[094] [094] Block S120 can occur at any time and / or appropriate place in the environment. In addition, multiple types and / or instances of associations can be established for a specific human being. In some variations, multiple associations can be established at different times, which can work to provide multiple identification factors and / or to adequately expand the confidence of a mapping between a CV person and a user registry. These associations can additionally act as additional factors when having high confidence in other associations, such as when associating a CV person with computing devices installed in the environment as a verification station.
[095] [095] The establishment of an association to a user registry and / or user account is preferably established through at least one associative identification element such as a device instance, application instance and / or an identifier of being human. One or more associative mechanisms can be used to establish the association. With an association established with an associative identification element, the associative identification element can be used to indirectly establish an association with a suitable user record or user account. The user registration or user account can be stored and consulted using a key, an identifier, a signature or properties acquired from the associative identification element. Consequently, block S120 will generally include the establishment of an association between the person modeled by computer vision and at least one associative element and, thus, associating the person modeled by computer vision and a user record linked through the associative element. Effectively, the method establishes an association of three elements between: a CV person; one or both of a user registry and a user account; and at least one of a device instance, an application instance and / or a human identifier.
[096] [096] An association to a user record, which can specifically be a user account, can expand a person's understanding of CV to platform-managed data and / or to a historical record of the human entity. In an automated verification implementation, payment information, purchase history, personalized loyalty program rewards and / or other information can be exposed for use in combination with modeled CV data.
[097] [097] An association to a user registry is preferably produced in connection with some identification association, such as a device instance association or association with human identity.
[098] [098] An association with a device instance (or, in some variations, an application instance) can facilitate the identification of a device associated with humans. The association with the device instance can also enable a communication link between the CV monitoring system and a device and / or application that is accessible to the corresponding human being. An association with a human identity can make it possible to authenticate the identity of the human being who corresponds to the CV person. In a variation, an association with a human being can be performed directly through CV-driven analysis of the CV person. For example, biometric identification can be used. In another variation, authentication and, more specifically, biometric authentication, can be facilitated by an accessible computing device, such as a personal computing device or kiosk using biometric authentication.
[099] [099] Establishing an association with a CV person may involve the use of one or more associative mechanisms to establish associations. Different associative mechanisms can have different levels of reliability, security and / or be usable for adding associations to different associative elements. A subset of these associative mechanisms can be classified as system-initiated associative mechanisms, and another subset of associative mechanisms can be classified as user-initiated associative mechanisms. The establishment of an association may involve the execution of variations of such associative mechanisms as shown in Figure 7.
[0100] [0100] The associative mechanisms initiated by the system can take advantage of natural conditions, without depending on any form of active participation of the user at work. System-initiated associative mechanisms can be used to automatically establish at least part of an association. They usually operate in the background and can be transparent to a user. System-initiated associative mechanisms can be used to establish an automatic association - possibly without the active participation of a human being at the time of association. Three potential types of associative mechanisms initiated by a system can be biometric, passive and active.
[0101] [0101] A biometric type of system-initiated associative mechanism preferably uses biometric input collected in real time from a CV person in the environment. This biometric identification can preferably be carried out remotely using the image data used by the CV monitoring system. Biometric identification can be used in combination with other associative mechanisms to increase confidence in biometric identification. For example, with the use of device signature detection and / or raw device location information, the candidate grouping of user identities can be reduced so that confidence in biometric identification can be more resilient. A face recognition CV process could be set up to identify a face from a group of 300 candidates close to the store's location, as opposed to millions of potential candidates found at some point in many places.
[0102] [0102] A passive type of associative mechanism initiated by a system can be an "always-on" technology that is typically exposed by a computing device carried by a human being. These signals can be unique to each device or at least provide distinctive features in a limited sample of devices and can therefore be used to form connections between devices and CV people with a relatively high degree of certainty. Passive associative mechanisms may not establish a positively confirmed association in some situations, as devices can be shared or stolen, but passive detection of devices in the background can be used to establish a probabilistically likely association and / or to restrict the scope of associative elements for other association techniques such as the automatic biometric analysis above. Such signals may include Wi-Fi, Bluetooth, MAC addresses, cellular subscription and the like. Such signals may not be 100% accurate associations, since smart devices can be shared or stolen by different human beings. However, such signs can at least be useful to humans during a single visit. They can additionally be useful device signatures for humans with a personal computing device, but without an application installed and / or without a user account. For example, a human being without installing a user application on their smart device may have a smart device to passively facilitate the association of a CV person with an instance of the device and the association of a user record with purchase history and Payment Information.
[0103] [0103] An active type of associative mechanism initiated by a system can be some technology installed or initiated by a user that, in some cases, can affirmatively connect people from CVs to a computing device. This variation of the system-initiated associative mechanism can operate without an explicit use of a device by a human being while in the store. However, they may depend on installing an application, installing or activating a service. Bluetooth LE signaling, background application update, geographic delimitation, relative GPS or GPS, other location services and / or other device functionality can expose signals by which a device could be detected and associated with a user registration or account. user.
[0104] [0104] User-initiated associative mechanisms may include an associative mechanism dependent on user action. A variation can be device-based initiation. Other forms of user-initiated associative mechanisms can be various forms of user input records.
[0105] [0105] Some preferred associative mechanisms could include the detection of an instance of the device associated with the human S121 and / or the collection of real-time image data from a CV person in the environment and the application of a form of biometric identification S125 and / or receiving enrollment on an S126 enrollment device. Some preferred variations of detection of an instance of the device associated with the human S121 may include: detection of a device signature exposed by devices carried by an S122 human, detection of a device usage mechanism explicitly or implicitly enabled by an S123 user and establishing an association during a process of pairing an instance of the S124 device.
[0106] [0106] Block S121, which includes the detection of an instance of the device associated with humans, works to use the presence of an identifiable device to establish an association. Block S121 will generally involve: through a device identification system, detecting an instance of the device that matches the CV person and then selecting a user record by a device instance identifier. This works to associate the CV person, the device instance and the user registry. Here, the device instance could be some human-identifiable device, such as a personal computing device such as a smart phone, a personal computer, a body-worn computer and the like. The device instance could alternatively be an instance of an application installed on a device, a browser session, or any suitable client that is discoverable and associated with a user. In some variations, the device instance could be a shared-computing device installed in the environment. A shared computing device will be shared by multiple users in different instances. A shared computing device can be used directly by humans when establishing the association (for example, an information kiosk or self-checking station). The shared computing device can alternatively be used to serve a specific human being when establishing the association (for example, a worker / employee verification station).
[0107] [0107] Here, the coincidence condition characterizes some form of associated proximity, which could include spatial and / or temporal proximity. An instance of the device can be spatially coincident when the instance of the device is detected at a location that corresponds to a modeled location of the CV person. The detection of a device is preferably isolated to a specific region or location. This location can be mapped to a corresponding location in the environmental model of the CV system. If a CV person is detected at the corresponding location, an association can be established between the device and the CV person. Depending on the spatial resolution of the device instance or the CV person, different proximity thresholds can be used. In some cases, the gross spatial proximity (for example, detected at a distance of 15.24 m (50 feet) from each other) may be sufficient, such as when the grouping of possible candidate pairings of CV persons and device instances it is not high. A device can be temporarily overlapped when the device instance is detected in a similar time window. For example, if an instance of the device is detected in the environment within one minute after detecting a person's CV, then they can be paired.
[0108] [0108] In a crowded environment, device detection can occur in multiple locations in an environment, and an association of CV person to a device instance can be established through longitudinal analysis of previous device detection instances. This may include observing the tracked movements of a device instance, analyzing sets of device instances and candidate CV people, and / or using other appropriate techniques. For example, a device can be detected at the entrance to a store. However, there may be multiple CV candidates, so a confirmed association may not be established initially. The same device instance can be detected at a second location. Even though the number of CV candidates is still large, CV persons detected at the entrance and at the second location may restrict CV candidates.
[0109] [0109] Detection of a device instance can be used to identify and select a corresponding user record associated with the device instance. In a variation, the device instance may provide some key or distinctive identifier by which a user record stored in association with that identifier can be found and accessed. In this variation, the detection of an instance of the device can be used to re-establish a previous user record. This user record can be accessed by merging or replacing a current associated user record.
[0110] [0110] In addition, an instance of the device can be used to establish an association with a user account. In some cases, the application instance can be associated with a user account (for example, if a human has signed up for their account on the application), and establishing association with a device instance will establish, by association, a user account association. Consequently, using an instance of the device to establish an association with a user account may include authenticating a user account on the device instance; selection of a user record based on the user account authenticated to the device instance when the device instance is detected. The computing platform will generally have access to the device instance and, therefore, could map the user account recorded on the specific device instance with the CV person.
[0111] [0111] Similarly, a device instance and / or an application instance can facilitate human identification and thus can establish a validated association with a human being. This human association to the application instance can also be transferred to an association with a CV person. For example, fingerprint identification, facial identification, voice identification or other forms of biometric identification performed in the application instance can establish the association of human identity.
[0112] [0112] The detection of an instance of the device can be performed through a variety of approaches. As discussed above, the S121 block may include the detection of a device signature exposed by devices carried by an S122 human being, the detection of a mechanism of use on the device explicitly or implicitly enabled by an S123 user and / or the establishment of a association during an S124 device instance pairing process.
[0113] [0113] Block S122, which includes the detection of device signatures exposed by devices carried by a human being, works to facilitate the passive detection of devices in the background. Passive background device detection is preferably used to establish an association with a device instance through exposed communication device signatures. Device signatures preferably include communication signals from a device that are generally unique to a device and therefore can be used to form associations between an instance of the device and a CV person. A device signature can be detectable properties or identifiers exposed over Wi-Fi, over Bluetooth, through MAC addresses, through cellular signals and / or other exposed broadcasts. The S122 block can preferably operate as a system-initiated associative mechanism and can be used to assist in providing enhancement functionality to users even if they are not registered or registered with a user account. As a user-initiated association, the user can set some option to enable (or disable) the user of device subscriptions. If a device instance was previously associated with a device registration or, more preferably, a user account, then the device signature can be used to establish associations with other associative elements. Block S123, which includes the detection of a device use mechanism explicitly or implicitly enabled by a user, works to facilitate the detection of background devices enabled by the user. There are several options that, when activated by a user, will facilitate the automatic establishment of associations for that specific user. In a variation, a user can explicitly enable geographic delimitation for automatic detection when he enters a store. In another variation, a user can implicitly enable a detection mechanism by registering a user account to access Wi-Fi in the environment. In another variation, a user can enable kinematic monitoring to synchronize the movement of the human being with the movement of the CV person. These options may depend on a user who installs an application and / or enables or confirms specific device permissions.
[0114] [0114] User-enabled background device detection can be performed substantially similar to the passive background device detection described above. However, user-enabled background device detection can use detection approaches such as Bluetooth LE signaling, background application update, geographic delimitation, LED positioning, GPS, relative positioning in the environment, and the like.
[0115] [0115] With techniques such as Bluetooth signaling and geographical delimitation, the system can be actively notified when the device instance is present in the environment. With knowledge of the presence of a device instance, that device instance and previously associated human accounts, user accounts and / or user records can become candidates for associations with a CV person.
[0116] [0116] When using Bluetooth signaling, detection of the device instance may include detection of the location and / or presence of an identifiable device instance. The location information can be correlated with CV people with corresponding locations as shown in Figure 8. When Bluetooth signaling is used in multiple locations, a CV person can be mapped and associated with an instance of the device where there is an exclusive match of coincidence through a set of detection events. When there is only one CV person in the region of a first flag during a first detection event, then the detected device instance and CV person can be associated. When there are multiple people during multiple detection events, a CV person can be associated with the device instance if the CV person is the CV person exclusively present in the regions of the various flags at the time of the detection events.
[0117] [0117] When using location detection, device instance detection can include detecting the location of a device instance in the environment, and associating the device instance with a modeled CV person with a corresponding location as shown in Figure 9. Multiple location samples and / or the change in location can additionally be used. In a similar way to the Bluetooth signaling approach, sampling across many regions can be used to reduce a grouping of candidate CV people to a selected CV person.
[0118] [0118] In a variation of kinematic monitoring, the method may include, in the device instance, the capture of the movement and / or device orientation. This device movement and / or orientation can then be used in a variation where the S123 block includes the detection of an instance of the device associated with the device movement that satisfies a condition of synchronization with the activity of the CV person. In other words, the movement of the device instance is correlated to the movement of the CV person. An inertial measurement unit that can include accelerometers, gyroscopes, magnetometers (for direction) and / or other sensors can detect movement such as walking, stops and stops, hand movements, changes in body orientation and the like. By comparing these actions with the movement and orientation properties of a CV person, a CV person can be linked to an instance of the corresponding device. The use of movement as a synchronization mechanism may depend mainly on coincidence in time and cannot take location into account, although location can additionally be used.
[0119] [0119] In a variation, the establishment of an association can initiate the confirmation of the association, which works to trigger the user's claim to establish an association. Confirmation of an association can include requesting confirmation through communication with a human being (usually through an instance of the device). In a variation, an association can include a confirmed or possible association with an instance of the device. This device instance can have a communication address (for example, phone number, application instance identifier, push notification terminal, etc.). A message or notification can be transmitted to the communication address, and a human being can confirm or deny the request. Upon receipt of affirmative confirmation, the method can proceed with the establishment of the association. In another variation, the possible association may involve a user registration or a user account, which may have a communication address configured as a phone number or application instance identifier. A message or notification can be transmitted in a similar way.
[0120] [0120] Confirmation may require explicit confirmation by a human being. For example, a human being may receive a text message that says “It looks like you're at the supermarket. Answer 1 for yes and 2 for no ”. A confirmation can alternatively notify a human being, but it requires explicit denial to cancel / prevent the association. For example, a human being may receive a push notification that says “enjoy your shopping experience today! Select cancel if you received this in error ”. A confirmation can alternatively be approved automatically if a human selects a user account option to not confirm new sessions. Confirmation could be applied in a similar way before carrying out specific interactions that depend on an established association. For example, a user may receive a push notification in an application that asks if they want to automatically send checklist information to a checkpoint when they are nearby.
[0121] [0121] Block S124, which includes the establishment of an association during a pairing process of a device instance, works in order to have a device or, more preferably, an application that facilitates the establishment of an association. In some variations, a physical computing device can be designed to enter a pairing mode or to continuously perform some pairing action. The pairing mode can be configured to generate an identification signal via a user interface output from the device instance. As will be described below, the graphical display and the speakers can both generate signals usable to detect a device. Similarly, the captured data can be collected and used during pairing mode. In other variations, an application instance installed on a user's device may be actively involved in carrying out actions that may enable the exclusive detection of that application instance by the CV system and thus be associated with a CV person. In this document, the process of pairing an application instance is described, but it applies similarly to a device instance.
[0122] [0122] The pairing process is preferably started when the application instance becomes active (for example, it is brought to the foreground of a modal operating system). Activating the application instance can result in the application instance that records the state of pairing of the application instance with the CV monitoring system, so that the CV monitoring system can begin to cooperatively establish an association. Once in pairing mode, one or more signaling mechanisms can be used. Examples of signaling mechanisms may include the use of a camera, a screen or visual output, an audio system, an inertial measurement unit (IMU), application interactions and / or stored data.
[0123] [0123] As shown in Figure 10A, an application instance can use the computing device's camera to capture an image that can then be used to determine the position. In a variation, several visual identifiers (for example, a QR code or data-encoded image) can be positioned throughout the store. The capture of image data from the application can be used to determine the position of the human being who operates the application when the image data contains the visual identifier. In a related variation, the human operator of the application can be directed to take a picture of a cart of selected items or some other artifact, which can be used as an identifier.
[0124] [0124] In another variation, the camera can be activated in the background in order to observe the scene. This activation of the camera can be based on the detected orientation of the device (for example, it is the device held by the human being). Scene observations can act as a visual signature that can be mapped to images captured by the CV monitoring system with another approach to locating the device in the environment. For example, an application instance can capture images while the user uses the application. If an image of an item shelf is captured, that image can be used to determine the user's location in the store and thereby associate the application instance with a CV person. Visual identifiers can be integrated into the environment, such as the floor, ceiling, shelves, walls and the like to improve the mapping of visual signatures and positioning in the environment.
[0125] [0125] As shown in Figure 10B, an application instance can use the screen or other mechanisms for visual output when pairing an application instance with a CV person. In a preferred variation, the screen of a smart device can be adjusted to display a visual identifier. The visual identifier can be a static graph, but could alternatively be a time-varying visual display. When displaying the visual identifier, the application instance communicates with the system so that the detection of this visual identifier by the CV system can be associated with the application instance. The imaging system used by the CV monitoring system will preferably be able to identify the displayed identifier and map a suitable CV person to the application instance. A visual identifier could, alternatively, be produced by other device elements, such as a light and LED.
[0126] [0126] As shown in Figure 10C, an application instance can use the audio output when pairing an application instance with a CV person. An audio signal is generated with a unique identifier. The detection of this audio signal can then be used to determine the location and then used to select candidates for CVs. The audio signal is preferably in a frequency range at the limit or beyond a human's listenable range, but it could also be a sound audible by a human being. In one variation, the application instance generates the audio signal, and microphones distributed in the environment can detect the audio signal. Microphones are associated with a general region in the environment or can be used to triangulate a more precise location. In another variation, the speakers distributed across the environment generate audio signals that can be detected by an application instance. Each speaker preferably produces a unique audio signal, so that the detected audio signal can be mapped to a positioned speaker and / or a location. The detection of multiple audio signals can be used to triangulate a more precise location.
[0127] [0127] As shown in Figure 10D, an application instance can use the movement of the device as detected by an inertial measurement unit when pairing an application instance with a CV person. The inertial measurement unit may include a digital accelerometer, a gyroscope, a magnetometer and the like. During a pairing mode, movements, orientation and / or direction can be monitored to establish human movements. The CV monitoring system can similarly detect movements from the CV person to candidate CV people. CV people with corresponding movement patterns at a similar time can be associated with the device instance.
[0128] [0128] As shown in Figure 10E, an application instance can use application interaction as a mechanism to pair an application instance with a CV person. An application interaction can be used by detecting the human operation of the application and using the CV monitoring system to detect candidate CV people who perform similar actions. Application interaction can be used passively, which preferably uses normal interactions with the application instance as CV-detectable actions. For example, the application instance may require a human to perform a check-in action to use an automatic self-check feature. The act of removing a smart device and pressing a check-in button on the application instance can be detected as actions performed by a CV person. Additionally, the timing of activation of the check-in button as detected by the application instance can be used to determine CV people who perform this action in synchronization with this act.
[0129] [0129] During an application instance pairing mode, block S120 can include directing a physical action by the user and detecting a corresponding physical action by the CV person. By correlating the movement captured in the device instance with the modeled movement of the CV person, the device instance can be associated with the CV person. For example, application interactions can be actively driven by the application instance where an application instance instructs a human to perform some action or gesture, such as waving his hand, holding the smart device, pointing at an object or any action proper. These human gestures can be more detectable than interactions with the application instance. The timing of actions can be orchestrated by the application instance. In addition, the nature of the action can be controlled and changed to help establish the association. For example, different types of actions can be targeted so that the type, as well as the location and timing can better establish an association with high confidence. The movement of the device, as discussed above, can similarly be used in combination with targeted actions.
[0130] [0130] The establishment of an association during a pairing process of an instance of the device may additionally or alternatively use information collected from the application instance. When a pairing mode is activated, preferably by humans, then the system can start using stored information associated with the application instance and / or the account to establish an association. As a specific example, if a customer entered a shopping list in an application, then the CV monitoring system can compare that shopping list with the current CV person checklists. A CV person detected as having some subset of the shopping list can be associated with that application instance, as shown in Figure 10F. Purchase history, favorite products and / or other information can be used in a similar way.
[0131] [0131] Block S125, which includes collecting real-time image data from a CV person in the environment and applying a form of biometric identification, works to facilitate the automatic biometric analysis of a CV person. A variety of types of biometric identification techniques can be used, such as facial identification, locomotion identification, retinal identification, physical property identification (eg, height, weight, gender, etc.), and / or other forms of biometric identification. Biometric analysis can be used to establish a human association when a unique human identity is determined. Automatic biometric analysis can additionally establish associations with other associative elements such as a user record.
[0132] [0132] As an alternative or additional approach to biometric identification, the biometric identification capture capabilities of a computing device can be used when a computing device can be coupled and communicatively linked to a CV person (for example, using one of the above approaches). This variation may include, at the device instance, receipt of the biometric identification; and the association of human identity verification with the modeled person and user registration. The receipt of the biometric identification can act to confirm or specify the human identity of the current user of the computing device. Receipt of biometric identification could include verification of a fingerprint, facial pattern, voice, vital signs (eg, heart rate, respiratory rate) and / or any suitable biometric identification. These can be provided on a personal computing device or some shared computing device as a check-in kiosk in the environment.
[0133] [0133] Block S126, which includes receipt of enrollment on a enrollment device, works to establish an association during the active enrollment of a user registry, user account, human being and / or application instance. The enrollment device can be a kiosk or check-in station installed in the environment. The human being will preferably perform some interaction with the registration device to establish an association. Enrollment on the enrollment device can take many forms, such as scanning / scanning a card (for example, a payment card), displaying an NFC device, scanning a QR or barcode, biometric scanning, inserting a account credentials, PIN code insertion and / or any appropriate action. An enrollment device could additionally include biometric sensors to establish human associations. Some of these enrollment techniques may not need to have an instance of the device and / or other physical symbols. This can provide an option for humans who wish to participate in the system without using a physical device. The location of the enrollment device (or enrollment devices) and the proximity of a CV person during registration can be used to associate with a CV person. Alternatively, the method can use enrollment regions where some enrollment can occur without a physical enrollment device.
[0134] [0134] The mechanism for establishing an association may be one or more of the mechanisms described in this document.
[0135] [0135] There may also be different modes of associations that may depend on the associative elements, the mechanism for establishing associations and / or the options selected by the user. There could be an anonymous association in which a CV person is treated as a generic user. There could be an unrecognizable association mode, in which the information and capabilities enabled by associations to a user registry, user account, application registry and / or a human being can be used, but in which the session is not committed to the data records of these associations in the system. There could also be several forms of confirmed identity associations. For example, an association can be an association with a confirmed human identity, and secure permissions can be enabled, such as those that traditionally require revision of the form of physical identification.
[0136] [0136] Associations are preferably established before taking any action that requires permission confirmed through the association. In a preferred implementation, associations are established in response to approaching or entering an environment. However, the method can retroactively support the application of an association. As an illustration of the flexibility in establishing an association, the method can support the establishment of an association immediately before the human being enters the store and is incorporated as a CV person, immediately before a transaction during an automatic self-check and / or in conjunction with the transaction. Associations can additionally be developed during the period of time that the human being is in the environment, in which the establishment of an association can include the establishment of an association through multiple associative mechanisms carried out in different locations and times in the environment. For example, a CV person can initially be associated with a user record, then an application instance can be added and then a human association. Associations can additionally happen after a CV person has left the store, in which actions such as a billing transaction can occur by default. This can also happen over multiple visits to the environment by a human being. For example, a thief who subsequently creates a user account may have past activities and illicit behavior retroactively associated with the new user account.
[0137] [0137] Block S130, which includes targeting the user interaction experience based, at least in part, on the combination of the modeled person of the computer system and at least on the user record, works to apply the association established in the magnification of one or more processes in the CV-based computing system. Once an association is established, the information and capabilities of the different associated elements can be used cooperatively. At some level, the S130 block is used to coordinate a person's modeled state of CV with the state in another associated element.
[0138] [0138] A CV person association can use data to improve CV processing of image data and similarly extract information that can be provided for associative elements.
[0139] [0139] A user registry and / or user account can accept information from other associated elements when building a data profile. User registration and / or user account information can be used to improve the operation of the CV system and / or other devices, such as an application instance or a connected device in the environment.
[0140] [0140] A device or application association may be able to use information extracted from the CV monitoring system. The devices and the application will additionally have some status or data that can be synchronized with associated elements. The device or application can also expose an interface to receive user input or use other device features, such as the camera, biometric authentication elements and the like. A device association can additionally enable an authentication symbol-based way to define privileges.
[0141] [0141] A human association preferably provides a biometric authentication factor, which can be used to enable various permissions and privileges. A human association can preferably provide a specific, more human level of authentication than a device or application association.
[0142] [0142] An association is preferably applied by exposing data and / or status from at least one associative element to a second associative element. In the case of using automatic self-verification, an association of a CV person with a user record can expose data records stored in connection with the user record, such as purchase history, payment information and user settings. Having access can enable the automatic charging of detected actions from a CV person during a verification transaction. Purchase history, shopping lists and / or other information can similarly be accessed and used by the CV monitoring system to improve CV-based forecasts. User settings, configurations and preferences can be adjusted in association with a user account. However, even anonymous users with only one user registry can have the option to define personalized settings, such as privacy settings. For example, any user may be able to address an instance of the device installed in the environment, such as a help kiosk or verification kiosk, and in synchronizing the user registry with the state of that device instance, the settings linked to that registry User settings can be modified while the user is present on that device instance.
[0143] [0143] Three preferred variations of targeting the user interaction experience may include enforcing permissions set through the S132 association, synchronizing the state in an instance of the device with the CV monitoring system S134 and / or controlling an device connected in the environment in coordination with a CV person and at least one associated element S136.
[0144] [0144] Block S132, which includes the reinforcement of permissions adjusted through the association, works to enable, disable or change the functionality in the coordination with association properties. Different associative elements and / or ways of establishing an association can be used to adjust permissions for an interactive experience. Consequently, permissions can be set based, in part, on the properties of established associations. In one variation, permissions are based on the membership topology. For example, some permission may depend on validated human identity or validated device instance detection. In other variations, permissions can be adjusted for specific associative elements, so that establishing an association with that associative element can enable this permission definition. The definition of a permission can include granting or retaining a permission / privilege definition.
[0145] [0145] Permissions on a CV-based computer application for commerce can be used to enable purchases of controlled substances such as alcohol, tobacco, firearms, medications, limited purchase items (eg, pseudoephedrine) and other items. Permissions can also be used to restrict business practices, such as limiting a customer to purchasing a specified number of a sales item. The permissions can also be used in other use cases to restrict or allow access to different regions of the environment, interaction with different objects, automatic security line processing or regulation of any action observed through the CV monitoring system.
[0146] [0146] In an implementation, some subsets of permissions may additionally include human validation.
[0147] [0147] As an exemplary process, in which support for trade involves controlled substances, a multi-stage process can establish verified identity, thereby enabling associations with validated permissions. The process can be used in combination with the preferred modality method and can include: receiving a human identification document, encouraging permission validation, receiving human identification validation and attaching that validation to an associative element as shown in Figure 12. When an association is later confirmed with that associative element, then that person in the CV can be granted permissions to perform actions that require those permissions, such as the purchase of alcohol. In a variation, permissions are attached to a human association, in which the biometric identification of the human being is necessary to allow the purchase of controlled substances. In another variation, permissions can be attached to the physical token, such as an application instance or RFID card.
[0148] [0148] Receiving a human identification document preferably includes receiving an image or taking a photo of the document. For example, a user can use an app to take a front and back photo of a driver's license. Automatic document validation can be applied. Then, the application can instruct the human being to validate the document on the next visit to enable permissions. The worker can then perform human-level validation of the human identification document and approve permission validation from a worker-controlled system.
[0149] [0149] In an implementation, a subset of permissions can be validated once and used during subsequent sessions. In some cases, permissions can be preserved indefinitely, while in other cases, permissions can expire based on certain conditions. Single validation can similarly use the approaches discussed above. Once validated, permissions can be added to a user registry for subsequent use.
[0150] [0150] Permissions can be additionally revoked or reduced conditionally based on the rules for maintaining associations. Basic rules can be defined based on several conditions. For example, an association can expire after a certain period of time. The permissions could alternatively be revoked based on CV-based detection of different conditions. For example, the detection of a CV person who exhibits unusual behavior (for example, irregular behavior, loud noise, excessive interruption of objects), consuming a number of drinks above a threshold, or crossing lines that do not cross can be used in the detection of intoxication, in which case the permission to purchase controlled substances may be revoked. This could potentially be used to automatically allow alcoholic beverages to be sold in compliance with laws and regulations. Other exemplary conditions may be based on your account balance or payment information status. The revocation and / or reduction of permissions can be permanent, restored through an external event and / or restored after some time or other condition.
[0151] [0151] Block S134, which includes state synchronization on a device instance with the CV monitoring system, works to relay information between a device instance and a CV monitoring system. This synchronization with the CV monitoring system preferably synchronizes specific data for the CV person and / or device instance. Data and information can flow in one direction from one associative element to another, but data and information could similarly flow in multiple directions between associative elements. Since the CV monitoring system will preferably be used simultaneously by multiple different human beings, this synchronization allows for personalized interaction with the CV monitoring system while simultaneously sharing the CV monitoring system with multiple users.
[0152] [0152] In a variation, device instance or application instance information can be synchronized with the CV monitoring system to improve CV analysis, change business logic and / or otherwise change the interactive experience for a human being. This variation may include receiving user input communicated from the device instance and then executing the interactive user experience based, in part, on the combination of modeled state of the CV monitoring system and user input. .
[0153] [0153] In another variation, the information generated by the CV monitoring system can be communicated to the application instance. In this variation, block S134 can include communicating the modeled state of the CV monitoring system to the device instance. For example, a person's CV checklist could be communicated to an application instance. In some cases, the method may support conflict resolution between a CV monitoring system model and a user application model. For example, if a user deletes a product from a user application's checklist, but the CV monitoring system still predicts that the user has that object, some rule can be used to resolve the conflict.
[0154] [0154] Block S136, which refers to S134 and includes coordination with a secondary device, works to control an environmentally controlled device in response to an association and the CV person. This is a variation of block S134, in which the computing device is a secondary computing device present in the environment. The secondary device can be a kiosk, computing station, intelligent networked device (for example, smart lock, smart lights, smart scales, etc.) and / or any suitable computing device. The secondary device is, in general, a device installed and supplied by the environment so that there is no specific association for humans (that is, multiple humans can interact with the secondary device). Block S136 may include detecting the secondary device in close proximity to the CV person and synchronizing the state between the association of the CV person and the secondary device. As with block S134, it can include status and data communication to and from the secondary device as shown in Figure 13. The secondary device can be detected based on spatial proximity. In a variation, a proxy interface device can be used as an accessible computing device to interface with a target computing device (for example, a verification station) as shown in Figure 14. The proximity of the secondary device may alternatively depend on detect interactions with the secondary computing device and then identify an expected CV person responsible for the interaction.
[0155] [0155] The coordination of interactions with a secondary device can be used to enable the functionality in which a human being can approach a computing device and the device can automatically customize its state for the human being. It can similarly be used to automatically log into a user account based on permissions. But it can additionally facilitate interactions in which a user without a user account can walk up to a kiosk, and the kiosk automatically provides information obtained by the CV system. Similarly, a user could provide input to the CV monitoring system since actions performed through the secondary computing device can be communicated to the CV monitoring system as an input exclusively associated with that human being.
[0156] [0156] In a use case, it can be used to automatically communicate a generated checklist associated with a user record to a verification station. In another use case, it can be used to automatically communicate payment engine credentials to execute a financial transaction as shown in Figure 14.
[0157] [0157] In practice, the method is preferably carried out for as long as a human being is present in the environment. Consequently, when the human being enters the environment subjected to monitoring by the CV monitoring system, a person of CV can be detected. In one variation, a person's CV detection can trigger an association-building process. If an association can be established and if it can be used to select an existing user record / user account, then it can be associated with and used for that CV person. If an association cannot be established or if no user record / user account exists for an associative element, then a new default user record can be created and used. In the case of a later established association, a previously unknown user record or user account has been identified, then the current user record can be reconciled with the newly established one. In an implementation, multiple user records and user accounts can be maintained separately until some condition triggers the merge / reconciliation. In some cases, an association can be established with low trust and, for this, merging a linked user record may be undesirable until more trust is established. Greater confidence in user registration / user account associations can be established through more robust associative mechanisms and / or when multiple associations indicate similar associations.
[0158] [0158] In general, the establishment of an association can be carried out as a person enters an environment. However, the method can be similarly applied across an environment, so that a person's modeling can be resilient to interruptions in tracking a person's CV. For example, a buyer may have selected items monitored after entering the store. This person's tracking can be interrupted when the buyer enters an unmonitored space, such as a bathroom. When the buyer enters a monitored space again, the reestablishment of an association with an associative identification element can enable the user registration prior to the connection to this new CV person.
[0159] [0159] The method is preferably applied by multiple participants simultaneously, so that associations are appropriately created for different people in the environment. As shown in Figure 16, the method when applied to multiple participants could alternatively be described as including: detecting multiple people from CV S210, detecting multiple associative elements through at least one associative mechanism, S220, establishing associations correlating a person from CV and a associative element S230 and directing user interaction based on the combined state of data modeling of a set of associated elements S240. The variations described above for blocks S110, S120 and S130 can be similarly applied in this approach. The filtering of people from candidate CVs and associative identification elements can be facilitated by performing multiple instances of establishing an association. Different associations made with the use of different mechanisms, at different times, and in different locations can act to isolate exclusive correlations between a person's CV and associative identification elements. In practice, a computing platform is simultaneously monitoring the environment for potential associations. When one is concentrated, the computing platform evaluates this association to identify candidate associations and potentially exclusive pairings of associative elements. A longitudinal track record of candidate associations can be evaluated together with new candidate associations, which can facilitate the resolution of a single exclusive association.
[0160] [0160] The variations above the method could be similarly applied. In addition, different techniques can be applied to different users within an environment depending on different scenarios. For example, a user may have an associative mechanism employed to establish one or more associations, while a second user may have a second associative mechanism employed to establish a different set of associations.
[0161] [0161] The systems and methods of the modalities can be incorporated and / or implemented at least in part as a machine configured to receive a computer-readable medium that stores computer-readable instructions. Instructions can be executed by executable components integrated with the application, applet, host, server, network, website, communication service, communication interface, hardware / firmware / software elements of a user computer or mobile device, bracelet , smartphone or any suitable combination thereof. Other systems and methods of the modality can be incorporated and / or implemented at least in part as a machine configured to receive a computer-readable medium that stores computer-readable instructions. The instructions can be executed by computer executable components integrated with devices and networks of the type described above. The computer-readable medium can be stored on any suitable computer-readable media, such as RAMs, ROMs, flash memory, EEPROMs, optical devices (CD or DVD), hard drives or any suitable device. The computer executable component can be a processor, but any suitable dedicated hardware device can (alternatively or additionally) execute the instructions.
[0162] [0162] As a person skilled in the art will recognize from the previous detailed description and from the figures and claims, modifications and changes that can be made to the modalities of the invention without departing from the scope of this invention as defined in the following claims.

权利要求:
Claims (22)
[1]
1. METHOD, characterized by understanding: - through a computer vision monitoring system, to detect and track a human being as a person modeled by computer vision within an environment, and the computer vision monitoring system is part of a computing platform that manages a user interaction experience; - through at least one associative mechanism, establish an association between the person modeled by computer vision and at least one associative element and, thus, associate the person modeled by computer vision and a user record linked through the associative element; and - target the user interaction experience at least in part based on the combination of the modeled person and at least the user record.
[2]
2. METHOD, according to claim 1, characterized by the establishment of the association comprising, through an association monitoring system, detecting an instance of the device with close proximity to the modeled person and selecting a user record by an instance identifier thus associating the modeled person, the device instance and the user registry.
[3]
3. METHOD, according to claim 2, characterized by additionally comprising authenticating a user account in the device instance; and wherein selecting a user record in association with the device instance comprises selecting a user record based on the user account authenticated to the device instance when the device instance is detected.
[4]
4. METHOD, according to claim 2, characterized by directing the user interaction experience to understand synchronizing the state in the device instance with the state of the computer vision monitoring system.
[5]
5. METHOD, according to claim 2, characterized by directing the user interaction experience to understand communicating the modeled state of the CV monitoring system to the device instance.
[6]
6. METHOD, according to claim 2, characterized in that it additionally comprises, on the computing platform, receiving the user input communicated from the device instance; and where targeting the user interaction experience comprises executing the interactive user experience based, in part, on the combination of modeled state of the computer vision monitoring system and user input.
[7]
7. METHOD, according to claim 2, characterized by the device instance being an application instance operable on a personal computing device.
[8]
8. METHOD, according to claim 2, characterized by the instance of the device being a computing device with shared use in the environment.
[9]
9. METHOD, according to claim 2, characterized by detecting the device instance comprising detecting a device signature.
[10]
10. METHOD, according to claim 2, characterized by the detection of the device instance comprising detecting the location of an instance of the device in the environment.
[11]
11. METHOD, according to claim 2, characterized by the detection of the device instance comprising entering the device instance in a pairing mode configured to generate an identification signal through a device instance user interface output.
[12]
12. METHOD, according to claim 2, characterized by the detection of the device instance comprising, in the device instance, directing a physical action of the user and detecting a corresponding physical action of the modeled person and thereby associating the device instance to the modeled person.
[13]
13. METHOD, according to claim 2, characterized by additionally understanding, in the instance of the device in communication with the computing platform, the movement of the capture device and in which the establishment of an association between the person modeled by computer vision and at least one associative element comprises detecting the device instance associated with the device movement that satisfies a condition of synchronization with the person activity modeled by computer vision.
[14]
14. METHOD, according to claim 2, characterized in that it additionally comprises, in the device instance, receiving biometric identification; and associate the confirmation of human identity with the modeled person and the user registry.
[15]
15. METHOD, according to claim 2, characterized by the establishment of the association additionally comprising biometrically identifying a human being through the computer vision system and associating a human identity to the modeled person.
[16]
16. METHOD, according to claim 2, characterized by the establishment of the association being established through multiple instances of the associations established in different locations and times in the environment.
[17]
17. METHOD, according to claim 2, characterized by additionally understanding, before the establishment of an association, request confirmation of the association of an instance of the device, and establish the association upon receipt of the affirmative confirmation of the association.
[18]
18. METHOD, according to claim 1, characterized by additionally comprising: through the computer vision monitoring system, detecting and tracking a second human being as a second person modeled by computer vision in the environment; establishing an association between the second person modeled by computer vision and at least a second associative element and, thus, associating the second person modeled by computer vision and a second user record linked through the second associative element; and targeting a second user interaction experience at least in part based on the combination of the second modeled person and at least the second user record.
[19]
19. METHOD, according to claim 1, characterized by the user registration being an anonymous user registration.
[20]
20. METHOD, according to claim 1, characterized by the user registration being a user account with user-managed authentication credentials.
[21]
21. METHOD, according to claim 1, characterized in that it further comprises defining permissions based, in part, on the properties of associations established with the CV person; and where the targeting of the interaction experience comprises strengthening the permissions during the interaction experience.
[22]
22. SYSTEM, according to claim 1, characterized in that it additionally comprises receiving a human identification document; encourage permission validation; receive validation of human identification; attach this validation to an associative element; and in which the reinforcement of the permissions of the interactive experience additionally includes allowing actions based, in part, on the presence of validation of an associative element.

类似技术:

---

公开号 | 公开日 | 专利标题

---

US10740742B2|2020-08-11|Linked observed human activity on video to a user account

---

US20190253414A1|2019-08-15|Proximity-Based System for Object Tracking

---

US11095640B1|2021-08-17|Proximity-based system for automatic application or data access and item tracking

---

US20190325119A1|2019-10-24|Methods and system for passive authentication through user attributes

---

US11132882B1|2021-09-28|Proximity-based system for object tracking and automatic application initialization

---

JP2017522634A|2017-08-10|System and method for connecting to a mobile device to provide an electronic key and manage access

---

US11257086B2|2022-02-22|Automated sensor-based customer identification and authorization systems within a physical environment

---

RU2717957C2|2020-03-27|Method and system of user connection with portable device

---

US20210082271A1|2021-03-18|Facility control methods and apparatus

---

US20210352485A1|2021-11-11|Reader device with sensor streaming data and methods

---

US20210160658A1|2021-05-27|Methods and apparatus for presence sensing reporting

---

US10922396B2|2021-02-16|Signals-based authentication

---

Wójtowicz et al.2017|Technical feasibility of context-aware passive payment authorization for physical points of sale

---

US10952015B2|2021-03-16|Interlinked geo-fencing

---

JP7037899B2|2022-03-17|Judgment device, judgment method and judgment program

---

US20210194691A1|2021-06-24|Methods and apparatus for authorizing and providing of distributed goods or services

---

US20210166224A1|2021-06-03|Methods and apparatus for authorizing and providing of goods or services with reduced hardware resources

---

TWI745891B|2021-11-11|Authentication system, authentication terminal, user terminal, authentication method, and program product

---

TW202040454A|2020-11-01|Authentication system, authentication terminal, user terminal, authentication method, and program

---

JPWO2019181364A1|2021-03-11|Store management device and store management method, program

---

WO2020227109A1|2020-11-12|Device-independent, contextually driven application computing environment

同族专利:

---

公开号 | 公开日

---

EP3635623A4|2020-10-21|

---

US20200394636A1|2020-12-17|

---

WO2018237210A8|2019-06-13|

---

AU2018289552A1|2020-01-16|

---

US10740742B2|2020-08-11|

---

US20190005479A1|2019-01-03|

---

IL271528D0|2020-02-27|

---

US20180373928A1|2018-12-27|

---

WO2018237210A1|2018-12-27|

---

EP3635623A1|2020-04-15|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

US5254853A|1990-02-14|1993-10-19|Stefan Reich|Optical sensing device|

---

US5418567A|1993-01-29|1995-05-23|Bayport Controls, Inc.|Surveillance camera system|

---

US5502564A|1994-09-13|1996-03-26|Hughes Aircraft Company|Substrate thickness measurement using oblique incidence multispectral interferometry|

---

US9609287B2|2005-03-02|2017-03-28|En-Gauge, Inc.|Remote monitoring|

---

US6697103B1|1998-03-19|2004-02-24|Dennis Sunga Fernandez|Integrated network for monitoring remote objects|

---

US6970183B1|2000-06-14|2005-11-29|E-Watch, Inc.|Multimedia surveillance and monitoring system including network configuration|

---

US7107110B2|2001-03-05|2006-09-12|Microsoft Corporation|Audio buffers with audio effects|

---

US20040201754A1|2001-10-12|2004-10-14|Mcalister Micheal J.|Dual camera mounting arrangement for a wide screen imaging system|

---

US8321302B2|2002-01-23|2012-11-27|Sensormatic Electronics, LLC|Inventory management system|

---

US7274803B1|2002-04-02|2007-09-25|Videomining Corporation|Method and system for detecting conscious hand movement patterns and computer-generated visual feedback for facilitating human-computer interaction|

---

US7921036B1|2002-04-30|2011-04-05|Videomining Corporation|Method and system for dynamically targeting content based on automatic demographics and behavior analysis|

---

US20030210340A1|2002-05-07|2003-11-13|John Frederick Romanowich|Camera with a mechanical and electrical interface for couplable engagement with a standard lampholder|

---

US7227976B1|2002-07-08|2007-06-05|Videomining Corporation|Method and system for real-time facial image enhancement|

---

US8351647B2|2002-07-29|2013-01-08|Videomining Corporation|Automatic detection and aggregation of demographics and behavior of people|

---

US7053915B1|2002-07-30|2006-05-30|Advanced Interfaces, Inc|Method and system for enhancing virtual stage experience|

---

US8010402B1|2002-08-12|2011-08-30|Videomining Corporation|Method for augmenting transaction data with visually extracted demographics of people using computer vision|

---

US7225414B1|2002-09-10|2007-05-29|Videomining Corporation|Method and system for virtual touch entertainment|

---

US9711153B2|2002-09-27|2017-07-18|The Nielsen Company , Llc|Activating functions in processing devices using encoded audio and detecting audio signatures|

---

US6996460B1|2002-10-03|2006-02-07|Advanced Interfaces, Inc.|Method and apparatus for providing virtual touch interaction in the drive-thru|

---

US7912246B1|2002-10-28|2011-03-22|Videomining Corporation|Method and system for determining the age category of people based on facial images|

---

US7283650B1|2002-11-27|2007-10-16|Video Mining Corporation|Method and system for printing of automatically captured facial images augmented with promotional content|

---

US7734070B1|2002-12-31|2010-06-08|Rajeev Sharma|Method and system for immersing face images into a video sequence|

---

US10326921B2|2011-11-14|2019-06-18|Tseng-Lu Chien|Light device has built-in camera and related digital data device's functions|

---

US20040260513A1|2003-02-26|2004-12-23|Fitzpatrick Kerien W.|Real-time prediction and management of food product demand|

---

US7711155B1|2003-04-14|2010-05-04|Videomining Corporation|Method and system for enhancing three dimensional face modeling using demographic classification|

---

US7590261B1|2003-07-31|2009-09-15|Videomining Corporation|Method and system for event detection by analysis of linear feature occlusion|

---

US7505621B1|2003-10-24|2009-03-17|Videomining Corporation|Demographic classification using image components|

---

US20050096997A1|2003-10-31|2005-05-05|Vivek Jain|Targeting shoppers in an online shopping environment|

---

US7319779B1|2003-12-08|2008-01-15|Videomining Corporation|Classification of humans into multiple age categories from digital images|

---

US7100824B2|2004-02-27|2006-09-05|Evolution Robotics, Inc.|System and methods for merchandise checkout|

---

US7168618B2|2004-08-12|2007-01-30|International Business Machines Corporation|Retail store method and system|

---

US20060036485A1|2004-08-13|2006-02-16|International Business Machines Corporation|Methods and apparatus for presenting personalized information to consumers in a retail environment|

---

US7646887B2|2005-01-04|2010-01-12|Evolution Robotics Retail, Inc.|Optical flow for object recognition|

---

US9036028B2|2005-09-02|2015-05-19|Sensormatic Electronics, LLC|Object tracking and alerts|

---

US20070091177A1|2005-10-24|2007-04-26|The Regents Of The University Of California|Remote unattended camera and computer integrated security system|

---

US20070126871A1|2005-12-06|2007-06-07|Henninger Paul E Iii|Modular surveillance camera system with self-identification capability|

---

US8005314B2|2005-12-09|2011-08-23|Amnis Corporation|Extended depth of field imaging for high speed object analysis|

---

US7911482B1|2006-01-06|2011-03-22|Videomining Corporation|Method and system for efficient annotation of object trajectories in image sequences|

---

JP4125328B2|2006-04-17|2008-07-30|キヤノン株式会社|Electronic device, control method of peripheral device by electronic device, program, and storage medium|

---

US7930204B1|2006-07-25|2011-04-19|Videomining Corporation|Method and system for narrowcasting based on automatic analysis of customer behavior in a retail store|

---

US7974869B1|2006-09-20|2011-07-05|Videomining Corporation|Method and system for automatically measuring and forecasting the behavioral characterization of customers to help customize programming contents in a media network|

---

US7987111B1|2006-10-30|2011-07-26|Videomining Corporation|Method and system for characterizing physical retail spaces by determining the demographic composition of people in the physical retail spaces utilizing video image analysis|

---

US8380558B1|2006-12-21|2013-02-19|Videomining Corporation|Method and system for analyzing shopping behavior in a store by associating RFID data with video-based behavior and segmentation data|

---

US8189926B2|2006-12-30|2012-05-29|Videomining Corporation|Method and system for automatically analyzing categories in a physical space based on the visual characterization of people|

---

US8146811B2|2007-03-12|2012-04-03|Stoplift, Inc.|Cart inspection for suspicious items|

---

US8295597B1|2007-03-14|2012-10-23|Videomining Corporation|Method and system for segmenting people in a physical space based on automatic behavior analysis|

---

US7957565B1|2007-04-05|2011-06-07|Videomining Corporation|Method and system for recognizing employees in a physical space based on automatic behavior analysis|

---

EP2153641B2|2007-04-13|2021-10-27|Ari M. Presler|Digital cinema camera system for recording, editing and visualizing images|

---

US7848548B1|2007-06-11|2010-12-07|Videomining Corporation|Method and system for robust demographic classification using pose independent model from sequence of face images|

---

US7909248B1|2007-08-17|2011-03-22|Evolution Robotics Retail, Inc.|Self checkout with visual recognition|

---

US8520906B1|2007-09-24|2013-08-27|Videomining Corporation|Method and system for age estimation based on relative ages of pairwise facial images of people|

---

US10296936B1|2007-09-26|2019-05-21|Videomining Corporation|Method and system for measuring effectiveness of a marketing campaign on digital signage|

---

US20090158309A1|2007-12-12|2009-06-18|Hankyu Moon|Method and system for media audience measurement and spatial extrapolation based on site, display, crowd, and viewership characterization|

---

US20100280956A1|2007-12-26|2010-11-04|Johnson Controls Technology Company|Systems and methods for conducting commerce in a vehicle|

---

US8098888B1|2008-01-28|2012-01-17|Videomining Corporation|Method and system for automatic analysis of the trip of people in a retail space using multiple cameras|

---

US8330809B2|2008-02-04|2012-12-11|Fps Food Processing Systems, B.V.|Vision system with software control for detecting dirt and other imperfections on egg surfaces|

---

US20130215116A1|2008-03-21|2013-08-22|Dressbot, Inc.|System and Method for Collaborative Shopping, Business and Entertainment|

---

US8027521B1|2008-03-25|2011-09-27|Videomining Corporation|Method and system for robust human gender recognition using facial feature localization|

---

US8433612B1|2008-03-27|2013-04-30|Videomining Corporation|Method and system for measuring packaging effectiveness using video-based analysis of in-store shopper response|

---

US8009863B1|2008-06-30|2011-08-30|Videomining Corporation|Method and system for analyzing shopping behavior using multiple sensor tracking|

---

US8219438B1|2008-06-30|2012-07-10|Videomining Corporation|Method and system for measuring shopper response to products based on behavior and facial expression|

---

DE202008009834U1|2008-07-22|2009-12-10|Liebherr-Elektronik Gmbh|Camera for use in a digital network|

---

US8448859B2|2008-09-05|2013-05-28|Datalogic ADC, Inc.|System and method for preventing cashier and customer fraud at retail checkout|

---

US8379937B1|2008-09-29|2013-02-19|Videomining Corporation|Method and system for robust human ethnicity recognition using image feature-based probabilistic graphical models|

---

US8577705B1|2008-12-30|2013-11-05|Videomining Corporation|Method and system for rating the role of a product category in the performance of a store area|

---

US8175388B1|2009-01-30|2012-05-08|Adobe Systems Incorporated|Recognizing text at multiple orientations|

---

KR101511193B1|2009-02-27|2015-04-10|파운데이션 프로덕션, 엘엘씨|Headset-based telecommunications platform|

---

US8892469B2|2009-04-01|2014-11-18|Igt|Gaming device security mechanism|

---

US9747497B1|2009-04-21|2017-08-29|Videomining Corporation|Method and system for rating in-store media elements|

---

US8254633B1|2009-04-21|2012-08-28|Videomining Corporation|Method and system for finding correspondence between face camera views and behavior camera views|

---

US8638211B2|2009-04-30|2014-01-28|Icontrol Networks, Inc.|Configurable controller and interface for home SMA, phone and multimedia|

---

US8872964B2|2009-05-20|2014-10-28|Express Imaging Systems, Llc|Long-range motion detection for illumination control|

---

US9740977B1|2009-05-29|2017-08-22|Videomining Corporation|Method and system for recognizing the intentions of shoppers in retail aisles based on their trajectories|

---

US8812344B1|2009-06-29|2014-08-19|Videomining Corporation|Method and system for determining the impact of crowding on retail performance|

---

US8325982B1|2009-07-23|2012-12-04|Videomining Corporation|Method and system for detecting and tracking shopping carts from videos|

---

US8412656B1|2009-08-13|2013-04-02|Videomining Corporation|Method and system for building a consumer decision tree in a hierarchical decision tree structure based on in-store behavior analysis|

---

JP5257335B2|2009-11-24|2013-08-07|オムロン株式会社|Method for displaying measurement effective area in three-dimensional visual sensor and three-dimensional visual sensor|

---

WO2011071542A1|2009-12-13|2011-06-16|AisleBuyer LLC|Systems and methods for purchasing products from a retail establishment using a mobile device|

---

US8803888B2|2010-06-02|2014-08-12|Microsoft Corporation|Recognition system for sharing information|

---

JP2012028015A|2010-07-20|2012-02-09|Toshiba Corp|Illumination control system and illumination control method|

---

US8488881B2|2010-07-27|2013-07-16|International Business Machines Corporation|Object segmentation at a self-checkout|

---

US8615254B2|2010-08-18|2013-12-24|Nearbuy Systems, Inc.|Target localization utilizing wireless and camera sensor fusion|

---

US8652033B2|2010-09-23|2014-02-18|Karl Storz Endovision, Inc.|Video stylet with directable tip|

---

US20120173351A1|2010-12-29|2012-07-05|Qthru, Llc|Mobile Electronic Shopping|

---

US10474858B2|2011-08-30|2019-11-12|Digimarc Corporation|Methods of identifying barcoded items by evaluating multiple identification hypotheses, based on data from sensors including inventory sensors and ceiling-mounted cameras|

---

US20130103537A1|2011-10-14|2013-04-25|Spencer Thornton Hewett|Interactive consumer self-service shopping system|

---

WO2013059716A2|2011-10-19|2013-04-25|Ran Margalit|Automated purchasing system|

---

US20150095189A1|2012-03-16|2015-04-02|In Situ Media Corporation|System and method for scanning, tracking and collating customer shopping selections|

---

US9661047B2|2012-04-30|2017-05-23|Mobilatv Ltd.|Method and system for central utilization of remotely generated large media data streams despite network bandwidth limitations|

---

US9892438B1|2012-05-03|2018-02-13|Stoplift, Inc.|Notification system and methods for use in retail environments|

---

EP2848009B1|2012-05-07|2020-12-02|Dolby International AB|Method and apparatus for layout and format independent 3d audio reproduction|

---

US9147114B2|2012-06-19|2015-09-29|Honeywell International Inc.|Vision based target tracking for constrained environments|

---

US9774459B2|2012-06-22|2017-09-26|Sensormatic Electronics, LLC|Security system and method using wireless adapters and PoE cameras|

---

US20140082610A1|2012-09-14|2014-03-20|DewMobile Inc.|Mesh network and mesh network node application|

---

US9288299B2|2012-09-14|2016-03-15|Dewmobile, Inc.|Method and apparatus for file sharing in a network|

---

US9647906B2|2012-11-02|2017-05-09|Rockwell Automation Technologies, Inc.|Cloud based drive monitoring solution|

---

US20140155022A1|2012-12-05|2014-06-05|Anil Kandregula|Methods and apparatus to monitor usage of mobile devices|

---

US20140245160A1|2013-02-22|2014-08-28|Ubiquiti Networks, Inc.|Mobile application for monitoring and controlling devices|

---

US10198080B1|2013-03-11|2019-02-05|Amazon Technologies, Inc.|Virtual user interface|

---

US9392675B2|2013-03-14|2016-07-12|Lutron Electronics Co., Inc.|Digital load control system providing power and communication via existing power wiring|

---

US9330413B2|2013-03-14|2016-05-03|Sears Brands, L.L.C.|Checkout and/or ordering systems and methods|

---

US9613659B2|2013-03-15|2017-04-04|Fitbit, Inc.|Generating custom audio content for an exercise session|

---

US9098825B2|2013-03-26|2015-08-04|Leonard Bashkin|Storage container with inventory control|

---

US9213803B2|2013-05-02|2015-12-15|David Rolley|System and method for collecting, analyzing and reporting fitness activity data|

---

US9412099B1|2013-05-09|2016-08-09|Ca, Inc.|Automated item recognition for retail checkout systems|

---

US20140363059A1|2013-06-07|2014-12-11|Bby Solutions, Inc.|Retail customer service interaction system and method|

---

US9329682B2|2013-06-18|2016-05-03|Microsoft Technology Licensing, Llc|Multi-step virtual object selection|

---

US10268983B2|2013-06-26|2019-04-23|Amazon Technologies, Inc.|Detecting item interaction and movement|

---

US10176456B2|2013-06-26|2019-01-08|Amazon Technologies, Inc.|Transitioning items from a materials handling facility|

---

US10290031B2|2013-07-24|2019-05-14|Gregorio Reid|Method and system for automated retail checkout using context recognition|

---

US9473747B2|2013-07-25|2016-10-18|Ncr Corporation|Whole store scanner|

---

US20150046213A1|2013-08-07|2015-02-12|Motorola Solutions, Inc.|Method for identifying a shopping group in a store|

---

EP3031206B1|2013-08-09|2020-01-22|ICN Acquisition, LLC|System, method and apparatus for remote monitoring|

---

JP6361103B2|2013-09-17|2018-07-25|株式会社リコー|Management device, management system, object management method, and program|

---

JP5920299B2|2013-09-17|2016-05-18|コニカミノルタ株式会社|Image forming apparatus, remote control method, and remote control program|

---

US9141931B2|2013-09-26|2015-09-22|Amazon Technologies, Inc.|Inventory distribution method and system|

---

US9984352B2|2013-09-26|2018-05-29|Amazon Technologies, Inc.|Kiosk network in a kiosk management system|

---

US9474934B1|2013-10-11|2016-10-25|Fit Intuition, LLC|Biometric assessment in fitness improvement|

---

US9183620B2|2013-11-21|2015-11-10|International Business Machines Corporation|Automated tilt and shift optimization|

---

US20150161452A1|2013-12-11|2015-06-11|Echostar Technologies, Llc|Home Monitoring and Control|

---

EP3100250B1|2014-01-30|2019-03-13|Signify Holding B.V.|Controlling a lighting system using a mobile terminal|

---

US20150310601A1|2014-03-07|2015-10-29|Digimarc Corporation|Methods and arrangements for identifying objects|

---

US9948902B1|2014-03-07|2018-04-17|Alarm.Com Incorporated|Video camera and sensor integration|

---

US9120621B1|2014-03-25|2015-09-01|Amazon Technologies, Inc.|Verifying bin content in an automated materials handling facility|

---

US9317785B1|2014-04-21|2016-04-19|Video Mining Corporation|Method and system for determining ethnicity category of facial images based on multi-level primary and auxiliary classifiers|

---

US9918213B2|2014-05-07|2018-03-13|DewMobile Inc.|Discovery and networking of proximate wireless devices by acoustic messaging|

---

US20150373509A1|2014-06-19|2015-12-24|Dewmobile, Inc.|Group gaming platform for mobile devices in proximity|

---

JP5866522B2|2014-07-08|2016-02-17|パナソニックＩｐマネジメント株式会社|Facility management support apparatus, facility management support system, and facility management support method|

---

US10129507B2|2014-07-15|2018-11-13|Toshiba Global Commerce Solutions Holdings Corporation|System and method for self-checkout using product images|

---

US9547964B2|2014-07-24|2017-01-17|Heathco, Llc|Integrated home lighting and notification system|

---

EP3009997B1|2014-10-15|2016-11-23|Axis AB|Arrangement for a monitoring camera device|

---

US9262681B1|2014-11-19|2016-02-16|Amazon Technologies, Inc.|Probabilistic registration of interactions, actions or activities from multiple views|

---

US10594983B2|2014-12-10|2020-03-17|Robert Bosch Gmbh|Integrated camera awareness and wireless sensor system|

---

US10134004B1|2014-12-23|2018-11-20|Amazon Technologies, Inc.|Processing image data from a camera cluster|

---

US10722166B2|2014-12-30|2020-07-28|Ergoview S.R.L.|Method and system for biomechanical analysis of the posture of a cyclist and automatic customized manufacture of bicycle parts|

---

US9990587B2|2015-01-22|2018-06-05|Preferred Networks, Inc.|Machine learning heterogeneous edge device, method, and system|

---

US9412034B1|2015-01-29|2016-08-09|Qualcomm Incorporated|Occlusion handling for computer vision|

---

US9706619B2|2015-02-16|2017-07-11|Cree, Inc.|Lighting fixture with image sensor|

---

US9853730B2|2015-02-27|2017-12-26|Xicato, Inc.|Lighting based authentication of a mobile electronic device|

---

US9270634B1|2015-03-02|2016-02-23|Dewmobile, Inc.|Building a proximate social networking database based on relative distance profiling of two or more operably coupled computers|

---

CA2979263A1|2015-03-13|2016-09-22|Lutron Electronics Co., Inc.|Control device having an illuminated portion controlled in response to an external sensor|

---

US10089520B2|2015-03-26|2018-10-02|Krishna V Motukuri|System for displaying the contents of a refrigerator|

---

US20160289964A1|2015-04-02|2016-10-06|Shawn Engberg|Suspended ceiling|

---

WO2016155021A1|2015-04-03|2016-10-06|绿仕科技控股有限公司|Environmental control system|

---

US10217120B1|2015-04-21|2019-02-26|Videomining Corporation|Method and system for in-store shopper behavior analysis with multi-modal sensor fusion|

---

US10565455B2|2015-04-30|2020-02-18|Ants Technology Limited|Methods and systems for audiovisual communication|

---

US10037592B2|2015-06-05|2018-07-31|Mindaptiv LLC|Digital quaternion logarithm signal processing system and method for images and other data types|

---

CA2989894A1|2015-06-24|2016-12-29|Magic Leap, Inc.|Augmented reality devices, systems and methods for purchasing|

---

US9911290B1|2015-07-25|2018-03-06|Gary M. Zalewski|Wireless coded communication devices for tracking retail interactions with goods and association to user accounts|

---

US20190054347A1|2015-08-18|2019-02-21|Michael Saigh|Wearable sports guidance communication system and developers tool kit|

---

US10180469B2|2015-10-28|2019-01-15|Siemens Healthcare Gmbh|Gesture-controlled MR imaging system and method|

---

CN105335509B|2015-10-29|2017-06-30|广州神马移动信息科技有限公司|A kind of method for recommending action message, device and server|

---

US20170161703A1|2015-12-03|2017-06-08|Wal-Mart Stores, Inc.|Smart cart for self-checkout of retail merchandise|

---

US10915910B2|2015-12-09|2021-02-09|International Business Machines Corporation|Passive analysis of shopping behavior in a physical shopping area using shopping carts and shopping trays|

---

EP3391339A2|2015-12-18|2018-10-24|Iris Automation, Inc.|Real-time visual situational awareness system|

---

US10262331B1|2016-01-29|2019-04-16|Videomining Corporation|Cross-channel in-store shopper behavior analysis|

---

US20170216667A1|2016-02-02|2017-08-03|Gaming Grids Wearables, Llc|Esports fitness and training system|

---

WO2017149875A1|2016-02-29|2017-09-08|ソニー株式会社|Image capture control device, image capture device, and image capture control method|

---

US10198625B1|2016-03-26|2019-02-05|Videomining Corporation|Association of unique person to a mobile device using repeat face image matching|

---

US10387896B1|2016-04-27|2019-08-20|Videomining Corporation|At-shelf brand strength tracking and decision analytics|

---

WO2017192457A1|2016-05-02|2017-11-09|Focal Systems, Inc.|Expedited checkout system through portable checkout units|

---

US10339595B2|2016-05-09|2019-07-02|Grabango Co.|System and method for computer vision driven applications within an environment|

---

WO2017210330A1|2016-05-31|2017-12-07|Theia Group, Incorporated|System for transmission and digitization of machine telemetry|

---

US10354262B1|2016-06-02|2019-07-16|Videomining Corporation|Brand-switching analysis using longitudinal tracking of at-shelf shopper behavior|

---

US10659247B2|2016-07-09|2020-05-19|Grabango Co.|Computer vision for ambient data acquisition|

---

US10083358B1|2016-07-26|2018-09-25|Videomining Corporation|Association of unique person to point-of-sale transaction data|

---

BR102016019151A2|2016-08-18|2018-03-06|De Souza Lopes Roberto|METHOD AND COMPUTER VEHICLE DISPLAY AND IDENTIFICATION SYSTEM THROUGH CAMERAS APPLIED IN FUEL STATIONS AND CONVENIENCE STORES|

---

US10409548B2|2016-09-27|2019-09-10|Grabango Co.|System and method for differentially locating and modifying audio sources|

---

US10002344B2|2016-10-17|2018-06-19|Conduent Business Services, Llc|System and method for retail store promotional price tag detection|

---

WO2018125712A1|2016-12-30|2018-07-05|Datalogic Usa, Inc.|Self-checkout with three dimensional scanning|

---

CA3052292A1|2017-02-10|2018-08-16|Grabango Co.|A dynamic customer checkout experience within an automated shopping environment|

---

US20180240180A1|2017-02-20|2018-08-23|Grabango Co.|Contextually aware customer item entry for autonomous shopping applications|

---

US10458595B2|2017-02-28|2019-10-29|Cisco Technology, Inc.|Smart Power over Ethernet lift|

---

US10997421B2|2017-03-30|2021-05-04|Hrl Laboratories, Llc|Neuromorphic system for real-time visual activity recognition|

---

EP3610469A4|2017-05-10|2021-04-28|Grabango Co.|Series-configured camera array for efficient deployment|

---

AU2018289552A1|2017-06-21|2020-01-16|Grabango Co.|Linking observed human activity on video to a user account|

---

US10055853B1|2017-08-07|2018-08-21|Standard Cognition, Corp|Subject identification and tracking using image recognition|

---

US10474991B2|2017-08-07|2019-11-12|Standard Cognition, Corp.|Deep learning-based store realograms|

---

EP3665615A4|2017-08-07|2020-12-30|Standard Cognition, Corp.|Predicting inventory events using semantic diffing|

---

US10127438B1|2017-08-07|2018-11-13|Standard Cognition, Corp|Predicting inventory events using semantic diffing|

---

US10650545B2|2017-08-07|2020-05-12|Standard Cognition, Corp.|Systems and methods to check-in shoppers in a cashier-less store|

---

US11023850B2|2017-08-07|2021-06-01|Standard Cognition, Corp.|Realtime inventory location management using deep learning|

---

US10474988B2|2017-08-07|2019-11-12|Standard Cognition, Corp.|Predicting inventory events using foreground/background processing|

---

US10445694B2|2017-08-07|2019-10-15|Standard Cognition, Corp.|Realtime inventory tracking using deep learning|

---

US10133933B1|2017-08-07|2018-11-20|Standard Cognition, Corp|Item put and take detection using image recognition|

---

US20190079591A1|2017-09-14|2019-03-14|Grabango Co.|System and method for human gesture processing from video input|

---

US10469768B2|2017-10-13|2019-11-05|Fyusion, Inc.|Skeleton-based effects and background replacement|

---

US10963704B2|2017-10-16|2021-03-30|Grabango Co.|Multiple-factor verification for vision-based systems|

---

US20190205933A1|2018-01-03|2019-07-04|Grabango Co.|Marketing and couponing in a retail environment using computer vision|

---

WO2020092450A1|2018-10-29|2020-05-07|Grabango Co.|Commerce automation for a fueling station|

---

US10347009B1|2018-11-21|2019-07-09|Juan Ramon Terven|Self callbrating camera system|US10339595B2|2016-05-09|2019-07-02|Grabango Co.|System and method for computer vision driven applications within an environment|

---

US10659247B2|2016-07-09|2020-05-19|Grabango Co.|Computer vision for ambient data acquisition|

---

US11019162B2|2016-11-16|2021-05-25|Dell Products L.P.|System and method for provisioning a user interface for sharing|

---

CA3052292A1|2017-02-10|2018-08-16|Grabango Co.|A dynamic customer checkout experience within an automated shopping environment|

---

EP3610469A4|2017-05-10|2021-04-28|Grabango Co.|Series-configured camera array for efficient deployment|

---

AU2018289552A1|2017-06-21|2020-01-16|Grabango Co.|Linking observed human activity on video to a user account|

---

US10650545B2|2017-08-07|2020-05-12|Standard Cognition, Corp.|Systems and methods to check-in shoppers in a cashier-less store|

---

US10853965B2|2017-08-07|2020-12-01|Standard Cognition, Corp|Directional impression analysis using deep learning|

---

US11250376B2|2017-08-07|2022-02-15|Standard Cognition, Corp|Product correlation analysis using deep learning|

---

US11232687B2|2017-08-07|2022-01-25|Standard Cognition, Corp|Deep learning-based shopper statuses in a cashier-less store|

---

US10445694B2|2017-08-07|2019-10-15|Standard Cognition, Corp.|Realtime inventory tracking using deep learning|

---

US10474988B2|2017-08-07|2019-11-12|Standard Cognition, Corp.|Predicting inventory events using foreground/background processing|

---

US11200692B2|2017-08-07|2021-12-14|Standard Cognition, Corp|Systems and methods to check-in shoppers in a cashier-less store|

---

US11023850B2|2017-08-07|2021-06-01|Standard Cognition, Corp.|Realtime inventory location management using deep learning|

---

US10474991B2|2017-08-07|2019-11-12|Standard Cognition, Corp.|Deep learning-based store realograms|

---

US20190079591A1|2017-09-14|2019-03-14|Grabango Co.|System and method for human gesture processing from video input|

---

US10963704B2|2017-10-16|2021-03-30|Grabango Co.|Multiple-factor verification for vision-based systems|

---

JP6548279B1|2018-02-28|2019-07-24|Ｎｅｃプラットフォームズ株式会社|Self POS terminal|

---

US11029710B2|2018-12-31|2021-06-08|Wipro Limited|Method and system for real-time tracking of a moving target object|

---

US11245875B2|2019-01-15|2022-02-08|Microsoft Technology Licensing, Llc|Monitoring activity with depth and multi-spectral camera|

---

CA3131604A1|2019-03-01|2020-09-10|Grabango Co.|Cashier interface for linking customers to virtual data|

---

US10997414B2|2019-03-29|2021-05-04|Toshiba Global Commerce Solutions Holdings Corporation|Methods and systems providing actions related to recognized objects in video data to administrators of a retail information processing system and related articles of manufacture|

---

US11232575B2|2019-04-18|2022-01-25|Standard Cognition, Corp|Systems and methods for deep learning-based subject persistence|

---

FR3102872A1|2019-11-06|2021-05-07|Carrefour|Purchase and payment automation method and device in a physical merchant site|

---

JP2021096612A|2019-12-17|2021-06-24|東芝テック株式会社|Sales management device and control program thereof|

---

JP2021096624A|2019-12-17|2021-06-24|東芝テック株式会社|Shoppers management device, information processing program, shoppers management method, and shoppers management system|

---

JP2021096791A|2019-12-19|2021-06-24|東芝テック株式会社|Transaction processing system|

---

WO2021137219A1|2019-12-30|2021-07-08|Shopic Technologies Ltd.|System and method for fast checkout using a portable computerized device|

---

US11203370B2|2020-03-11|2021-12-21|Gatekeeper Systems, Inc.|Shopping cart monitoring using computer vision|

法律状态:
2021-11-03| B350| Update of information on the portal [chapter 15.35 patent gazette]|

优先权:

---

申请号 | 申请日 | 专利标题

---

US201762523183P| true| 2017-06-21|2017-06-21|

---

US62/523,183|2017-06-21|

---

PCT/US2018/038861|WO2018237210A1|2017-06-21|2018-06-21|Linking observed human activity on video to a user account|

---