digital predictive system, method and computer readable storage device

专利摘要:
digital prediction system, method and computer readable storage device. These are systems and techniques for facilitating digital data prediction. A system may process a body of stored data, generate respective digital signatures representing respective subsets of the body of stored data, and mark respective digital signatures with markings corresponding to extrinsic events. Digital signatures can be stored and indexed in a digital signature library. The system can also compare a new digital signature with learned digital signatures to identify one or more matches, and predict a future event associated with the new digital signature based on the matches and inferences generated for the learned digital signatures.
公开号:BR102017012278A2
申请号:R102017012278
申请日:2017-06-09
公开日:2018-10-30
发明作者:Alan Phillips Richard
申请人:Gen Electric；
IPC主号:

专利说明:

(54) Title: DIGITAL PROGNOSTICS SYSTEM, METHOD AND LEGIBLE STORAGE DEVICE BY COMPUTER (51) Int. Cl .: G06F 21/32 (30) Unionist Priority: 06/10/2016 EP 16173941.2 (73) Holder (s) : GENERAL ELECTRIC COMPANY (72) Inventor (s): RICHARD ALAN PHILLIPS (85) National Phase Start Date:
06/06/2017 (57) Abstract: DIGITAL PROGNOSTICS SYSTEM, METHOD AND STORAGE DEVICE BY COMPUTER. These are systems and techniques to facilitate predictions of digital data. A system can process a body of stored data, generate respective digital signatures that represent respective subsets of the body of stored data and mark the respective digital signatures with markings that correspond to extrinsic events. Digital signatures can be stored and indexed in a digital signature library. The system can also compare a new digital signature with learned digital signatures in order to identify one or more matches, and predict a future event associated with the new digital signature based on the correspondences and inferences generated for the learned digital signatures.
L

1/56 "DIGITAL PROGNOSTICS SYSTEM, METHOD AND STORAGE DEVICE BY COMPUTER"
Field of Technique [001] This disclosure refers, in general, to predictions of digital data processing (for example, through the use of artificial intelligence).
Background [002] A vast amount of data (for example, trillions of bytes) is generated daily by various devices connected to the network and / or systems connected to the network (for example, sensors, mobile devices, device records, controllers, etc.). ) all over the world. Such data is often saved in a cloud-based data infrastructure (or infrastructure), and typically stored as unstructured data. Consequently, processing, searching and / or analyzing the voluminous amounts of unstructured data is computationally expensive, not to mention the difficulty. In addition, collecting insights from data stored in a cloud-based data infrastructure is, in general, time-consuming and / or difficult to achieve.
Short Description [003] The following is a simplified summary description of the specification in order to provide a basic understanding of some aspects of the specification. This brief description is not an extensive overview of the specification. It is not intended to identify key or crucial elements of the specification, nor to outline any scope of particular deployments of the specification or any scope of the claims. Its sole purpose is to present some concepts of the description in a simplified way as a prelude to the more detailed description that is presented later.
Petition 870170039394, of 06/09/2017, p. 15/89
2/56 [004] In accordance with an exemplary deployment, a system includes a data signature generation component, a tagging component, an artificial intelligence component, a search component, a prediction component and a display component . The data signature generation component processes a stored body or set of data and generates respective digital signatures that represent respective subsets of the stored data body. Digital signatures are stored and indexed in a digital signature library. The marking component marks the respective digital signatures with markings that correspond to extrinsic events. The artificial intelligence component learns the respective digital signatures and associated markings, and generates inferences about the respective digital signatures. The search component, searches and compares a new digital signature with the digital signatures learned in order to identify one or more matches. The prognostication component predicts a future event associated with the new digital signature based, at least in part, on the inferences generated and the correspondences. The display component generates a user interface, for display, that outputs the predictions in a format interpretable by humans.
[005] Additionally, an implementation without limitation is provided to generate a first digital signature based on a portion of stored data, to mark the first digital signature with a mark that corresponds to an event extrinsic to the system, to store the first digital signature in a digital signature library, generate inferences about the first digital signature, compare a second digital signature with the first digital signature in order to identify a match, identify a future event associated with the second signature
Petition 870170039394, of 06/09/2017, p. 16/89
3/56 digital based, at least in part, on inferences and correspondence, and generate a user interface that emits information associated with the future event in a format interpretable by humans through a display.
[006] In accordance with another exemplary implantation, a computer-readable storage device that comprises instructions that, in response to execution, cause a system that comprises a processor to perform operations that comprise: generating a first electronic fingerprint based on a portion of data stored in a first data store, generate a mark for the first electronic fingerprint to associate the first electronic fingerprint with an extrinsic event, store the first electronic fingerprint in a second data store, determine inferences associated with first electronic fingerprint, identify a correspondence between a second electronic fingerprint and the first electronic fingerprint, identify a future event associated with the second electronic fingerprint based, at least in part, on inferences and correspondence, and present associated information s to the future event in a format interpretable by humans through a user interface associated with a display.
[007] The following description and the attached Figures present certain illustrative aspects of the specification. These aspects are indicative, however, of just a few of the many ways in which the principles of the specification can be employed. Other advantages and innovative features of the specification will become apparent from the following detailed description of the specification when considered in combination with the Figures.
Brief Description of the Figures [008] Various aspects, implantations, objects and advantages of
Petition 870170039394, of 06/09/2017, p. 17/89
4/56 the present invention will be apparent upon consideration of the following detailed description, obtained in combination with the attached Figures, in which similar reference characters refer to similar parts throughout the description, and in which:
Figure 1 illustrates a high-level block diagram of an exemplary pattern detection component, in accordance with the various aspects and implementations described in this document;
Figure 2 illustrates an exemplary system for storing data provided by assets, in accordance with the various aspects and implementations described in this document;
Figure 3 illustrates an exemplary system for providing stored data to a pattern detection component, in accordance with the various aspects and implementations described in this document;
Figure 4 illustrates an exemplary system for displaying information provided by a pattern detection component, in accordance with the various aspects and implementations described in this document;
Figure 5 illustrates another example system for displaying information provided by a pattern detection component, in accordance with the various aspects and implementations described in this document;
Figure 6 illustrates an exemplary system associated with the stored data, in accordance with the various aspects and implementations described in this document;
Figure 7 illustrates another exemplary system associated with the stored data, in accordance with the various aspects and implementations described in this document;
Figure 8 illustrates an exemplary user interface in
Petition 870170039394, of 06/09/2017, p. 18/89
5/56 connection with a pattern detection component, in accordance with various aspects and implementations described in this document;
Figure 9 represents a flowchart of an exemplary method for identifying, predicting and / or managing an event associated with a stored data body, in accordance with the various aspects and implementations described in this document;
Figure 10 represents a flowchart of an exemplary method for generating and / or storing digital signatures, in accordance with the various aspects and implementations described in this document;
Figure 11 represents a flowchart of an exemplary method for employing digital signatures to identify, predict and / or manage an event associated with the stored data, in accordance with the various aspects and implementations described in this document;
Figure 12 is a schematic block diagram that illustrates a suitable operating environment; and
Figure 13 is a schematic block diagram of a sample computing environment.
Detailed Description [009] Several aspects of this disclosure are now described with reference to the Figures, in which similar reference numerals are used to refer to similar elements throughout the description. In the following description, for explanatory purposes, several specific details are presented in order to provide a thorough understanding of one or more aspects. It must be understood, however, that certain aspects of this disclosure can be practiced without these specific details, or with other methods, components, materials, etc. In other cases, well-known structures and devices are shown in the form of a block diagram to facilitate
Petition 870170039394, of 06/09/2017, p. 19/89
6/56 description of one or more aspects.
[010] Systems and techniques for employing a digital standard to facilitate predictions of digital data are presented. For example, a digital library of electronic fingerprints (for example, digital signatures, digital standards) can be created. An electronic fingerprint stored in the digital library may include one or more parameters and corresponding values over a period of time. For example, an electronic fingerprint can be a subset of parametric time series data derived from a parametric time series data stream and / or a parametric time series data set. Artificial intelligence can also be employed to learn about electronic fingerprints in the digital library and / or to identify correlations between electronic fingerprints and anomalies (for example, unique behavior) associated with time series data. Anomalies associated with time series data may be related to the particular graphic characteristics associated with time series data. For example, anomalies can be identified from time series data based on peaks in time series data, valleys in time series data, a rate of change associated with time series data, etc. These anomalies can also predict and / or be associated with an event (for example, an extrinsic event). For example, an event (for example, an extrinsic event) can be associated with an asset and / or an external system that provides and / or generates time series data for electronic fingerprints. Markings can also be generated for electronic fingerprints stored in the digital library to facilitate identification of similar anomalies and / or similar events in other portions of the time series data. In response to learning and / or correlations determined for electronic fingerprints through one or more
Petition 870170039394, of 06/09/2017, p. 20/89
7/56 artificial intelligence techniques, the markings can also be updated.
[011] Instead of a conventional system that searches for unstructured data sets of time series data, the digital fingerprint library and / or markings can be used to search for other portions of time series data (for example, other portions of the time series data stored in one or more databases and / or included in a time series data stream) for similar anomalies and / or similar events. The digital library of electronic fingerprints and / or markings can be additionally or alternatively employed for use in analyzes as conditional claims to trigger the execution of one or more actions. In addition, the digital library of electronic fingerprints can be repeatedly updated and / or refined over time to facilitate the identification of similar anomalies and / or similar events in other time series data portions. Using the digital library of electronic fingerprints and / or the markings, trends and / or particular behaviors in time series data can be detected, so that a conventional data training algorithm would not, in general, have the capacity to detect. For example, the digital library of electronic fingerprints can facilitate the detection of anomalies in data associated with an asset system without the knowledge of past anomalies associated with the asset system. In comparison to a conventional system, the digital library of electronic fingerprints and / or markings can also provide improved accuracy, reduced time and / or greater adaptability to predict anomalies and / or behavior associated with time series data. The digital library of electronic fingerprints and / or markings can also be used to analyze a system associated with time series data and / or to perform an analysis based on the usefulness of a system associated with time data.
Petition 870170039394, of 06/09/2017, p. 21/89
8/56 time series. In this way, the management of time series data and / or systems associated with time series data can be improved.
In addition, the performance of systems that generate and / or provide time series data can be improved and / or the costs associated with the systems can be reduced.
[012] With reference initially to Figure 1, an exemplary system 100 is illustrated that identifies, generates and / or manages a digital pattern to facilitate the predictions of digital data, according to an aspect of the submitted disclosure. System 100 can be deployed on or in connection with a server network associated with an enterprise application (for example, a corporate network of connected machines). System 100 can be used by various systems, such as, but not limited to, industrial systems, aviation systems, manufacturing systems, factory systems, energy management systems, electrical grid systems, water supply systems, transport systems, healthcare systems, refinery systems, media systems, research systems, financial systems, data driven forecasting systems, machine learning systems, neural network systems, network systems, computer network systems , communication systems, router systems, server systems, high availability server systems (for example, telecommunication server systems), web server systems, file server systems, data server systems, array systems disk, powered insert card systems, cloud based systems and the like. In one example, system 100 can be associated with a platform as a service (PaaS) and / or an asset performance management system. In another example, system 100 may be a digital prediction system. In addition, system 100 and / or system components 100 may be employed to use hardware and / or
Petition 870170039394, of 06/09/2017, p. 22/89
9/56 software to solve problems that are highly technical in nature (for example, related to machine learning, related to digital data processing prognosis, related to digital data analysis, etc.), which are not abstract and which they cannot be performed as a set of mental acts by a human being.
[013] System 100 may include a pattern detection component 102. Pattern detection component 102 may be communicatively coupled to a digital signature library 104. In Figure 1, pattern detection component 102 includes a data signature generation 106, a tagging component 108, an artificial intelligence component 110, a search component 112, a prediction component 114 and a display component 116. Aspects of the systems, devices or processes explained in this disclosure may constitute machine executable component (or components) embedded within a machine (or machines), for example, embedded in one or more computer-readable media (or media) associated with one or more machines. Such component (or components), when run by one or more machines, for example, computer (or computers), computing device (or computing devices), virtual machine (or virtual machines), etc. can cause the machine (or machines) to perform the described operations. System 100 (for example, pattern recognition component 102) can include memory 120 for storing computer executable components and instructions. System 100 (for example, pattern recognition component 102) may additionally include a processor 118 to facilitate the operation of instructions (for example, computer-executable components and instructions) through system 100 (for example, the recognition component standard 102).
Petition 870170039394, of 06/09/2017, p. 23/89
10/56 [014] The pattern recognition component 102 (for example, the data signature generation component 106) can receive the stored data (for example, STORED DATA shown in Figure 1). The stored data can be received from one or more databases (for example, a network of databases). For example, stored data can be associated with data stored on a network of servers. The stored data can also be a body of stored data generated by and / or associated with a plurality of data sources. For example, stored data can be generated by and / or associated with various assets, various types of devices, various types of machines and / or various types of equipment. In addition, the plurality of data sources can be located in a plurality of locations (for example, a plurality of geographical locations). Aspects of the plurality of data sources can also be dynamic. For example, a data source associated with stored data can be a mobile asset or a mobile machine (for example, a data source location may vary, etc.).
[015] The stored data can be time series data. The stored data can also be, for example, a set of parametric data that includes one or more parameters and corresponding data values. The stored data may include various data, such as, but not limited to, sensor data, process data (for example, process log data), operational data, monitoring data, maintenance data, parameter data, data measurement data, performance data, d audio data, image data, video data, industrial data, machine data, asset data, equipment data, device data, meter data, real-time data, historical data and / or other data. For example, stored data
Petition 870170039394, of 06/09/2017, p. 24/89
11/56 can be associated with an audio system, a vibration detection system, a temperature detection system, an image system, a video capture system, a pressure detection system, a pressure detection system flow rate, electric current sensors, voltage detectors, a thermal charging system and / or another system associated with time series data. The stored data can also be encrypted data, processed data and / or raw data. In an example without limitation, stored data can be associated with data collected from multiple assets for an airline (for example, multiple aircraft, multiple airline flights, etc.) and / or multiple corporate systems associated with multiple airlines aerial. However, it must be verified that the stored data can be associated with different systems, such as, without limitation, industrial systems, aviation systems, manufacturing systems, factory systems, energy management systems, power grid systems , water supply systems, transportation systems, healthcare systems, refinery systems, media systems, financial systems, research systems, PaaS systems, asset performance management systems, other corporate systems, etc.
[016] The data signature generation component 106 can process the stored data and can also generate digital signatures (or digital signatures) for the stored data. For example, the data signature generation component 106 can generate respective digital signatures that represent respective subsets of the stored data body. A digital signature can be associated with electronic fingerprint data that represents a digital standard. For example, a digital signature can be an electronic fingerprint that comprises electronic fingerprint data (for example, a string
Petition 870170039394, of 06/09/2017, p. 25/89
12/56 bits) associated with a portion of the stored data. A digital signature can also include a set of data values for one or more parameters over a defined period of time. In this way, a set of data values for one or more parameters over a defined period of time can represent an electronic fingerprint for an event. In certain deployments, a digital signature can comprise a sequence of digital subprints. In addition, a digital signature can identify and / or carry only a portion of the stored data. For example, a digital signature can be a data element that encodes a portion of the stored data. A digital signature can also be associated with a time stamp and / or a period of time. In addition, a digital signature can represent a digital standard for a portion of the stored data. For example, a digital signature can be generated based on physical characteristics of the stored data, such as spikes in stored data, coupons in stored data, rate of change associated with stored data, an interval of time between a first spike in stored data and a second spike in the stored data and / or other graphical characteristics of the stored data. In this way, a digital signature can carry trends (for example, graphical trends) and / or predict anomalies in the stored data. In addition, the data signature generation component 106 can generate a digital signature without prior knowledge of the anomalies associated with the stored data. For example, the data signature generation component 106 can generate a digital signature in real time based on extrinsic evidence related to environmental conditions, environmental evidence and / or other conditions related to an asset system associated with the stored data.
Petition 870170039394, of 06/09/2017, p. 26/89
13/56 [017] The data signature generation component 106 can employ one or more electronic fingerprint techniques (for example, one or more electronic fingerprint algorithms) to map the data stored in the digital signatures to the stored data . For example, the data signature generation component 106 may employ a hashing technique to generate digital signatures for the stored data. In another example, the data signature generation component 106 may employ a location-sensitive hashing technique to generate digital signatures for the stored data. In yet another example, the data signature generation component 106 may employ a random hashing technique to generate digital signatures for the stored data. In a deployment, a digital signature can comprise min-hash values associated with a portion of the stored data. For example, a digital signature may comprise a vector of min-hash values associated with a portion of the stored data. In another example, a digital signature may comprise a band of minimum hash values associated with a portion of the stored data. In yet another example, a digital signature may comprise a hash band sensitive to the location of min-hash values associated with a portion of the stored data. Digital signatures for stored data can also be associated with a set of min-hash signatures, a set of weighted min-hash signatures and / or a set of independent permutation min-wise for stored data. However, it must be verified that other types of electronic digital printing techniques and / or hashing techniques can be used to generate digital signatures for the stored data.
[018] A digital signature generated by the data signature generation component 106 can be associated with an event (for example, a
Petition 870170039394, of 06/09/2017, p. 27/89
14/56 extrinsic event). An event (for example, an extrinsic event) can be an event related to a system associated with the stored data and / or the plurality of data sources (for example, the plurality of data sources that generate by and / or are associated with stored data). An event (for example, an extrinsic event) can be, additionally or alternatively, a process related to a system associated with the stored data and / or the plurality of data sources (for example, the plurality of data sources that generate by and / or are associated with the stored data). For example, an event (for example, an extrinsic event) can be associated with extrinsic evidence for a system associated with stored data and / or the plurality of data sources. In an example without limitation, an event (for example, an extrinsic event) can be a condition in a factory or a condition for a machine in a factory. In another example without limitation, an event (for example, an extrinsic event) can be a condition for a device associated with a controller. In yet another example without limitation, an event (for example, an extrinsic event) can be a condition related to an asset associated with the stored data. The event (for example, the extrinsic event) can also be associated with time stamp information, location information and / or device information. A digital signature generated by the data signature generating component 106 may include a sequence of values for one or more parameters during a time interval before an event. Additionally, in certain deployments, a digital signature generated by the data signature generation component 106 may include another sequence of values for the one or more parameters during another time interval after the event. In one aspect, the data signature generating component 106 can generate a digital signature in response to an event (for example, an extrinsic event). For example, the
Petition 870170039394, of 06/09/2017, p. 28/89
15/56 data signature 106 can identify an event associated with the stored data and / or a certain time value for the event. Alternatively, the data signature generating component 106 may receive an indication of an event associated with the stored data and / or a certain time value for the event. For example, the data signature generating component 106 can generate a data signature in response to feedback data (e.g., input data) that identifies an event at a certain time. The identification of the event at a certain time can be determined, for example, by a user who interacts with a user interface on a display.
[019] Marking component 108 can mark the respective digital signatures with markings that correspond to events (for example, extrinsic events). For example, the dialing component 108 can associate the respective digital signatures with the respective identifiers associated with the respective events (for example, respective extrinsic events). In this way, a marked digital signature can also be associated with an event. A set of data values for one or more parameters over a defined period of time for an event can represent an electronic fingerprint. Tagging component 108 can store one or more tags for each digital signature stored in digital signature library 104. A tag can be data (for example, metadata) assigned to a digital signature that identifies an event and / or other information associated with a digital signature. Information associated with a tag can include, for example, text, comments, a description, a time stamp, images, etc.
[020] A digital signature that is marked by the dialing component 108 can be stored in the digital signature library 104.
Petition 870170039394, of 06/09/2017, p. 29/89
16/56
For example, digital signature library 104 may include a set of tagged digital signatures. Alternatively, digital signature library 104 can store digital signatures without tags. When storing a set of marked digital signatures and / or a set of digital signatures, the digital signature library 104 can be employed as a library of digital standards and / or a library of grouped parameters. Digital signature library 104 can be a data store (for example, a database) that stores digital signatures generated by data signature generation component 106 and / or tagged by markup component 108. In a deployment, the digital signature library 104 may be separate from pattern detection component 102. In another deployment, pattern detection component 102 may include digital signature library 104.
[021] The set of tagged digital signatures that are stored in the digital signature library 104 can be used to detect future events associated with the events represented by the set of tagged digital signatures. To facilitate the detection of future events, the artificial intelligence component 110 can learn the respective digital signatures and associated markings. The artificial intelligence component 110 can also generate inferences about the respective digital signatures. The artificial intelligence component 110 can employ artificial intelligence principles to facilitate learning and / or the generation of inferences for the respective digital signatures and / or associated markings. The artificial intelligence component 110 can perform learning explicitly or implicitly. The learning and / or inferences generated by the artificial intelligence component 110 can facilitate the identification and / or classification of different patterns associated with the stored data.
Petition 870170039394, of 06/09/2017, p. 30/89
17/56 [022] The artificial intelligence component 110 may also employ an automatic classification system and / or an automatic classification process to facilitate learning and / or the generation of inferences for the respective digital signatures and / or associated markings. For example, the artificial intelligence component 110 may employ probabilistic and / or statistics-based analysis (for example, taking into account utilities and costs in the analysis) to learn and / or generate inferences for the respective digital signatures and / or markings associated companies. The artificial intelligence component 110 may employ, for example, a support vector machine classifier (SVM) to learn and / or generate inferences for the respective digital signatures and / or associated markings. In addition or alternatively, the artificial intelligence component 110 may employ other classification techniques associated with Bayesian networks, decision trees and / or probabilistic classification models. Classifiers employed by the artificial intelligence component 110 can be explicitly trained (for example, through generic training data) as well as implicitly trained (for example, by observing user behavior, receiving extrinsic information). For example, with regard to SVM's that are well understood, SVM's are configured through a learning or training phase within a resource selection module and classifier manufacturer. A classifier is a function that maps an input attribute vector, x = (x1, x2, x3, x4, xn), with a confidence that the input belongs to a class - that is, f (x) = confidence ( class). The artificial intelligence component 110 can also employ, in certain deployments, historical data in addition to the stored data to facilitate learning and / or generating inferences for the respective digital signatures and / or associated markings.
Petition 870170039394, of 06/09/2017, p. 31/89
18/56 [023] In one aspect, the artificial intelligence component 110 can include an inference component that can additionally highlight automated aspects of the artificial intelligence component 110 that uses, in part, schema based inference to facilitate learning and / or generating inferences for the respective digital signatures and / or associated markings. The artificial intelligence component 110 can employ any techniques based on machine learning, techniques with statistical basis and / or techniques with a probabilistic basis. For example, the artificial intelligence component 110 can employ specialized systems, fuzzy logic, SVMs, hidden Markov models (HMMs), ambitious search algorithms, rules-based systems, Bayesian models (for example, Bayesian networks), neural networks, other nonlinear training techniques, data fusion, utility-based analytical systems, systems using Bayesian models, etc.
[024] In another aspect, the artificial intelligence component 110 can perform a set of machine learning computations associated with the stored data. For example, artificial intelligence component 110 can perform a set of cluster machine learning computations, a set of decision tree machine learning computations, a set of example machine learning computations, a set regression machine learning computations, a smoothing machine learning computations set, a rule learning machine learning computations set, a Bayesian machine learning computations set, a set of machine learning computations Deep Boltzmann, a set of deep belief network computations, a set of convolution neural network computations, a set of autocoder computations
Petition 870170039394, of 06/09/2017, p. 32/89
19/56 stacked and / or a set of different machine learning computations. Learned digital signatures associated with the artificial intelligence component 110 can be stored, for example, in the digital signature library 104. Digital signatures and / or markings stored in the digital signature library 104 can also be repeatedly updated by the data signature generation component. 106 and / or by tagging component 108 in response to new stored data received by pattern detection component 102 and / or learning and inferences associated with artificial intelligence component 110. In this way, digital signature library 104 can be repeatedly built and / or refined over a period of time.
[025] Search component 112 can search and / or compare a new digital signature with the digital signatures learned in order to identify one or more matches. For example, after a new digital signature is generated by the data signature generation component 106 using the techniques disclosed in this document, the search component 112 can compare the new digital signature with the learned digital signatures. The data signature generating component 106 can generate the new digital signature in response to receiving a portion of the stored data associated with the new digital signature. The new digital signature can be associated with a portion of the stored data that is different from the other portions of the stored data associated with the learned digital signatures. A match between a new digital signature for learned digital signatures can indicate a matched event. Search component 112 can determine whether the new digital signature is similar to one or more of the learned digital signatures. For example, search component 112 can compute similarities between the new digital signature and digital signatures
Petition 870170039394, of 06/09/2017, p. 33/89
20/56 learned. A new digital signature can be determined to match a learned digital signature if a pattern from the new digital signature matches the learned digital signature. A match between a new digital signature and a learned digital signature can be, for example, approximately an exact match. Alternatively, a correspondence between a new digital signature and a learned digital signature can be, for example, fuzzy correspondence. The search component 112 can compute similarities based on learning and / or inferences determined by the artificial intelligence component 110. Additionally, the search component 112 can compute similarities based on one or more pattern recognition techniques and / or one or more statistical techniques.
[026] Search component 112 can compute similarity, in one example, based on hashing scheme values (for example, min-hash data values) of the new digital signature and corresponding hashing scheme values (for example, corresponding min-hash data) of a learned digital signature. Additionally or alternatively, the search component 112 can compute similarities between the new digital signature and the digital signatures learned based on a metric distance. For example, the search component 112 can compute similarities between the new digital signature and the digital signatures learned based on a Hammimg distance. In another example, the search component 112 can compute similarity between the new digital signature and the digital signatures learned based on a Jaccard distance. However, other mechanisms for computing similarity between the new digital signature and the learned digital signatures can be employed.
[027] In one aspect, search component 112 can
Petition 870170039394, of 06/09/2017, p. 34/89
21/56 compare the new digital signature with the set of marked digital signatures stored in the digital signature library 104 before the digital signature is stored in the digital signature library 104. For example, before a digital signature is stored in the digital signature library 104, the search component 112 can determine whether a previously generated data signature that matches the digital signature is stored in the digital signature library 104. In another aspect, the search component 112 can determine that the new digital signatures match a signature digital among digital signatures stored in digital signature library 104 (for example, search component 112 may determine that new digital signatures correspond to a learned digital signature among learned digital signatures stored in digital signature library 104).
[028] The forecast component 114 can predict a future event associated with the new digital signature based, at least in part, on the inferences generated and the correspondences. For example, the prediction component 114 may associate the new digital signature with an event in response to a determination that the new digital signature corresponds to a learned digital signature among the learned digital signatures. The forecast component 114 can also correlate an event with an asset and / or a system associated with the event. In one aspect, the prediction component 114 may trigger one or more actions in response to a determination that the new digital signature corresponds to a learned digital signature among the learned digital signatures. An action can be, for example, the execution of a certain task or a certain function. An action can be external to system 100. For example, an action can be associated with an asset and / or a system associated with stored data. In another example, an action can be associated with a
Petition 870170039394, of 06/09/2017, p. 35/89
22/56 analytical process related to the stored data. For example, learned digital signatures can be used as conditional claims in analyzes that trigger the execution of an analytical engine.
[029] The display component 116 can generate a user interface, for display, that outputs the predictions in a format interpretable by humans. Display component 116 can render a display to and / or receive data from a display device or component, such as a monitor, television, computer, mobile device, browser or the like. In one example, the predictions and / or information associated with the predictions can be presented graphically in an easily understandable way. The predictions and / or information associated with the predictions can be presented as one or more among alphanumeric characters, illustrations, animations, audio and video. Additionally, the predictions and / or information associated with the predictions can be static or dynamically updated to provide real-time information as changes or events occur.
[030] The display component 116 can display and / or facilitate the display of one or more display elements associated with the predictions. The display component 116 can generate, receive, retrieve or otherwise obtain a graphic element (e.g., a graphic representation) associated with the predictions. In accordance with one aspect, a graphic element (e.g., a graphic representation) provided by the display component 116 can form the entire display or part of it rendered on a display device. In addition to the graphical representation, one or more items can form part of the display. In one example, the display component 116 can generate a notification associated with the predictions, a message associated with the predictions, an icon associated with the predictions,
Petition 870170039394, of 06/09/2017, p. 36/89
23/56 a thumbnail associated with the prognoses, a dialog box associated with the prognoses, a tool associated with the prognoses, a graphic interface accessory associated with the prognoses, a graph associated with the prognoses and / or another display element associated with the prognoses. A display element associated with the predictions can be transparent, translucent or opaque. A display element associated with the predictions can also be of various sizes, various colors, of various luminosities and so on, as well as being animated (for example, for appearance and disappearance, etc.).
[031] In one embodiment, the display component 116 can present information associated with a digital signature by means of a graphic. For example, display component 116 can display one or more parameters and / or a set of values over time on a graph. The display component 116 can also modify the graph based on user feedback data. For example, a user can advance back and forth through a geometric time axis on the graph. A user can also select a portion of the chart (for example, a horizontal portion of the chart) using a cursor. When selecting a portion of the chart, a user can add data (for example, metadata) to a digital signature associated with the chart. For example, a user can add data associated with an event (for example, an event associated with a digital signature), add data associated with an asset (for example, an asset associated with a digital signature), other associated data, such as a model , date / time, title, etc. Markup component 108 can generate and / or update a markup for a digital signature based on data provided by a user through a graph and / or a user interface.
[032] In another deployment, a digital signature can be
Petition 870170039394, of 06/09/2017, p. 37/89
24/56 generated based on information presented by the display component 116. For example, the data signature generation component 106 can employ data received through a display device associated with the information provided by the display component 116. In a example without limitation, the display component 116 can display one or more parameters and / or a set of values over time in a graph. A user can move back and forth through a geometric time axis of the graph. A user can also select a portion of the chart (for example, a horizontal portion of the chart) using a cursor. Based on the selection of portion of the graph, the data signature generation component 106 can generate a digital signature. For example, an electronic fingerprint can be generated based on the portion of the graph that is selected by the user.
[033] Although Figure 1 represents separate components in the pattern detection component 102, it should be noted that two or more components can be deployed in a common component. In addition, it can be seen that system design 100 and / or pattern detection component 102 can include other component selections, component settings, etc., to facilitate digital data predictions.
[034] Referring now to Figure 2, an unrestricted deployment of a system 200 is illustrated in accordance with various aspects and deployments of this disclosure. System 200 includes one or more assets 2021-N and a database 204. The one or more assets 2021-N and database 204 can be communicating over a network 206. Network 206 can be a network communication network, a wireless network, an internet protocol (IP) network, a voIP network, an internet telephone network, a mobile telecommunications network and / or another type of network. An asset among
Petition 870170039394, of 06/09/2017, p. 38/89
25/56 the one or more active 202i-n can be a device, a machine, a vehicle, equipment, a controller device (for example, a programmable logic controller), a data acquisition and supervisory control device (SCADA ), a meter device, a monitoring device (for example, a remote monitoring device), a network-connected device, a sensor device, a remote terminal unit, a telemetry device, a user interface device ( for example, a human-machine interface device), a historian device, a computing device, another type of asset, etc. The one or more active 2021-n can also supply data (e.g., encrypted data) to database 204 via network 206.
[035] In an example shown in Figure 2, a first asset 202i can generate and / or provide first data (for example, FIRST DATA shown in Figure 2). In addition, an N-th asset 202n can generate and / or provide N-th data (for example, N-th data shown in Figure 2). In certain deployments, the first asset 202i may be located in a first location (for example, a first geographic location) and the N-th asset 202n may be located in an N-th location (for example, an N-th geographical location ) which is different from the first location. The first data and N-th data can be transmitted to database 204 via network 206. The first data and N-th data can be transmitted to database 204 as encoded signals. Then, the first data and the Nth data can be stored in database 204 as stored data 208. Stored data 208 can correspond to stored data supplied to pattern detection component 102 (for example, stored data shown in Figure 1). In one aspect, database 204 may be a set of servers that store stored data 208
Petition 870170039394, of 06/09/2017, p. 39/89
26/56 (for example, database 204 can include multiple servers that store stored data 208).
[036] The one or more 2021-n assets can generate and / or provide time series data. The one or more active 2021-n can also be associated with an audio system, a vibration detection system, a temperature detection system, an image system, a video capture system, a pressure detection system , a flow rate detection system, an electric current sensor system, a voltage detector system, a thermal charging system and / or another type of system associated with time series data. Time series data generated and / or provided by one or more active 2021-n can be raw data. Additionally, in certain deployments, database 204 can process time series data generated and / or provided by one or more assets 2021-n to generate processed data. Therefore, stored data 208 can be processed data, in certain deployments. The stored data 208 can be structured data, semi-structured data and / or unstructured data. The stored data 208 can also be stored time series data. In one example, database 204 can be associated with a distributed parallel architecture to store stored data 208. In another example, database 204 can be associated with a storage repository for stored data 208 and / or a processing engine to process data provided by one or more assets 2021-n into stored data 208 (for example, database 204 may be a data lake).
[037] With reference to Figure 3, an unrestricted deployment of a system 300 is illustrated in accordance with various aspects and deployments of this disclosure. System 300 includes one or more assets 2021-n, database 204 and system 100. System 100 can include at least
Petition 870170039394, of 06/09/2017, p. 40/89
27/56 the pattern detection component 102 and the digital signature library 104. The one or more active 2021-neo database 204 may be in communication via a network 206. Additionally, database 204 and the system 100 (for example, database 204 and pattern detection component 102) can be communicating over a network 302. Network 302 can be a communication network, a wireless network, an IP network, a voIP network, an internet phone network, a mobile telecommunications network and / or another type of network. In one embodiment, system 100 can receive stored data 208. For example, pattern detection component 102 (for example, data signature generation component 106 of pattern detection component 102) can receive stored data 208. Stored data 208 can be supplied to pattern detection component 102 as a data stream (for example, a time series data stream). Pattern detection component 102 (for example, data signature generation component 106 and / or tagging component 108 of pattern detection component 102) can generate one or more digital signatures (for example, one or more digital signatures for storage in digital signature library 104) based on stored data 208. In an alternative embodiment, system 100 can be in direct communication with database 204. Therefore, system 100 can receive stored data 208 without the network 302. In one aspect, pattern detection component 102 (for example, pattern prediction component 114 of pattern detection component 102) can correlate an event (for example, an event associated with a digital signature) with a asset among assets 2021-n. In another aspect, the digital signature library 104 can be employed as a forecasting model for abnormalities, patterns and / or events associated with stored data 208 and / or the one or more active 2021-n.
Petition 870170039394, of 06/09/2017, p. 41/89
28/56 [038] Compared to a conventional system, system 100 that includes pattern detection component 102 and digital signature library 104 can provide improved accuracy, reduced time, greater capabilities and / or greater adaptability to identify anomalies , patterns and / or events associated with stored data 208. Management of stored data 208 and / or the one or more assets 2021-N associated with stored data 208 can also be improved using the system 100 which includes the detection component standard 102 and digital signature library 104. In addition, using system 100 that includes pattern detection component 102 and digital signature library 104, the performance of one or more 2021-N assets can be improved, the costs associated with one or more 2021-N assets can be reduced and the risks associated with one or more 2021-N assets can be minimized.
[039] It should be noted that the technical features of the pattern detection component 102 and the processing of stored data 208 that facilitate the generation of data signatures, the identification of events in stored data 208, etc. they are highly technical in nature and not abstract ideas. Processing segments of pattern detection component 102 that process stored data 208 cannot be performed by a human being (for example, they are larger than the capacity of a single human mind). For example, the amount of stored data 208 processed, the processing speed of stored data 208 and / or the data types of stored data 208 processed by pattern detection component 102 over a certain period of time can be, respectively, greater , faster and different than the amount, speed and type of data that can be processed by a single human mind during the same
Petition 870170039394, of 06/09/2017, p. 42/89
29/56 time period. In addition, stored data 208 processed by pattern detection component 102 can be raw data and / or compressed data associated with assets 2021-N. In addition, the pattern detection component 102 can be fully operational in relation to the performance of one or more other functions (e.g., fully connected, completely executed, etc.) while also processing the stored data 208.
[040] With reference to Figure 4, an unrestricted deployment of a 400 system is illustrated in accordance with various aspects and deployments of this disclosure. System 400 includes one or more assets 2021-N, database 204, system 100 and a display device 402. System 100 can include at least pattern detection component 102 and digital signature library 104 A display device 402 may be communicatively coupled to system 100. Display device 402 may be deployed separately from system 100. Alternatively, display device 402 and / or a device associated with display device 402 may include system 100 The display device 402 can be associated with a display, monitor and / or user interface. Additionally, the display device 402 may be a computing device and / or may be included in a computing device, such as, but without limitation, a smart device, a smart phone, a mobile device, a handheld device, a tablet-type computer, a computer, a desktop-type computer, a laptop-type computer, a monitor device, a portable computing device, or other type of computing device. Display component 116 can generate a user interface for display on display device 402. Display device 402 can also display content provided by and / or generated by display component 116. For example,
Petition 870170039394, of 06/09/2017, p. 43/89
Display device 402 may display one or more display elements related to predictions associated with stored data 208.
[041] In one aspect, the display device 402 may display information regarding abnormalities, patterns and / or events determined by system 100 based on stored data 208. The display device 402 may also display information regarding the one or more most active 2021-N based on abnormalities, patterns and / or events associated with stored data 208. For example, pattern detection component 102 can employ digital signatures and / or markings stored in digital signature library 104, as well as learning and correlations associated therewith, to identify abnormalities, patterns and / or events associated with the stored data 208. Digital signatures and / or markings stored in the digital signature library 104 can be additionally employed by the pattern detection component 102 to correlate abnormalities, patterns and / or events identified with the one or more active 2021-N. The display device 402 can render graphics associated with the abnormalities, patterns and / or events determined by the system 100. The display device 402 can, additionally or alternatively, render graphics associated with one or more 2021-N assets. These graphic elements can be in a human-interpretable format to allow a user to employ the display device 402 to interpret the abnormalities, patterns and / or events associated with the stored data 208, as well as a description and / or rendering of the asset ( or assets) of the one or more 2021-N assets that are affected by abnormalities, patterns and / or events.
[042] The display device 402 may also allow the stored data 208 to be presented through a user interface as time series and / or real time data. For example,
Petition 870170039394, of 06/09/2017, p. 44/89
31/56 stored data 208 can be presented as a graphical representation of time series data that is formatted based on the time and parameter (or parameters) associated with stored data 208. A user can then monitor stored data 208 via graphical representation of stored data 208. A user can also detect patterns associated with graphical representation of stored data 208, such as, for example, peaks associated with stored data 208, valleys associated with stored data 208, a rate of change associated with data stored 208, a time interval between a first peak associated with stored data 208 and a second peak associated with stored data 208, etc. The patterns detected by the user through the graphical representation of the stored data 208 can be used by the system 100 as a digital signature. The user can also add a tag for a digital signature that is generated based on the graphical representation of the stored data 208. In this way, a user can provide user input data to facilitate the generation of digital signatures and / or tags for storage in the digital signature library 104.
[043] In an example without limitation, the first asset 2021 can be associated with a first set line (for example, in a factory) and the N-th asset 202n can be associated with a set line N-th which is different from the first set line. The first assembly line associated with the first active 2021 and the N-th assembly line associated with the N-th active 202n can both manufacture a corresponding product (for example, an engine, a semiconductor product, another type of product, etc.) . In addition, the first set line associated with the first asset 2021 and the set line N-th associated with the N-th asset 202n can be configured in a similar way (for example, with corresponding arrangements, with
Petition 870170039394, of 06/09/2017, p. 45/89
32/56 corresponding robots, with corresponding controller devices, with corresponding sensors, etc.). During a first assembly process associated with the first 2021 asset, the first 2021 asset can generate the first data. Similarly, during an N-th assembly process associated with the N-th active 202N, the N-th active 202N can generate the Nth data. Therefore, the first data and the Nth data, generated during the first assembly process and the Nésimo assembly process, can be transmitted to database 204 through network 306 and stored as stored data 208. The first data and the Nth data can be unstructured data. In one example, a first product manufactured by the first active 2021 can be associated with a defect that is not present in an N-th product manufactured by the N-th active 202n. A conventional system would not, in general, have the capacity to identify a cause for the defect in the first product manufactured by the first asset 2021 using the first data and the Nth data since it collects perceptions of unstructured data associated with the first data and N-th data is, in general, time-consuming and / or difficult to obtain.
[044] On the other hand, system 100 (for example, pattern detection component 102 and digital signature library 104) can employ the stored data 208 associated with the first asset 2021 and the Nth asset 202N to identify with successfully a cause for the defect in the first product manufactured by the first asset 2021. For example, system 100 (for example, pattern detection component 102 and digital signature library 104) can generate digital signatures and / or markings based on in the stored data 208 associated with the first set line and the N-th set line, perform learning and / or generate inferences about the digital signatures associated with the first set line and the
Petition 870170039394, of 06/09/2017, p. 46/89
33/56 N-th assembly line, etc., to predict an event associated with the defect in the first product manufactured by the first asset 2021. In certain deployments, system 100 (for example, pattern detection component 102) can also identify any correlations between the first asset 2021 and the Nth asset 202N with respect to the operators associated with the first asset 2021 and the Nth asset 202N. It should be noted that the system 100 can also employ other techniques and / or aspects, as more fully revealed in this document, to predict an event associated with the defect in the first product manufactured by the first asset 2021. Information associated with the event and / or the first active 2021 can be displayed on a user interface associated with display device 402. In a deployment, system 100 (for example, pattern detection component 102) can generate multiple possible causes and / or events associated with the defect in the first product manufactured by the first asset 2021. In this way, the multiple possible causes and / or events associated with the defect in the first product can be presented as different graphic elements in a user interface associated with the display device 402 to allow a user to further investigate a exact cause for the defect in the first product. In one example, an ordered list of multiple possible causes and / or events can be displayed in the user interface associated with the display device 402, where the ordered list is weighted based on other data, other inferences, other learning and / or other digital signatures associated with the first 2021 asset. In this way, the performance of the first set line associated with the first 2021 asset can be improved and / or the costs related to the first set line associated with the first 2021 asset can be reduced.
[045] With reference to Figure 5, a deployment is illustrated
Petition 870170039394, of 06/09/2017, p. 47/89
34/56 without limitation of a 400 system in accordance with various aspects and implementations of this disclosure. System 500 includes one or more assets 2021-n, database 204, system 100 and a display device 402. System 100 can include at least pattern detection component 102 and digital signature library 104 In the embodiment shown in Figure 5, the display device 402 can be communicating with the system 100 over a network 502. The network 502 can be a communication network, a wireless network, an IP network, a voIP network , an internet telephone network, a mobile telecommunications network and / or another type of network. Display device 402 may display content provided by display component 116 over network 502. For example, display device 402 may receive one or more display elements and / or information regarding one or more display elements per network 502. The one or more display elements and / or information received through network 502 can be related to predictions associated with the stored data 208. In one example, the display device 402 (for example, a user displayed on display device 402) can be integrated with a web-based application communicating with system 100 via network 502. The web-based application can allow abnormalities, patterns and / or events determined by system 100 are viewed in a format interpretable by humans, as described above in connection with at least Figure 5. Additionally, the web-based application may allow a user o monitor and / or analyze stored data 208 by means of a graphical representation of stored data 208, as described above in connection with at least Figure 5.
[046] Now with reference to Figure 6, an unimpeded deployment of a 600 system is illustrated in accordance with various aspects and deployments of this disclosure. The 600 system includes data
Petition 870170039394, of 06/09/2017, p. 48/89
35/56 stored 602. Stored data 602 can be associated, for example, with stored data 208 and / or stored data received by pattern detection component 102. Stored data 602 can also be transmitted from a database. data (for example, database 204) and received by pattern detection component 102. Stored data 602 can be a portion of time series data associated with a time interval that starts at time A and ends at time C. Stored data 602 can also be associated with an event (for example, an extrinsic event) that occurs at time B. The event that occurs at time B can be associated with a pattern and / or a graphic feature associated with the stored data 602. For example, the event that occurs at time B can be associated with a spike in stored data 602, a valley associated with stored data 602, a particular rate of change associated with stored data 602 and / or another pa pattern or graphic feature associated with 602. A pattern and / or a graphic feature associated with the event that occurs at time B can be identified by the data signature generation component 102. Alternatively, user input data received by the data generation component data signature 106 can identify a pattern and / or a graphic characteristic associated with the event that occurs at time B. For example, a user can identify a pattern and / or a graphic characteristic associated with the event that occurs at time B by means of a user interface (for example, a user interface rendered on the 402 display device).
[047] Referring now to Figure 7, an unlimited system deployment of a system 700 is illustrated in accordance with various aspects and deployments of this disclosure. System 700 includes the stored data 602 described in relation to Figure 6. However, the data
Petition 870170039394, of 06/09/2017, p. 49/89
36/56 stored 602 shown in Figure 7 can represent the stored data after being processed by the pattern detection component 102. The stored data 602 shown in Figure 7 can include a first portion of data 702 and a second portion of data 704. A first portion of data 702 can be associated with a data signature (for example, an electronic fingerprint). The first piece of data 702 can also include a sequence of values for one or more parameters during a time interval (for example, a time interval between time A and time B) before the event in time B. For example, the first data portion 702 can be a portion of the stored data 602 that is associated with a time interval before the event (e.g., a time interval between time A and time B). Therefore, the first piece of data 702 can represent a data pattern before the event occurs (for example, a data pattern leading to the event). In certain deployments, the first data portion 702 may additionally include another sequence of values for the one or more parameters during another time interval after the event at time B. For example, the first data portion 702 may additionally include another sequence of data. values for one or more parameters during another time interval that starts at time B and ends at a time value before time C. Consequently, a 'snapshot' of stored data 602 can be created as a data signature (for example, example, an electronic fingerprint) associated with the first 702 data portion.
[048] In one aspect, a data signature (for example, an electronic fingerprint) associated with the first data portion 702 can be stored in the digital signature library 104. A data signature (for example, an electronic fingerprint) associated with the first 702 data portion can also be marked with the event associated with the
Petition 870170039394, of 06/09/2017, p. 50/89
37/56 time B. Additionally, a data signature (for example, an electronic fingerprint) associated with the first data portion 702 can be employed by the pattern detection component 102 (for example, the search component 112 of the pattern detection 102) to identify a future event related to the event associated with time B. For example, a data signature (eg, an electronic fingerprint) associated with the first data portion 702 can be employed by the pattern detection component 102 (for example, search component 112 of pattern detection component 102) to identify corresponding events associated with stored data 208 that are stored in database 204. In another aspect, pattern detection component 102 (for example , the data signature generating component 106 of the pattern detection component 102) can determine a time period (for example, a time period from time A to time B) that occurs before the event in time B to facilitate the generation of the data signature (for example, the electronic fingerprint) associated with the first data portion 702.
[049] With reference to Figure 8, an unlimited deployment of an 800 system is illustrated in accordance with various aspects and deployments of this disclosure. In one aspect, system 800 can be associated with display component 116 and / or a display device. System 800 illustrates an exemplary 802 user interface. The 802 user interface can be a graphical user interface that features (for example, displays) graphic elements. In one example, the 802 user interface can be associated with an industrial internet application (for example, a cloud-based PaaS). The 802 user interface can be displayed on a display device display, but, without limitation, a computing device, a smart device, a
Petition 870170039394, of 06/09/2017, p. 51/89
38/56 smart phone, a mobile device, a handheld device, a tablet computer, a computer, a desktop computer, a laptop computer, a monitor device, a portable computing device or other type of display device. In one aspect, the 802 user interface can display forecast information 804. Forecast information 804 can be associated with information generated by forecast component 114. For example, forecast information 804 can display information related to an associated future event. to a digital signature. The prognostic information 804 can be presented in a format interpretable by humans. For example, the prediction information 804 can be presented as a graphic element, such as, without limitation, a notification, a message, an icon, a thumbnail, a dialog box, an interactive tool, a graphical interface accessory , a chart, or other type of graphic. The prognostic information 804 can also be related to the information provided by an 806 asset section of the 802 user interface and / or an 808 event section of the 802 user interface. The 806 asset section can present information for various 8061N assets that provide data associated with the 804 forecast information. The information for the 8061-N assets may correspond, for example, to the 2021-N assets. The 808 event section can display information for various 8081-N events associated with the 804 forecast information. The information for various 8081-N events can correspond, for example, to extrinsic events identified based on data provided by 8061-N assets. The 802 user interface can also facilitate analysis, asset performance management and / or operations optimization associated with 804 forecast information, 8061-N assets and / or 8081-N events. In one respect, the 802 user interface can allow
Petition 870170039394, of 06/09/2017, p. 52/89
39/56 a user to view, analyze, mark and / or manage data in real time. It should be noted that the 802 user interface is merely an example. Therefore, the location and / or content of forecast information 804, asset section 806 and / or event section 808 can be varied. In addition, the 802 user interface may include other features, content and / or functions not shown in Figure 8.
[050] The systems and / or devices mentioned above have been described in relation to the interaction between different components. It should be noted that such systems and components may include those components or subcomponents specified therein, some of the specified components or subcomponents, and / or additional components. Subcomponents can also be deployed as components communicatively coupled to other components instead of being included in parental components. In addition, one or more components and / or subcomponents can be combined into a single component, which provides added functionality. The components may also interact with one or more other components not specifically described in this document for the sake of brevity, however, they are known to those skilled in the art.
[051] Figures 9 to 11 illustrate methodologies and / or flowcharts in accordance with the revealed matter. For simplicity of explanation, the methodologies are represented and described with a series of acts. It should be understood and verified that the innovation submitted is not limited by the illustrated acts and / or the order of the acts, for example, acts can occur in several orders and / or simultaneously, and with other acts not presented and described in this document. In addition, not all of the illustrated acts may be required to implement the methodologies in accordance with the disclosed matter. Additionally, those who are versed in the technique
Petition 870170039394, of 06/09/2017, p. 53/89
40/56 will understand and verify that the methodologies could, alternatively, be represented as a series of interrelated states through a state diagram or events. In addition, it should be further verified that the methodologies revealed hereinafter and throughout this specification are capable of being stored in an article of manufacture to facilitate the transport and transfer of such methodologies to computers. The term article of manufacture as used in this document is intended to encompass a computer program accessible from any computer-readable device or storage media.
[052] With reference to Figure 9, a 900 methodology is illustrated to identify, predict and / or manage an event associated with a stored data body, according to an aspect of the innovation submitted. As an example, the 900 methodology can be used in several orders, such as, but without limitation, industrial systems, aviation systems, manufacturing systems, factory systems, energy management systems, electrical grid systems, water supply, transportation systems, health systems, refinery systems, media systems, research systems, financial systems, data driven forecasting systems, machine learning systems, neural network systems, network systems, systems network systems, communication systems, router systems, server systems, high availability server systems (for example, telecommunication server systems), web server systems, file server systems, data server systems , disk array systems, powered insertion card systems, cloud-based systems, PaaS systems, performance management systems active, etc. In 902, a body of stored data is processed (for example, by a component of
Petition 870170039394, of 06/09/2017, p. 54/89
41/56 data signature generation 106) and respective digital signatures that represent respective subsets of the stored data body are generated (for example, by a data signature generation component 106). For example, stored data can be received from a database (for example, a network of databases) through a network. Their digital signatures can include respective portions of the stored data. A data signature can be an electronic fingerprint that encodes a portion of the stored data (for example, a sequence of data values associated with the stored data). A digital signature can also be associated with a digital standard for the portion of the stored data. In 904, the respective digital signatures are marked (for example, by a mark component 108) with markings that correspond to extrinsic events. For example, a tag can identify and / or provide information for an extrinsic event associated with a digital signature. In 906, digital signatures with the markings are stored (for example, by a data signature generation component 106 and / or by a markings component 108) in a digital signature library. For example, digital signatures with tags can be stored in a database that is indexed and / or formatted as a digital signature library.
[053] In 908, learning for the respective digital signatures and associated markings is carried out (for example, by an artificial intelligence component 110) and inferences regarding the respective digital signatures are generated (for example, by an artificial intelligence component 110). For example, one or more machine learning techniques can be performed to facilitate learning and inferences for the respective digital signatures. Based on the learning and inferences for the respective digital signatures, digital signatures
Petition 870170039394, of 06/09/2017, p. 55/89
42/56 learned can be generated and / or stored in the digital signature library. In 910, a new digital signature is searched for and compared with learned digital signatures (for example, by a search component 112) in order to identify one or more matches. For example, a new digital signature can be compared with learned digital signatures stored in the digital signature library based on one or more pattern recognition techniques and / or one or more statistical analysis techniques. In 912, a future event associated with the new digital signature is forecast (for example, by the forecast component 114) based, at least in part, on the inferences generated and the correspondences. For example, in response to a determination that the new digital signature corresponds to a learned digital signature stored in the digital signature library, an event associated with the learned digital signature (for example, the learned digital signature that corresponds to the new digital signature) may be identified and / or employed to determine the future event. In 914, a display user interface is generated (for example, by a display component 116) that outputs information associated with the future event in a format interpretable by humans. For example, a graphic that displays information associated with the future event can be rendered on a display associated with a display device.
[054] With reference to Figure 10, a methodology 1000 is illustrated to generate and / or store digital signatures, according to an aspect of the innovation submitted. At 1002, data that is stored in a network database is received (for example, by a data signature generation component 106). For example, the network database can receive data from one or more assets in wireless communication with the network database. In 1004, an extrinsic event associated with
Petition 870170039394, of 06/09/2017, p. 56/89
43/56 data is identified (for example, by a data signature generation component 106). For example, a pattern in the data can be identified. Additionally, based on the pattern in the data, an extrinsic event associated with one or more assets and / or a system associated with one or more assets can be identified.
[055] In 1006, a digital signature is generated (for example, by a data signature generation component 106) for a portion of the data that is associated with a time interval before the extrinsic event. For example, a pre-pattern data string in the data and / or a data value in the data associated with the extrinsic event can be used to generate a digital signature. The digital signature can be an electronic fingerprint. In 1008, the digital signature is marked (for example, by a mark component 108) with a mark that corresponds to the extrinsic event. For example, information that identifies and / or describes the extrinsic event can be attached and / or associated with the digital signature. In 1010, the digital signature with the tag corresponding to the extrinsic event is stored (for example, by a data signature generation component 106 and / or a tag component 108) in a digital signature library. For example, the digital signature and / or the markup can be stored in a database that is different from the network database.
[056] With reference to Figure 11, an 1100 methodology is illustrated to employ digital signatures to identify, predict and / or manage an event associated with the stored data, according to an aspect of the innovation submitted. In 1102, a digital signature is generated and / or received (for example, using a data signature generation component 106). For example, an electronic fingerprint for a portion of stored data (for example, a sequence of data values for
Petition 870170039394, of 06/09/2017, p. 57/89
44/56 stored data) can be generated and / or received. In 1104, the digital signature is compared to digital signatures stored in a digital signature library (for example, using an artificial intelligence component 110 and / or a search component 112). For example, the digital signature can be compared to previously generated digital signatures stored in a digital signature library.
[057] In 1106, it is determined whether the digital signature matches another digital signature stored in the digital signature library (for example, using an artificial intelligence component 110 and / or a search component 112). For example, in addition to the comparison between the digital signature and the digital signatures stored in the digital library, it is determined whether the digital signature matches another digital signature stored in the digital signature library based on one or more artificial intelligence techniques, one or more pattern recognition techniques, one or more statistical analysis techniques and / or one or more other comparison techniques.
[058] If so, the 1100 methodology proceeds to 1108. In 1108, a future event associated with the digital signature is determined (for example, with the use of a 114 forecast component) based, at least in part, on certain inferences and learning associated with the digital signature and / or other digital signature. For example, the future event can be determined based on an event associated with another digital signature. Then, the 1100 methodology proceeds to 1110. In 1110, a user interface that outputs information associated with the future event in a human-interpretable format is generated for display (for example, using a display component 116). The 1100 methodology then returns to 1102. For example, a graphic element associated with the information for the future event can be displayed on a display.
Petition 870170039394, of 06/09/2017, p. 58/89
45/56 [059] If not, the 1100 methodology proceeds to 1112. In 1112, a mark is generated for the digital signature (for example, with the use of a 108 mark component). For example, an event for the digital signature can be associated with the digital signature. Then, the 1100 methodology proceeds to 1114. In 1114, the digital signature and / or the markup is stored in the digital signature library (for example, using a data signature generation component 106 and / or a 108). For example, the digital signature can be added to digital signatures stored in the digital signature library. Thereafter, the 1100 methodology returns to 1102.
[060] In order to provide a context for the various aspects of the revealed matter, Figures 12 and 13, as well as the following discussion are intended to provide a brief overview of a suitable environment in which the various aspects of the revealed matter can be implanted.
[061] Referring to Figure 12, a suitable environment 1200 for deploying the various aspects of this disclosure includes a computer 1212. Computer 1212 includes a processing unit 1214, a system memory 1216 and a system bus 1218. The system bus system 1218 couples system components that include, but are not limited to system memory 1216, to processing unit 1214. processing unit 1214 can be any of several available processors. Dual microprocessors and other multiprocessor architectures can also be employed as the 1214 processing unit.
[062] The 1218 system bus can be any of several types of bus structure (or bus structures) that include the memory bus or memory controller, a peripheral bus or external bus and / or a local bus that uses any
Petition 870170039394, of 06/09/2017, p. 59/89
46/56 variety of bus architectures available that include, but are not limited to, industry standard architecture (ISA), microchannel architecture (MSA), extended ISA (EISA), IDE interface (IDE), local VESA bus (VLB), peripheral component interconnector (PCI), card bus, universal serial bus (USB), advanced graphics port (AGP), bus from the International Memory Card Association for Personal Computers (PCMCIA), Firewire (IEEE 1394) and interface small computer systems (SCSI).
[063] System memory 1216 includes volatile memory 1220 and non-volatile memory 1222. The basic input / output system (BIOS), which contains the basic routines for transferring information between the elements inside the computer 1212, such as during startup , is stored in non-volatile memory 1222. By way of illustration, not limitation, non-volatile memory 1222 may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically programmable ROM erasable (EEPROM), flash memory or non-volatile random access memory (RAM) (for example, ferroelectric RAM (FeRAM)). The volatile memory 1220 includes random access memory (RAM), which acts as an external cache memory. By way of illustration and not by way of limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), DRAM Synchlink (SLDRAM), RAM Rambus Direct (DRRAM), RAM Dynamic Rambus Direct (DRDRAM) and RAM Dynamic Rambus.
[064] The 1212 computer also includes removable / non-removable volatile / non-volatile computer-readable media. Figure 12 illustrates, for example, disk storage 1224. Disk storage 1224 includes, but is not limited to devices such as a disk drive
Petition 870170039394, of 06/09/2017, p. 60/89
47/56 magnetic, floppy drive, tape drive, Jaz drive, Zip drive, LS-100 drive, flash memory card or memory card. 1224 disk storage may also include storage media separately or in combination with other storage media that includes, but is not limited to, an optical disc drive, such as a compact disc ROM (CD-ROM) device, drive recordable CD (CD-R Drive), rewritable CD drive (CD-RW Drive) or a versatile digital disk ROM drive (DVD-ROM). To facilitate the connection of disk storage devices 1224 to the system bus 1218, a removable or non-removable interface is typically used, such as the 1226 interface.
[065] Figure 12 also represents the software that acts as an intermediary between users and the basic computer resources described in the appropriate operating environment 1200. Such software includes, for example, a 1228 operating system. This 1228 operating system, which can be stored in disk storage 1224, acts to control and allocate resources of the computer system 1212. System applications 1230 take advantage of resource management by the operating system 1228 through program modules 1232 and program data 1234, for example, stored either in system memory 1216 or disk storage 1224. It should be noted that this disclosure can be deployed with multiple operating systems or combinations of operating systems.
[066] A user enters commands or information on the 1212 computer through an input device (or input devices)
1236. 1236 input devices include, but are not limited to, a pointing device, such as a mouse, trackball, pen, touchpad, keyboard, microphone, controller, game control, satellite dish,
Petition 870170039394, of 06/09/2017, p. 61/89
48/56 digitizer, TV tuner card, digital camera, digital video camera, web camera and the like. These and other input devices connect to processing unit 1214 via system bus 1218 via interface port (or interface ports) 1238. Interface port (or interface ports) 1238 includes, for example, a serial port, a parallel port, a game port and a universal serial bus (USB). Output device (or output devices) 1240 uses some of the same types of ports as the input device (or input devices) 1236. So, for example, a USB port can be used to provide input to the 1212 computer and to output information from computer 1212 to a 1240 output device. 1242 output adapter is provided to illustrate that there are some 1240 output devices such as monitors, speakers and printers, among other 1240 output devices, that require special adapters. Output adapters 1242 include, by way of illustration and not limitation, video and sound cards that provide a means of connection between the output device 1240 and the system bus 1218. It should be noted that other devices and / or systems devices provide both input and output capabilities, such as remote computer (or remote computers) 1244.
[067] Computer 1212 can operate in a network environment using logical connections to one or more remote computers, such as remote computer (or remote computers) 1244. Remote computer (or remote computers) 1244 can be a computer personal computer, a server, a router, a network PC, a workstation, a microprocessor-based device, a peer device or other common network node and the like, and typically includes many or all of the elements described with respect to to the 1212 computer. For the sake of brevity, only one 1246 memory storage device is illustrated with the computer
Petition 870170039394, of 06/09/2017, p. 62/89
49/56 remote (or remote computers) 1244. The remote computer (or remote computers) 1244 is logically connected to computer 1212 via a 1248 network interface and then physically connected via the 1250 communication connection. The 1248 network includes wireless and / or wired communication networks, such as local area networks (LAN), wide area networks (WAN), cellular networks, etc. LAN technologies include the FDDI standard (FDDI), CDDI standard (CDDI), Ethernet, Token Ring and the like. However, WAN technologies include, but are not limited to point-to-point connections, circuit switching networks such as integrated service digital networks (ISDN) and variations in them, packet switching networks and digital subscriber lines (DSL).
[068] Communication connection (or communication connections) 1250 refers to the hardware / software used to connect the network interface 1248 to the bus 1218. Although the communication connection 1250 is shown for greater illustrative clarity inside the computer 1212, the same it can also be external to the 1212 computer. The hardware / software required to connect to the 1248 network interface includes, for example only, internal and external technologies, such as modems that include regular telephone modems, cable modems, and modems DSL, ISDN adapters and Ethernet cards.
[069] Figure 13 is a schematic block diagram of a 1300 sample computing environment with which the material in this disclosure can interact. The 1300 system includes one or more 1310 clients. The 1310 client (or clients) can be hardware and / or software (for example, segments, processes, computing devices). The 1300 system can also include one or more 1330 servers. Thus, the 1300 system can correspond to a two-tier client server model or a multi-tier model (for example, client, middle tier server,
Petition 870170039394, of 06/09/2017, p. 63/89
50/56 data), among other models. The 1330 server (or servers) can also be hardware and / or software (for example, segments, processes, computing devices). 1330 servers can host segments to perform transformations using this disclosure, for example. A possible communication between a 1310 client and a 1330 server can be in the form of a data packet transmitted between two or more computational processes.
[070] The 1300 system includes a 1350 communication frame that can be employed to facilitate communications between the 1310 client (or clients) and the 1330 server (or servers). The 1310 client (or clients) is operationally connected to one or more more 1320 client data stores that can be used to store local information for the 1310 client (or clients). Similarly, the 1330 server (or servers) are operationally connected to one or more 1340 server data stores that can be used to store local information for the 1330 server (or servers).
[071] It should be noted that aspects or features of this disclosure can be exploited in, substantially, any wireless telecommunication or radio technology, for example, Wi-Fi; Bluetooth; worldwide interoperability for microwave access (WiMAX); improved general packet radio communication service (enhanced GPRS); long-term evolution (LTE) in a third generation partnership project (3GPP); ultra-mobile broadband (UMB) in a third generation partnership project 2 (3GPP2); 3GPP UMTS system (UMTS); high speed packet access (HSPA); access to high speed downlink packet (HSDPA); access to high speed uplink (HSUPA) packet; GSM (global mobile communications system) EDGE (improved data rates for GSM evolution) radio access network (GERAN); radio access network
Petition 870170039394, of 06/09/2017, p. 64/89
51/56 terrestrial UMTS (UTRAN); Advanced LTE (LTE-A); etc. In addition, some or all of the aspects described in this document can be explored in legacy telecommunication technologies, for example, GSM. In addition, both mobile and non-mobile networks (for example, the Internet, data service network, such as Internet Protocol Television (IPTV), etc.) can explore aspects or features described in this document.
[072] Although the material has been described above in the general context of computer executable instructions for a computer program that runs on a computer and / or computers, those skilled in the art will recognize that this disclosure may or may also be implemented in combination with other program modules. In general, program modules include routines, programs, components, data structures, etc., that perform tasks and / or deploy particular abstract data types. In addition, those skilled in the art will find that inventive methods can be practiced with other computer system configurations, which include single processor or multiprocessor computer systems, minicomputing devices, mainframe computers, as well as personal computers, computing devices handheld (for example, PDA, telephone), microprocessor-based or consumer programmable or industrial electronics, and the like. The illustrated aspects can also be practiced in distributed computing environments where the tasks are performed through remote processing devices that are connected through a communication network. However, some, if not all, aspects of this disclosure can be practiced on independent computers. In a distributed computing environment, program modules can be located
Petition 870170039394, of 06/09/2017, p. 65/89
52/56 on both remote and local memory storage devices.
[073] As used in this application, the terms "component", "system", "platform", "interface" and the like, may refer to and / or include a computer-related entity or an entity related to an operating machine with a or more specific features. The entities disclosed in this document may be hardware, a combination of hardware and software, software or running software. For example, a component can be, without limitation, a process running on a processor, processor, object, executable, thread, program and / or computer. By way of illustration, both an application that runs on a server and the server can be a component. One or more components can reside in a process and / or thread of execution and a component can be located on a computer and / or distributed between two or more computers.
[074] In another example, the respective components can be executed from several computer-readable media that have several data structures stored in them. Components can communicate via local and / or remote processes, such as a signal that has one or more data packets (for example, data from a component that interacts with another component on a local system, distributed system and / or over a network, such as the internet with other systems using the signal). As another example, a component can be a device with specific functionality provided by mechanical parts operated by an electrical or electronic circuit assembly, which is operated by a software or firmware application run by a processor. In such a case, the processor can be internal or external to the device and can run at least part of the software application or firmware. As yet another example, a component can be a device that provides specific functionality through components
Petition 870170039394, of 06/09/2017, p. 66/89
53/56 electronics without mechanical parts, where the electronic components may include a processor or other means to run software or firmware that confers, at least in part, the functionality of the electronic components. In one aspect, a component can emulate an electronic component through a virtual machine, for example, within a cloud computing system.
[075] Additionally, the term “or” is intended to mean an inclusive “or” instead of an exclusive “or”. That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, if X employs A, X employs B or X employs both A and B, then "X employs A or B" is satisfied under any of the above examples. In addition, the articles “one” and “one” as used in this submitted specification and in the attached Figures should generally be interpreted as meaning “one or more”, unless otherwise specified or clear from the context to be directed to a singular form.
[076] As used herein, the terms example and / or example are used to assign the meaning of serving as an example, instance, or illustration. For the avoidance of doubt, the material disclosed in this document is not limited by such examples. In addition, any aspect or project described in this document as an “example” and / or “exemplary” should not necessarily be interpreted as preferential or advantageous over other aspects or projects, nor is it intended to exclude exemplary equivalent structures and techniques known to those of common skill in the technique.
[077] Various aspects or resources described in this document can be implemented as a method, device, system or article of manufacture using standard engineering techniques or
Petition 870170039394, of 06/09/2017, p. 67/89
54/56 programming. In addition, various aspects or resources revealed in this disclosure can be obtained through program modules that implement at least one or more of the methods disclosed in this document, in which the program modules are stored in memory and executed by at least one processor. Other combinations of hardware and software or hardware and firmware may enable or deploy aspects described in this document, including a revealed method (or revealed methods). The term article of manufacture as used in this document can encompass a computer program accessible from any computer-readable device, carrier or storage media. For example, computer-readable storage media may include, but are not limited to magnetic storage devices (eg hard disk, floppy disk, magnetic strips ...), optical discs (eg compact disc (CD), disk digital versatile (DVD), blu-ray disc (BD) ...), smart cards and flash memory devices (eg, card, analog stick, key unit.), or similar.
[078] As used in the submitted specification, the term “processor” can refer to substantially any computing device or processing unit that comprises, however, without limitation to single-core processors; simple processors capable of executing multiple software segments; multi-core processors; multi-core processors capable of running multiple software segments; multi-core processors capable of running multiple hardware segments; parallel platforms; and parallel platforms with distributed shared memory. In addition, a processor can refer to an integrated circuit, an application-specific integrated circuit (ASIC), a
Petition 870170039394, of 06/09/2017, p. 68/89
55/56 digital signal processor (DSP), a field programmable port arrangement (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), a transistor or distinct port logic, components hardware or any combination thereof designed to perform the functions described in this document. In addition, processors can explore nanoscale architectures such as, without limitation, molecular-based and quantum dot transistors, switches and ports, in order to optimize the use of space or improve the performance of user equipment. A processor can also be deployed as a combination of computing processing units.
[079] In this disclosure, terms such as "storage", "storage", "data storage", "data storage", "database" and substantially any other information storage component relevant to the operation and functionality of a component is used to refer to "memory components", entities embedded in a "memory" or components that comprise a memory. It should be noted that the memory and / or memory components described in this document may be volatile or non-volatile memory, or may include both volatile and non-volatile memory.
[080] By way of illustration, not limitation, non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory or non-volatile random access memory (RAM) (eg ferroelectric RAM (FeRAM). Volatile memory can include RAM, which can act as external cache memory, for example. As an illustration and not a limitation, RAM is available in many ways, such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDR SDRAM), SDRAM
Petition 870170039394, of 06/09/2017, p. 69/89
56/56 enhanced (ESDRAM), DRAM Synchlink (SLDRAM), RAM Rambus Direct (DRRAM), RAM Dynamic Rambus Direct (DRDRAM) and RAM Dynamic Rambus (RDRAM). In addition, the memory components disclosed of systems or methods in this document are intended to include, but are not limited to, these and any other suitable types of memory.
[081] It should be verified and understood that components, as described with respect to a particular system or method, may include the same functionality or similar functionality as the respective components (for example, respectively named components or similarly named components) as described with relation to the other systems or methods disclosed in this document.
[082] What has been described above includes examples of systems and methods that provide advantages of this disclosure. It is obviously not possible to describe all conceivable combinations of components or methods for the purposes of describing this disclosure, however, one of ordinary skill in the art may recognize that several additional combinations and permutations of this disclosure are possible. In addition, in a broad sense, the terms "includes", "has" or the like are used in the detailed description, in the claims, annexes and Figures, such terms are intended to be inclusive in a similar way to the term "understand" as "understand ”Is interpreted when used as a transitional word in a claim.
Petition 870170039394, of 06/09/2017, p. 70/89
1/5

权利要求:
Claims (20)
[1]
Claims
1. DIGITAL PROGNOSTICS SYSTEM characterized by the fact that it comprises:
a memory that has, stored in it, components executable by computer;
a processor that runs at least the following computer executable components:
a data signature generation component that processes a stored data body and generates respective digital signatures that represent respective subsets of the stored data body, with digital signatures being stored and indexed in a digital signature library;
a marking component that marks the respective digital signatures with markings that correspond to extrinsic events;
an artificial intelligence component that learns the respective digital signatures and associated markings, and generates inferences about the respective digital signatures;
a search component that searches for and compares a new digital signature with the digital signatures learned in order to identify one or more matches;
a prediction component that predicts a future event associated with the new digital signature based, at least in part, on the generated inferences and correspondences; and a display component that generates a user interface, for display, that outputs the predictions in a format interpretable by humans.
[2]
2. DIGITAL PROGNOSTICS SYSTEM, according to
Petition 870170039394, of 06/09/2017, p. 71/89
2/5 to claim 1, characterized by the fact that the data signature generation component generates a digital signature in response to an extrinsic event.
[3]
3. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the data signature generation component generates a digital signature based on a portion of the stored data that is associated with a time interval before a extrinsic event.
[4]
4. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the data signature generation component generates the new digital signature in response to receiving a portion of the stored data associated with the new digital signature.
[5]
5. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the data signature generation component generates a digital signature based on feedback data received from the user interface.
[6]
6. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the data signature generation component receives the stored data from a database in communication with the digital prognostic system through a network.
[7]
7. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the search component determines that the new digital signature corresponds to a digital signature among the digital signatures stored in the digital signature library.
[8]
8. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the prognostic component triggers an action in response to a determination that the new
Petition 870170039394, of 06/09/2017, p. 72/89
3/5 digital signature corresponds to a digital signature among the learned digital signatures.
[9]
9. DIGITAL PROGNOSTICS SYSTEM, according to claim 1, characterized by the fact that the prognostic component correlates the future event with an asset associated with the future event.
[10]
10. METHOD characterized by the fact that it comprises: generating, through a system comprising a processor, a first digital signature based on a portion of stored data;
mark, through the system, the first digital signature with a mark that corresponds to an event extrinsic to the system;
store, through the system, the first digital signature in a digital signature library;
generate, through the system, inferences regarding the first digital signature;
compare, through the system, a second digital signature with the first digital signature in order to identify a correspondence;
identify, through the system, a future event associated with the second digital signature based, at least in part, on inferences and correspondence; and generate, through the system, a user interface that emits information associated with the future event in a format interpretable by humans through a display.
[11]
11. METHOD, according to claim 10, characterized by the fact that generating the first digital signature comprises generating the first digital signature in response to the event.
[12]
12. METHOD, according to claim 10, characterized
Petition 870170039394, of 06/09/2017, p. 73/89
4/5 due to the fact that generating the first digital signature involves determining a time interval associated with the portion that occurs before the event.
[13]
13. METHOD, according to claim 10, characterized by the fact that generating the first digital signature comprises generating the first digital signature based on input data received through the user interface.
[14]
14. METHOD, according to claim 10, characterized by the fact that it additionally comprises generating, through the system, the second digital signature based on another portion of the stored data.
[15]
15. METHOD, according to claim 10, characterized by the fact that it additionally comprises receiving, through the system, the data stored from a database in communication with the system through a wireless network.
[16]
16. METHOD, according to claim 10, characterized by the fact that it additionally comprises triggering, through the system, an action extrinsic to the system in response to a determination that the second digital signature corresponds to the first digital signature.
[17]
17. METHOD, according to claim 10, characterized by the fact that it additionally comprises correlating, through the system, the future event with an asset associated with the portion of the stored data.
[18]
18. COMPUTER-READABLE STORAGE DEVICE characterized by the fact that it comprises instructions that, in response to execution, cause a system comprising a processor to perform operations comprising:
generating a first electronic fingerprint based on a portion of data stored in a first data store;
generate an appointment for the first electronic fingerprint to associate the first electronic fingerprint with an extrinsic event;
Petition 870170039394, of 06/09/2017, p. 74/89
5/5 store the first electronic fingerprint on a second data store;
determine inferences associated with the first electronic fingerprint;
identify a correspondence between a second electronic fingerprint and the first electronic fingerprint which comprises identifying a future event associated with the second electronic fingerprint based, at least in part, on inferences and correspondence; and present information associated with the future event in a format interpretable by humans through a user interface associated with a display.
[19]
19. COMPUTER-READABLE STORAGE DEVICE, according to claim 18, characterized by the fact that generating the first electronic fingerprint comprises generating the first electronic fingerprint in response to the identification of the extrinsic event.
[20]
20. COMPUTER-READABLE STORAGE DEVICE, according to claim 18, characterized by the fact that generating the first electronic fingerprint comprises determining a period of time associated with the portion that occurs before the extrinsic event.
Petition 870170039394, of 06/09/2017, p. 75/89
1/13

类似技术:

---

公开号 | 公开日 | 专利标题

---

BR102017012278A2|2018-10-30|digital predictive system, method and computer readable storage device

---

Hayes et al.2015|Contextual anomaly detection framework for big sensor data

---

Souza et al.2015|Data stream classification guided by clustering on nonstationary environments and extreme verification latency

---

Hayes et al.2014|Contextual anomaly detection in big sensor data

---

Zhukov et al.2016|Random forest based approach for concept drift handling

---

Abdullah et al.2012|Towards population scale activity recognition: A framework for handling data diversity

---

Kansal et al.2015|Detection of forest fires using machine learning technique: A perspective

---

US20210067527A1|2021-03-04|Structural graph neural networks for suspicious event detection

---

WO2017034512A1|2017-03-02|Interactive analytics on time series

---

US20180357564A1|2018-12-13|Cognitive flow prediction

---

Nakhodchi et al.2020|A comparison between different machine learning models for IoT malware detection

---

Ren et al.2015|Unsupervised kernel learning for abnormal events detection

---

US20200068243A1|2020-02-27|Intelligent updating of media data in a computing environment

---

EP3776115A1|2021-02-17|Predicting failures in electrical submersible pumps using pattern recognition

---

Paramkusem et al.2018|Classifying categories of SCADA attacks in a big data framework

---

Song et al.2015|A precise and real-time loop-closure detection for slam using the rsom tree

---

Singh et al.2017|A comprehensive study of big data machine learning approaches and challenges

---

Tennant et al.2014|Towards a parallel computationally efficient approach to scaling up data stream classification

---

Boytsov et al.2012|Where have you been? Using location clustering and context awareness to understand places of interest

---

US20200125470A1|2020-04-23|Active asset monitoring

---

Trusova2021|Machine learning methods application for the avionics systems health analysis and faults localization challenges

---

Shitole et al.2018|Machine Learning Supported Statistical Analysis of IoT Enabled Physical Location Monitoring Data

---

Zhang et al.2017|Curve-registration-based feature extraction for predictive maintenance of industrial equipment

---

Tang et al.2018|Discrete hashing based supervised matrix factorization for cross-modal retrieval

---

US11043289B2|2021-06-22|Monitoring, predicting and alerting for census periods in medical inpatient units

同族专利:

---

公开号 | 公开日

---

US20170357828A1|2017-12-14|

---

EP3255581A1|2017-12-13|

---

US10824761B2|2020-11-03|

---

CA2969957A1|2017-12-10|

引用文献:

---

公开号 | 申请日 | 公开日 | 申请人 | 专利标题

---

---

US7930546B2|1996-05-16|2011-04-19|Digimarc Corporation|Methods, systems, and sub-combinations useful in media identification|

---

US7707039B2|2004-02-15|2010-04-27|Exbiblio B.V.|Automatic modification of web pages|

---

US7493388B2|2004-08-20|2009-02-17|Bdna Corporation|Method and/or system for identifying information appliances|

---

US8027518B2|2007-06-25|2011-09-27|Microsoft Corporation|Automatic configuration of devices based on biometric data|

---

US7899777B2|2007-09-27|2011-03-01|Rockwell Automation Technologies, Inc.|Web-based visualization mash-ups for industrial automation|

---

US8026933B2|2007-09-27|2011-09-27|Rockwell Automation Technologies, Inc.|Visualization system and method for preserving or augmenting resolution and data associated with zooming or paning in an industrial automation environment|

---

US8677262B2|2007-09-27|2014-03-18|Rockwell Automation Technologies, Inc.|Presentation of industrial automation data as a function of relevance to user|

---

US8121618B2|2009-10-28|2012-02-21|Digimarc Corporation|Intuitive computing methods and systems|

---

CA2798093C|2010-05-04|2016-09-13|Avery Li-Chun Wang|Methods and systems for processing a sample of a media stream|

---

US8918854B1|2010-07-15|2014-12-23|Proxense, Llc|Proximity-based system for automatic application initialization|

---

US9484046B2|2010-11-04|2016-11-01|Digimarc Corporation|Smartphone-based methods and systems|

---

US8817984B2|2011-02-03|2014-08-26|mSignia, Inc.|Cryptographic security functions based on anticipated changes in dynamic minutiae|

---

US9292793B1|2012-03-31|2016-03-22|Emc Corporation|Analyzing device similarity|

---

US9183849B2|2012-12-21|2015-11-10|The Nielsen Company , Llc|Audio matching with semantic audio recognition and report generation|

---

WO2014149827A1|2013-03-15|2014-09-25|REMTCS Inc.|Artificial neural network interface and methods of training the same for various use cases|

---

US20140337277A1|2013-05-09|2014-11-13|Rockwell Automation Technologies, Inc.|Industrial device and system attestation in a cloud platform|

---

US9842302B2|2013-08-26|2017-12-12|Mtelligence Corporation|Population-based learning with deep belief networks|

---

US10122747B2|2013-12-06|2018-11-06|Lookout, Inc.|Response generation after distributed monitoring and evaluation of multiple devices|

---

US20150286873A1|2014-04-03|2015-10-08|Bruce L. Davis|Smartphone-based methods and systems|

---

US9589074B2|2014-08-20|2017-03-07|Oracle International Corporation|Multidimensional spatial searching for identifying duplicate crash dumps|

---

US20160119672A1|2014-10-24|2016-04-28|The Nielsen Company , Llc|Methods and apparatus to identify media using image recognition|

---

US20160191957A1|2014-12-31|2016-06-30|Opentv, Inc.|Lull management for content delivery|

---

US10873508B2|2015-01-27|2020-12-22|Moogsoft Inc.|Modularity and similarity graphics system with monitoring policy|

---

US10979304B2|2015-01-27|2021-04-13|Moogsoft Inc.|Agent technology system with monitoring policy|

---

US9632859B2|2015-06-11|2017-04-25|International Business Machines Corporation|Generating problem signatures from snapshots of time series data|

---

US9699205B2|2015-08-31|2017-07-04|Splunk Inc.|Network security system|

---

US10572640B2|2015-11-16|2020-02-25|Personnus|System for identity verification|

---

US9843877B2|2015-12-31|2017-12-12|Ebay Inc.|Sound recognition|

---

US20170213130A1|2016-01-21|2017-07-27|Ebay Inc.|Snippet extractor: recurrent neural networks for text summarization at industry scale|

---

US20170262758A1|2016-03-10|2017-09-14|Dell Products, Lp|System and method to assess anomalous behavior on an information handling system using indirect identifiers|

---

EP3255581A1|2016-06-10|2017-12-13|General Electric Company|Digital pattern prognostics|EP3255581A1|2016-06-10|2017-12-13|General Electric Company|Digital pattern prognostics|

---

US11004568B2|2017-03-10|2021-05-11|Altair Engineering, Inc.|Systems and methods for multi-dimensional fluid modeling of an organism or organ|

---

US10803211B2|2017-03-10|2020-10-13|General Electric Company|Multiple fluid model tool for interdisciplinary fluid modeling|

---

US10409950B2|2017-03-10|2019-09-10|General Electric Company|Systems and methods for utilizing a 3D CAD point-cloud to automatically create a fluid model|

---

US10867085B2|2017-03-10|2020-12-15|General Electric Company|Systems and methods for overlaying and integrating computer aided designdrawings with fluid models|

---

US10977397B2|2017-03-10|2021-04-13|Altair Engineering, Inc.|Optimization of prototype and machine design within a 3D fluid modeling environment|

---

US10789550B2|2017-04-13|2020-09-29|Battelle Memorial Institute|System and method for generating test vectors|

---

US11263835B2|2017-10-27|2022-03-01|The Boeing Company|Vehicle fault detection system and method utilizing graphically converted temporal data|

---

US10784715B2|2018-08-22|2020-09-22|LO3 Energy Inc.|Grid telemetry fingerprint|

---

US10931659B2|2018-08-24|2021-02-23|Bank Of America Corporation|Federated authentication for information sharing artificial intelligence systems|

---

US20200125470A1|2018-10-22|2020-04-23|General Electric Company|Active asset monitoring|

---

CN110033181B|2019-03-29|2021-06-11|华中科技大学|Power generation equipment state evaluation method based on self-encoder|

法律状态:
2018-10-30| B03A| Publication of an application: publication of a patent application or of a certificate of addition of invention|

优先权:

---

申请号 | 申请日 | 专利标题

---

EP16173941.2A|EP3255581A1|2016-06-10|2016-06-10|Digital pattern prognostics|

---