• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    Computer-implemented automated communication method. The method uses generic chatbot elements (311-314) associated with process steps that specialize in a subset of communications. The method comprises receiving a user message, identifying a process step based on the user message, generalizing the content of the user message to form a generalized message based on the identified process step, and transmitting the generalized message to the generic chatbot element associated with the identified process step.
    公开号:FI20185084A1
    申请号:FI20185084
    申请日:2018-01-31
    公开日:2019-08-01
    发明作者:Ville Ruutu；Hilla Pyykkönen；Anssi Grekula；Jussi Ruutu
    申请人:Elisa Oyj；
    IPC主号:
    专利说明:

    COMPUTER IMPLEMENTED AUTOMATIC COMMUNICATION SOLUTION
    The present invention relates generally to a computer-implemented automated communication solution.
    Chat is an increasingly popular channel in various electronic customer service and sales functions. Several companies and communities offer a chat channel on their websites and mobile apps. Other technical communication applications are also becoming more common in the consumer segment.
    A chatbot element is an automated communication solution designed to have a conversation with a person, for example on a website or similar electronic service. In practice, a chatbot element is a computer program programmed to simulate a client server (or more generally 15 chat partners). The person writes a line or two of text, and the chatbot element answers or asks counter-questions.
    The operation of chatbot elements can be based on different technologies:
    • Rule-based. The chatbot element is programmed with rules that make it work. For example, the chatbot element is programmed to ask questions and identify keywords in the responses, based on which the next message is decided.
    • Machine learning. The chatbot element can be taught through ongoing chat conversations. For example, deep learning models such as Long Short Term can be used in the operation
    Memory (LSTM) technology, semantic networks, generative models, etc.
    The operation of the chatbot elements is based on predictable issues and situations and how to operate in them. The implementation of a chatbot element typically requires the customization of operating models for the purpose in question and / or the teaching of the chatbot element by means of example situations.
    20185084 PRH 31 -01-2018
    A new approach to automated communication solutions is now being offered.
    A first aspect of the invention provides a computer-implemented automated communication method. The method uses generic chatbot elements associated with process steps 5 that specialize in some area of communication.
    The method receives a user message, identifies a process step based on the user message, generalizes the content of the user message to form a generalized message based on the identified process step, and sends the generalized message to a generic chatbot element associated with the identified process step.
    In one embodiment, the communication method processes messages received through a plurality of different service channels.
    In one embodiment, the communication method handles messages received by several different service providers.
    In one embodiment, generalization removes service-specific information from the message and / or changes the content of the message.
    In one embodiment, multiple user messages are processed, some of the user messages are generalized, and some of the user messages are sent to the generic chat element without generalization.
    In one embodiment, a response is received from the generic chatbot element and a response is sent to the user.
    In one embodiment, a user message (with or without generalization) is sent to more than one generic chatbot element, more than one of the generic chatbot elements is received
    20185084 PRH 31 -01-2018 response proposal and the response to be sent to the user is selected from the mentioned response proposals.
    In one embodiment, the selection of the response to be sent to the user is based on the performance metrics and / or reliability indicators of the 5 generic chatbots.
    In one embodiment, the at least one generic chatbot element is adapted to handle small talk situations, appointments, and / or information retrieval requests.
    In one embodiment, at least one generic chatbot element is adapted to handle appointments, and said generalization removes from the message information about what is being booked.
    In one embodiment, the method is performed in a chat master element adapted to receive user messages through a plurality of different service channels and to communicate with generic chatbot elements.
    Another aspect of the invention provides a device comprising a processor and a computer program stored in memory 20 configured together with said processor to control said device to perform the method of the first aspect. The device according to the second aspect of the invention may further be adapted to perform the method according to any embodiment related to the first aspect.
    A third aspect of the invention provides a computer program comprising computer executable program code which, when executed, directs a device to perform a method according to the first aspect or any related embodiment.
    The computer program according to the third aspect may comprise program code which can be executed, for example, by any of the following: a general-purpose processor, a microprocessor, an application-specific integrated circuit, and a digital signal processor. The computer program according to the third aspect may be stored on computer-readable media. Such media may be, for example, a floppy disk, CDROM, DVD, BD (Bluray Disc), memory stick, or other magnetic or optical storage medium.
    5 The invention will now be described, by way of example, with reference to the accompanying drawings, in which:Figure 1 shows an example of a device suitable for the inventionimplementation of embodiments; 10 Figure 2 shows a method according to an embodiment of the inventionan illustrative flowchart;Figure 3 shows a system according to an embodiment of the invention;Figure 4 illustrates an embodiment of the inventioncommunication event; and 15 Figure 5 illustrates another embodiment of the inventioncommunication event.
    20185084 PRH 31 -01-2018
    In one embodiment, a communication solution is provided that uses generic, process-associated chatbot elements. Each generic chatbot20 element specializes in some area of customer interaction and one chatbot element does not even attempt to cover all situations. In this context, a generic chatbot element means a chatbot element that is not configured or trained to handle only conversations of a particular service, organization, product, or the like, but of a particular type of service situation 25, regardless of the service to which the situation relates.
    In one embodiment, the generic chatbot elements are configured / trained to handle a certain sufficiently narrow part of the customer interaction, such as opening a conversation, ending a conversation, scheduling, subscribing, canceling, bug reporting, inquiring about additional information (e.g. It can be defined that chatbotel elements are generic in that they can handle different services and different
    20185084 PRH 31 -01-2018 messages related to companies and organizations, and at the same time specialize in a certain area of interaction.
    An arrangement according to one embodiment comprises a set of generic chatbot5 elements and a chat master element which manages the communication traffic between different communication applications and said generic chatbot elements. One function of the chat master element is to identify a process step from a user message sent by a communication application and, based on the process step, to select a suitable generic chatbot element for processing that message.
    If necessary, the chat master element generalizes the content of the user's message based on the identified process step to a form understood by the generic chatbot element and forwards the generalized message thus formed for processing by the generic chatbot element. In generalization, information that is too ad hoc for the 15 generic chatbot elements is removed or obscured from the user's message. This ensures the ability of the chatbot element to be able to handle different topics / products / services (genericity). In other words, the communication solution as a whole is generic in that it is industry-independent. It should be noted that the chat master element can generalize some of the user's messages and 20 process some of the user's messages without generalizing.
    In one embodiment, the chat master element and the generic chatbot elements may exchange metadata in addition to messages, which may be, for example, information related to generalizations made, information related to an identified user, or context-related information. 25
    The decision-making of the chat master element can be based on rules, or customer interaction process models can be used in decision-making that model typical customer interaction event functions. For example, the process models may be in a graphical format, such as flowcharts, in a text format, such as XML, or other suitable format. Individual process steps can include various parameters such as process step type / type, process step complexity, process step criticality, process step value, process step input, process step output, process step functions,
    20185084 PRH 31 -01-2018 internal flow chart of the process phase. In addition, the process step may be associated with one or more generic chatbot elements. It should be noted here that not all process steps are necessarily associated with a generic chatbot element, but at least one process step is associated with a generic chatbot element.
    Additionally or alternatively, different machine learning models can be utilized in the decision making of the chat master element. For example, a user message can be fed into a classification model (neural network, support vector machine, etc.) that results in the most likely generic chatbot element capable of processing the message. In addition to the user message, other information can be used as input to the machine learning models, such as profile information related to the identified user (age, gender, purchased services / products, open malfunctions or job requests, etc.), web behavior (before the communication event), customer positioning in the customer interaction process, etc.
    In one embodiment, the chat master element may put the user's message for processing on more than one generic chatbot element, and evaluate, for example, the generic chatbot elements based on reliability indicators and / or proportionality criteria, which of the best response suggestions.
    In one embodiment, feedback can be utilized in selecting a generic chatbot element as follows
    - If at a certain stage of the conversation 1 with the user 1 (for example at the beginning of the conversation, where the user presents his needs) it is possible to choose from several generic chatbot elements, the chat master element selects the chatbot element A.
    - In a conversation with 2 users 2, the chat master element selects the chatbot element B. The needs of users 1 and 2 are similar.
    - Ex-post comparison with statistically sufficient data, which choice was better. For example, the duration of the conversation (time, messages) of the selected chatbot element can be used as a criterion. For example, a faster performing chatbot element can be considered better. In addition, it can be
    20185084 PRH 31 -01-2018 look at the conversation as a whole, ie for example how many other chatbot elements the conversation has to be transferred to later process steps. Based on this analysis, the preferred chatbot element can later be favored and selected to be more likely to be used in the future.
    In one embodiment, the chat master element may utilize external data sources, such as customer relationship management (CRM) systems.
    In one embodiment, the chat master element may direct the first messages to be processed by the human agent, and the selection made by the human agent may be used to mechanically teach the chat master element. In one embodiment, the chat master element may decide, based on the machine learning model, how reliably the required chatbot element can be selected, and if the reliability is below a certain threshold, a message is directed to the human agent for decision.
    In one embodiment, messages generated by generic chatbots are personalized with additional information if the user can be identified.
    In one embodiment, the generic chatbot elements can validate the response they generate with a human agent. The human agent can accept, reject or amend the proposal. The feedback provided by the human agent can be used to mechanically teach the chatbot element.
    Figure 1 shows an example of a device 10 suitable for carrying out embodiments of the invention. The device may be, for example, a general purpose computer or server and may be adapted to perform, for example, the method shown in Figure 2 below.
    The device 10 comprises a processor 11 for controlling the operation of the device and a memory 12 comprising a computer program Z software 13 and a database 14. The computer software 13 may comprise instructions for the processor to control the device 10, such as an operating system and various applications. In addition, the computer software 13 may comprise
    20185084 PRH 31-01-2018, comprising instructions for controlling the device 10 so as to provide functionality in accordance with an embodiment of the invention.
    The processor 11 may be, for example, a computer processor (central processing unit, 5 CPU), a microprocessor, a digital signal processor (DSP), a graphics processor, or the like. The figure shows one processor, but the device may have several processors.
    The memory 12 may be, for example, read-only memory (ROM), programmable read-only memory (PROM) 10, erasable programmable read-only memory (EPROM), electronically erasable programmable read-only EEPROM memory), random access memory (RAM), flash memory, optical or magnetic memory, or the like. Your device may have multiple memories. The memory may be part of the device 10 or it may be a separate module that can be connected to the device 10 15. The memory can only be used to store data or it can also be used for data processing.
    In addition, the device 10 comprises a communication unit 15. The communication unit provides an interface for communicating with other devices. The interface may be, for example, a wired, wired connection, such as an Ethernet connection or an ADSLA / DSL connection, or a wireless connection, such as a WLAN, Bluetooth, GSM / GPRS, CDMA, WCDMA or LTE connection. The communication interface module may be integrated in the device 10 or may be part of an adapter, card or the like which may be connected to the device 10. The communication unit may support one or more communication technologies or the device may have several communication units.
    To receive input from the user and provide output to the user, the device 10 may also comprise a user interface unit (not shown), which may comprise, for example, a display and keyboard (not shown), which may be an integral part of the device 10 or independent parts connectable to the device 10.
    However, the user interface may not be required or the user interface may be implemented remotely via the communication unit 15.
    20185084 PRH 31 -01-2018
    In addition to or instead of the elements shown in Figure 1, the device 10 may comprise other elements.
    In one embodiment, the processor 11 together with the computer software 13 implements the functionality of the above-mentioned chat master element. In addition, the processor 11 and the computer software 13 can implement the functionality of the above-mentioned generic chatbot elements.
    Figure 2 shows a flow chart illustrating a method 10 according to an embodiment of the invention. The method can be performed, for example, in a chat master element implemented by the device of Figure 1 or another similar device.
    The steps in Figure 2 are explained below:
    201: A user message is received. The message is received, for example, from one of the 15 communication applications, such as a chat channel on a company's website.
    202: Based on the user's message, the process step to which the message relates is identified. The process step can be, for example, opening a conversation, ending a conversation, making an appointment, subscribing, canceling, reporting a bug, asking for more information (e.g., finding out contacts, opening hours, or payment methods), or some other stage of the conversation.
    203: The content of the user's message is generalized to form a generalized message. For example, the message “I would like to make an appointment for a haircut” can be generalized to “I would like to make an appointment” or “I would like to make an appointment * DESTINATION *”. Correspondingly, the message “I would make a bug report from my mobile phone” can be generalized to “I would make a bug report 25 * DESTINATION *” or “I would make a bug report” and the message “I want to register for Elisa's Annual General Meeting” can be generalized to “I want to register * DESTINATION *” or “I want to register”.
    204: The generalized message is sent to the generic chatbot element associated with the identified process step.
    205: A response is received from that chatbot element.
    206: The reply is sent to the user through the channel from which the user's original message came.
    20185084 PRH 31 -01-2018
    In the context of generalization, a generalized message may be accompanied by metadata, such as information about the communication channel from which the message came, or additional content-related information such as the number of people in the booking (eg restaurant or hotel booking) or the desired booking length (eg number of hotels) or whether there is food serving at the event (in which case a follow-up question on diet can be asked). It should be noted, however, that in all cases such metadata is not required.
    Figure 3 shows a system according to an embodiment of the invention. The system comprises a plurality of communication applications # 1, # 2 ... # n 302-304, a chat master element 310, a plurality of chatbot elements # 1, # 2, # 3, # n 311-314, an agent element 315, and a plurality of backend elements # 1, #n 316-317.
    The communication applications 302-304 may be, for example, chat channels on the websites 15 of different companies. Thus, different communication applications 302-304 may be services of different companies or organizations.
    The communication applications 302-304 communicate with the chat master element 310, which provides the communication applications 302-304 with a computer-implemented automatic communication service. In addition, the chat master element 310 manages message traffic between the communication applications 302-304 and the chatbot elements 311-314. The chat master element 310 identifies the process step from the user messages sent by the communication applications and, based on the process step, selects one of the chat bubble elements 311-314 to process that message. If necessary, the chat master 25 element 310 generalizes the content of the user's message to a format understood by the chatbot element 311-314 selected on the basis of the identified process step and forwards the generalized message thus formed to the chatbot element 311-314 for processing.
    Depending on the functionality of the chatbot element 311-314, the chatbot elements may retrieve additional information from the backend systems. In the example shown in Figure 3, chatbot element # 2 312 may retrieve information from backend element # 1316 and chatbot element # n 314 may retrieve information from backend element # n 317. Backend elements 316-317 may be, for example, different knowledge bases or reservation systems.
    20185084 PRH 31 -01-2018
    In addition, the chatbot elements 311-314 may transfer the message to the agent element 315 for processing, whereby the human agent handles the response to the message, for example in problem situations. Accordingly, the chat master element 310 may also transfer the message to the agent element 315 for processing, for example, if the chat master element 5 310 fails to identify the process step and / or cannot find a suitable chat element to process the message.
    In one embodiment, the chat master element 310, the chatbot elements 311-314, and the agent element 315 form a unified communication service (shown by 10 dashed lines in Figure 3). In another embodiment, one or more of the chatbot elements 311-314 is implemented separately from the communication service comprising the chat master element 310. Accordingly, the agent 315 may be separate from the communication service comprising the chat master element 310.
    Figure 4 illustrates a communication event according to an embodiment of the invention. The example transaction is processed in a system comprising a chat master element 310, a small talk bot 411, an appointment bot 412, and a reservation system 416. The communication transaction proceeds as follows:
    - 4.a: User sends message: “Hello” (User message # 1)
    - 4.b: The Chat master element identifies the message as a general conversation based on keyword recognition. For example, keyword recognition is used because the message is short. The chat master element redirects the message to a small talk bot that specializes in public chat.
    - 4.c, 4.d: The Small talk bot retrieves the “Hello, how can I help” response from the machine learning model, which is delivered to the user (Bot message # 1).
    - 4.e The user asks: "Do you have free time on Tuesday afternoon " (User Post # 2)
    - 4.f, 4.g: The chat master element uses the machine learning model and process modeling to identify the appointment of the message. The chat master element generalizes the content of the message (e.g., “free time” is replaced by the tag “resources” that models any item to be booked), and redirects the message to an appointment bot that specializes in scheduling
    20185084 PRH 31 -01-2018 with metadata (metadata can be related to, for example, which channel / web page, etc. the message is related to).
    - 4.h: The appointment bot analyzes the generalized message and ensures that there is a sufficient probability of an appointment (e.g., by classifying the message using a naive Bayesian model based on a predictive model based on a document-term matrix based on previous message history).
    - 4.i, 4.j: The appointment bot picks up key concepts from the generalized message (“Tuesday”, “Afternoon”). The appointment bot identifies the desired appointment system based on the metadata included in the generalized message (the appointment system of the channel / web page to which the message relates). The appointment bot sends a query to the appointment system about free resources (times).
    - 4.k, 4.I: The appointment bot receives a list of free times from the appointment system and generates a response that goes through the chat master element to the user “Yes, we would have free times from 2pm to 3pm on Tuesday. Will this be booked ” (Bot post # 2)
    - 4.m: The user answers "Yes." (User Post # 3)
    - 4.n, 4.O, 4.p, 4.q: The response is identified in the chat master element as a continuation of the previous message and thus the message is forwarded to the appointment bot. The appointment bot recognizes the confirmation, communicates with the appointment system, and confirms the reservation to the customer “Reservation confirmed, ID A123” (Bot message # 3).
    Figure 5 illustrates a communication event according to another embodiment of the invention. The example event is processed in a system comprising a chat master element 310, a small talk bot 411, an intelligence bot 513, and a knowledge base 517. The communication event may be a continuation of the communication event of Figure 4 or its own independent communication event. Communication event 30 proceeds as follows:
    - 5.a: The user asks "Can you pay with Visa " (User Post # 4)
    20185084 PRH 31 -01-2018
    - 5.b, 5.c: The chat master element uses a machine learning model and process modeling to identify an inquiry about additional information about the message (often in connection with an appointment the next step is an inquiry related to e.g. payment). The chat master element directs the message to an intelligence bot specializing in information retrieval together with metadata (metadata can be related to, for example, which channel / web page, etc. the message is related to). The chat master element can also generalize the content of the message.
    - 5.d, 5.e, 5.f: The intelligence bot analyzes the sentence and picks up the key terms “pay”, “Visa”. The intelligence bot supports modeling based on previous messages, which classifies the intelligence into the category “supported payment methods”. The intelligence bot identifies the desired knowledge system based on the metadata accompanying the generalized message (the knowledge base associated with the channel / web page to which the message relates). The intelligence bot sends a query to the knowledge base regarding the desired additional information.
    - 5.g, 5.h: Knowledge Base returns search results to the intelligence bot, which modifies the response message "Visa, Diners and Mastercard are supported." (Bot post # 4)
    - 5.i: The user ends the conversation "Ok, thank you." (User Post # 5)
    - 5.j, 5.k, 5.I: The chat master element recognizes the message as thankful based on keyword recognition. For example, keyword recognition is used because the message is short. The chat master element redirects the message to a small talk bot that specializes in public chat. The small talk bot retrieves from the machine learning model the answer “It doesn’t last” and is delivered to the user (Bot message # 5).
    It should be noted that all the messages in Figures 4 and 5 pass through the chat master element, although not all the operations performed in the chat master element are plotted for all steps. In addition, it should be noted that Figures 4 and 5 show only a few individual examples of communication events and, of course, the system can also handle other and also very different communication events. It should further be noted that Figures 4 and 5 show only some examples of generic chatbot elements according to different embodiments. The following is
    20185084 PRH 31 -01-2018 listed more examples of possible generic chatbots: feedback query bot, pre-data query bot, bug reporting bot, enrollment bot, reporting bot (eg reporting electricity meter reading, reporting water meter reading, reporting potholes in the road, etc.) It should be noted that there may be 5 generic chatbot elements for other aspects of the conversation as well.
    The above description provides non-limiting examples of some embodiments. However, it will be apparent to one skilled in the art that the invention is not limited to the details set forth, but that the invention may be practiced in other equivalent ways. For example, it is to be understood that in the disclosed methods, the order of the individual method steps may be changed and that some steps may be repeated several times or omitted altogether. It is also to be understood that the terms in this document comprise and include are open expressions and are not intended to be limiting.
    Different embodiments of the invention may allow for a better customer experience. In addition, various embodiments of the invention can speed up and facilitate the implementation of a communication solution based on the use of chatbotel elements. Still further, different embodiments of the invention may increase the utilization of the automation provided by communication solutions based on the use of chatbot elements, when the same generic chatbot element can be utilized in several different services. The chatbot element does not necessarily need to know which channel or service message it is processing. Instead, regardless of the channel or service, the same chatbot element can handle messages in exactly the same way.
    The generalization according to the different embodiments of the invention makes it possible that things with different details can be handled with the same chatbot element. For example, restaurant reservations, barber reservations, and hotel reservations can be processed by the same appointment bot.
    The various embodiments of the invention allow the generic chat bubble elements to be manufactured by different vendors. Furthermore, different embodiments of the invention allow the same generic chatbot element to be utilized in the service of several different clients.
    In addition, some features of the exemplary embodiments shown can be utilized without the use of other features. The foregoing description is to be construed as merely illustrative of the principles of the various embodiments. The scope is limited only by the appended claims.
    权利要求:
    Claims (15)
    [1]
    The claims
    1. A computer-implemented automatic communication method, characterized in that the method
    5 using generic chat steps associated with the process steps (311-314, 411, 412, 513) specializing in a communication sub-area, receiving (201) a user message, identifying (202) the process step based on the user message,
    10 generalizing (203) the content of the user's message to form a generalized message based on the identified process step, and sending (204) the generalized message to the generic chatbot element associated with the identified process step.
    15
    [2]
    A method according to claim 1, characterized in that said communication method processes messages received via a plurality of different service channels (302, 304).
    [3]
    Method according to claim 1 or 2, characterized in that said communication method 20 processes messages received by a service (302-304) of several different service providers.
    [4]
    Method according to any one of claims 1 to 3, characterized in that said generalization (203) removes service-specific information from the message and / or changes the message
    25 contents.
    [5]
    Method according to one of Claims 1 to 4, characterized in that the method processes several user messages, generalises part of the user messages and sends some of the user messages to a generic chatbot element.
    30 without generalization.
    20185084 PRH 31 -01-2018
    [6]
    Method according to one of Claims 1 to 5, characterized in that the method receives (205) a response from the generic chatbot element and sends (206) the response to the user.
    5
    [7]
    Method according to claim 6, characterized in that the method sends a user message to more than one generic chat element (311-314, 411, 412, 513), receives more than one response proposal from the generic chat elements (311-314, 411, 412, 513) and selecting a response to be sent to the user from said response suggestions.
    [8]
    Method according to claim 7, characterized in that the selection of the response to be sent to the user is based on the performance metrics and / or reliability indicators of the generic chatbot elements (311314, 411,412, 513).
    15
    [9]
    Method according to one of Claims 1 to 8, characterized in that the at least one generic chatbot element (411) is adapted to handle small talk situations.
    [10]
    Method according to one of Claims 1 to 9, characterized in that the at least one generic chatbot element (412) is adapted to process appointments.
    [11]
    Method according to any one of claims 1 to 10, characterized in that the at least one generic chatbot element (412) is adapted to process appointments, and said generalization removes from the message information about what is being reserved.
    [12]
    Method according to one of Claims 1 to 11, characterized in that the at least one generic chatbot element (513) is adapted to process information retrieval requests.
    30
    [13]
    Method according to one of Claims 1 to 12, characterized in that the method is carried out in a chat master element (310) which is adapted to receive user messages via a plurality of different service channels (302, 304) and to communicate with generic chat bot elements (311-314). ).
    [14]
    An apparatus (10) comprising a processor (11) and a computer program (13) stored in memory configured together with said processor to control said apparatus to perform any of claims 1-13.
    5 method.
    [15]
    A computer program comprising computer executable program code, characterized in that upon execution, the program code directs the computer to perform any of the methods of claims 1-13.
    类似技术:
    公开号 | 公开日 | 专利标题
    US10511560B2|2019-12-17|Systems and methods for electronic message prioritization
    US10452783B2|2019-10-22|Conversational agent
    US10083451B2|2018-09-25|Using semantic processing for customer support
    KR101103949B1|2012-01-12|System and method for preference application installation and execution
    US20190019197A1|2019-01-17|Determining to dispatch a technician for customer support
    US11031001B1|2021-06-08|Action agent architecture in a scalable multi-service virtual assistant platform
    US20090003309A1|2009-01-01|Capability or role-based routing
    US20180143989A1|2018-05-24|System to assist users of a software application
    US20210142291A1|2021-05-13|Virtual business assistant ai engine for multipoint communication
    JP6035404B1|2016-11-30|Visit preparation system
    EP3821352A1|2021-05-19|Machine learning tool for navigating a dialogue flow
    Kim et al.2020|A study on the restaurant recommendation service app based on AI chatbot using personalization information
    US20200279228A1|2020-09-03|Mobile secretary cloud application
    US20210374811A1|2021-12-02|Automated identity resolution in connection with a campaign management platform
    JP2019125011A|2019-07-25|Artificial intelligence loudspeaker system, and application software
    US11272015B2|2022-03-08|Function-as-a-service for two-way communication systems
    FI128511B|2020-06-30|Automatic communication solution implemented on a computer
    US20210201346A1|2021-07-01|Platform for Optimization and Personalization of Existing Communication Channels
    US20090007230A1|2009-01-01|Radio-type interface for tuning into content associated with projects
    US20200151254A1|2020-05-14|Processing communications using a prototype classifier
    US20180130067A1|2018-05-10|Managing agent relationships with a set of contacts via templated messages
    US11122001B2|2021-09-14|Systems and methods for a proactive two-way conversation
    US20210272128A1|2021-09-02|Contextual user interface interaction logging and analysis
    JP2019109905A|2019-07-04|Account name identification system
    McInerney2014|Intelligent agents for mobile location services
    同族专利:
    公开号 | 公开日
    FI128511B|2020-06-30|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    法律状态:
    2020-06-30| FG| Patent granted|Ref document number: 128511 Country of ref document: FI Kind code of ref document: B |
    优先权:
    申请号 | 申请日 | 专利标题
    FI20185084A|FI128511B|2018-01-31|2018-01-31|Automatic communication solution implemented on a computer|FI20185084A| FI128511B|2018-01-31|2018-01-31|Automatic communication solution implemented on a computer|
    [返回顶部]