system

Abstract

The system according to this embodiment aims to provide quick and accurate replies in a communication tool. [Solution] The system according to the embodiment comprises a learning unit, a suggestion unit, and a generation unit. The learning unit learns past interactions. The suggestion unit suggests a reply template at an appropriate time based on the content learned by the learning unit. The generation unit generates a natural response based on the template suggested by the suggestion unit.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to provide a quick and accurate reply in a communication tool, and there is room for improvement in efficiency.

[0005] The system according to the embodiment aims to provide a quick and accurate reply in a communication tool.

Means for Solving the Problems

[0006] The system according to the embodiment includes a learning unit, a proposal unit, and a generation unit. The learning unit learns past interactions. The proposal unit proposes a reply template at an appropriate timing based on the content learned by the learning unit. The generation unit generates a natural response based on the template proposed by the proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide quick and accurate replies in a communication tool. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The communication efficiency system according to an embodiment of the present invention is a system for streamlining replies to communication tools by utilizing an AI agent. This system enables rapid and accurate communication by learning past interactions, proposing reply templates at the appropriate time, and generating natural responses by understanding the flow of conversation. For example, the communication efficiency system analyzes and learns the content of past messages, the timing of replies, and the writing style. This allows it to learn interactions related to a specific project or interactions with specific members and propose appropriate reply templates. Next, when a user receives a new message, the communication efficiency system proposes an appropriate reply template based on past interactions. This allows the user to reply quickly. Furthermore, the communication efficiency system analyzes the content of the received message and generates an appropriate response. This allows the user to continue a natural conversation. This mechanism is expected to improve the efficiency and productivity of communication tool responses. For example, users can reduce the time spent replying and concentrate on other important tasks. In addition, the communication efficiency system's generation of natural responses improves the quality of communication and enables reliable interactions. As a result, the communication efficiency system can achieve rapid and accurate communication.

[0029] The communication efficiency system according to the embodiment comprises a learning unit, a suggestion unit, and a generation unit. The learning unit learns past interactions. The learning unit analyzes and learns, for example, the content of past messages, the timing of replies, and the writing style. For example, the learning unit can learn interactions related to a specific project or interactions with specific members. The learning unit analyzes the content of past messages and collects data for suggesting appropriate reply templates. The suggestion unit suggests a reply template at an appropriate time based on the content learned by the learning unit. For example, when a user receives a new message, the suggestion unit suggests an appropriate reply template based on past interactions. The suggestion unit provides a template for the user to reply quickly based on past interactions. The generation unit generates a natural response based on the template suggested by the suggestion unit. For example, the generation unit analyzes the content of a received message and generates an appropriate response. The generation unit generates a response that allows the user to continue a natural conversation. For example, the generation unit generates a contextually appropriate response based on the content of a received message. As a result, the communication efficiency system according to the embodiment can achieve fast and accurate communication.

[0030] The learning unit learns from past interactions. For example, it analyzes and learns from the content of past messages, the timing of replies, and writing style. Specifically, the learning unit uses natural language processing techniques to analyze past messages and extract the intent and emotions of each message. This allows the learning unit to learn about interactions related to specific projects or interactions with specific members. For example, it can understand appropriate replies according to the progress of a project, and the writing style and expressions preferred by specific members. Furthermore, the learning unit analyzes the content of past messages and collects data to suggest appropriate reply templates. This includes message topics, frequently occurring keywords, and reply patterns. Based on this data, the learning unit builds a foundation for generating templates that enable users to reply quickly and effectively. By continuously incorporating new data and updating its learning model, the learning unit can always respond to the latest communication patterns. This allows the learning unit to respond flexibly to the user's communication style and needs, improving the accuracy and usefulness of the entire system.

[0031] The suggestion unit proposes reply templates at the appropriate time based on what it has learned from the learning unit. For example, when a user receives a new message, the suggestion unit proposes an appropriate reply template based on past interactions. Specifically, the suggestion unit analyzes the content of the received message, refers to similar past interactions, and selects the most appropriate reply template. The suggestion unit considers the user's past reply patterns and writing style to provide templates that enable the user to reply quickly. For example, if the suggestion unit receives a message about a specific project, it will propose an appropriate reply template based on past interactions related to that project. The suggestion unit can also optimize the timing of replies based on the user's schedule and priorities. This allows the suggestion unit to support users in communicating efficiently and to achieve quick and accurate replies. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy of its suggestions. For example, it can optimize the suggestion algorithm by evaluating whether the user adopted the suggested template and their satisfaction with the suggestions. This allows the suggestion unit to provide highly accurate suggestions tailored to user needs and support more efficient communication.

[0032] The generation unit generates natural responses based on templates proposed by the suggestion unit. For example, the generation unit analyzes the content of a received message and generates an appropriate response. Specifically, the generation unit uses natural language generation technology to generate contextually appropriate responses based on the proposed templates. The generation unit considers the tone and style of the message in order to generate responses that allow the user to continue a natural conversation. For example, if the received message is formal, the generation unit generates a response in a formal style; if it is casual, it generates a response in a casual style. The generation unit can also generate responses that include appropriate information and suggestions depending on the content of the message. In this way, the generation unit provides support for users to communicate naturally and effectively. Furthermore, the generation unit can continuously improve its generation algorithm based on user feedback. For example, it optimizes the generation algorithm by evaluating whether the user adopted the generated response and their satisfaction with the response content. In this way, the generation unit can provide highly accurate responses tailored to user needs and support the efficiency of communication.

[0033] The reception unit can receive user input. The reception unit can receive user input in the form of, for example, text input, voice input, or gesture input. The reception unit provides an interface for the user to give instructions to the system. For example, the reception unit can provide a text box for the user to enter a text message. The reception unit can also provide a microphone input for the user to give instructions by voice. Furthermore, the reception unit can provide a gesture recognition function for the user to give instructions by gesture. In this way, by receiving user input, the reception unit can enable the system to operate based on the user's instructions. Some or all of the above processing in the reception unit may be performed using, for example, AI, or not using AI. For example, the reception unit can input the user's voice input into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0034] The service provider can provide the generated response. The service provider can provide the generated response in the form of, for example, a text message or an audio message. The service provider can provide a response that allows the user to reply quickly. For example, the service provider can display the generated text message in the user's chat window. The service provider can also play the generated audio message through the user's speaker. Furthermore, the service provider can provide the generated response as an email or push notification. This allows the service provider to provide the generated response, enabling the user to reply quickly. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the generated text message into a generating AI and have the generating AI perform the conversion from text data to audio data.

[0035] The learning unit can analyze and learn from the content of past messages, the timing of replies, and the writing style. For example, the learning unit can analyze the content of past messages and collect data to suggest appropriate reply templates. Based on the content of past messages, the learning unit learns the user's reply patterns. For example, the learning unit can analyze the content of past messages and learn about interactions related to a specific project or interactions with specific members. The learning unit can also analyze the timing of replies to past messages and learn appropriate reply timings. Furthermore, the learning unit can analyze the writing style of past messages and learn appropriate writing styles. As a result, by analyzing and learning from the content of past messages, the timing of replies, and the writing style, the learning unit can suggest more appropriate reply templates. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the content of past messages into a generating AI and have the generating AI perform message analysis.

[0036] The suggestion unit can propose appropriate reply templates based on past interactions. For example, the suggestion unit provides templates that allow users to reply quickly based on past interactions. The suggestion unit analyzes past interactions and selects appropriate reply templates. For example, the suggestion unit analyzes the content and context of past interactions and proposes appropriate reply templates. The suggestion unit can also analyze the timing of replies in past interactions and propose appropriate reply timing. Furthermore, the suggestion unit can analyze the writing style of past interactions and propose reply templates with appropriate writing styles. In this way, the suggestion unit enables users to reply quickly by proposing appropriate reply templates based on past interactions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the content of past interactions into a generation AI and have the generation AI select reply templates.

[0037] The generation unit can analyze the content of a received message and generate a natural response. For example, the generation unit can generate a contextually appropriate response based on the content of the received message. The generation unit analyzes the content of a received message and generates an appropriate response. For example, the generation unit analyzes the content of a received message and generates a grammatically correct and contextually consistent response. The generation unit can also analyze the content of a received message and generate a response with an appropriate tone and style. Furthermore, the generation unit can analyze the content of a received message and generate a response that includes appropriate information. In this way, the generation unit can analyze the content of a received message and generate a natural response, allowing the user to continue a natural conversation. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input the content of a received message into a generation AI and have the generation AI perform the generation of the response.

[0038] The learning unit can learn not only from the content of past messages but also by considering the relationship between the message sender and recipient. For example, if the message sender and recipient are a boss and a subordinate, the learning unit will learn an appropriate reply pattern based on that relationship. The learning unit analyzes the relationship between the message sender and recipient and learns an appropriate reply pattern. For example, if the message sender and recipient are colleagues, the learning unit will learn friendly interactions. The learning unit can also learn businesslike interactions if the message sender and recipient are a customer and a representative. In this way, the learning unit can learn more appropriate reply patterns by considering the relationship between the message sender and recipient. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input relationship data between the message sender and recipient into a generating AI and have the generating AI perform the learning of reply patterns.

[0039] The learning unit can analyze the time of day and frequency of message transmissions during training to learn the optimal timing for replies. For example, the learning unit can analyze the time of day of message transmissions to learn the time of day when replies are most frequent. The learning unit can analyze the time of day and frequency of message transmissions to learn the appropriate timing for replies. For example, the learning unit can analyze the frequency of message transmissions to learn the times when exchanges occur most frequently. The learning unit can also learn the optimal timing for replies by combining the time of day and frequency of message transmissions. As a result, the learning unit can provide more appropriate replies by analyzing the time of day and frequency of message transmissions and learning the optimal timing for replies. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input message transmission time and frequency data into a generating AI and have the generating AI perform the learning of reply timing.

[0040] The learning unit can learn region-specific communication styles by considering the user's geographical location during the learning process. For example, if the user is in Japan, the learning unit will learn Japanese-specific honorifics and manners. The learning unit analyzes the user's geographical location and learns an appropriate communication style. For example, if the user is in the United States, the learning unit will learn a casual communication style. The learning unit can also learn French-specific expressions and greetings if the user is in France. As a result, the learning unit can communicate more appropriately by learning region-specific communication styles by considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's geographical location into a generating AI and have the generating AI perform the communication style learning.

[0041] The learning unit can analyze the user's social media activity during training and learn relevant communication patterns. For example, the learning unit can learn expressions and hashtags that the user frequently uses on social media. The learning unit analyzes the user's social media activity and learns appropriate communication patterns. For example, the learning unit can analyze the user's interactions on social media and learn appropriate reply patterns. The learning unit can also learn the user's comments and message exchanges on social media. As a result, the learning unit can provide more appropriate replies by analyzing the user's social media activity and learning relevant communication patterns. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's social media activity data into a generating AI and have the generating AI perform the learning of communication patterns.

[0042] The proposal unit can adjust the level of detail in templates based on the importance of past interactions when making a proposal. For example, the proposal unit will propose a detailed template for important interactions. The proposal unit analyzes the importance of past interactions and adjusts the level of detail in templates appropriately. For example, the proposal unit will propose a simple template for general interactions. The proposal unit can also propose a template that allows for a quick response for urgent interactions. In this way, the proposal unit can propose more appropriate templates by adjusting the level of detail in templates based on the importance of past interactions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input data on the importance of past interactions into a generating AI and have the generating AI perform the adjustment of the level of detail in templates.

[0043] The proposal unit can apply different template suggestion algorithms depending on the category of the interaction when making a suggestion. For example, in the case of a business interaction, the proposal unit will suggest a formal template. The proposal unit analyzes the category of the interaction and applies an appropriate template suggestion algorithm. For example, in the case of a private interaction, the proposal unit will suggest a casual template. Also, in the case of a support interaction, the proposal unit can suggest a template that enables quick problem solving. In this way, the proposal unit can suggest a more appropriate template by applying different template suggestion algorithms depending on the category of the interaction. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input the category data of the interaction into a generating AI and have the generating AI execute the application of the template suggestion algorithm.

[0044] The proposal unit can determine template priorities based on the timing of communication transmissions when making a proposal. For example, the proposal unit will prioritize suggesting templates during times when there are many important communications. The proposal unit analyzes the timing of communication transmissions and determines the appropriate template priorities. For example, the proposal unit will suggest simple templates during times when there are many general communications. The proposal unit can also suggest templates that allow for quick replies during times when there are many urgent communications. In this way, the proposal unit can suggest more appropriate templates by determining template priorities based on the timing of communication transmissions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input communication transmission timing data into a generating AI and have the generating AI perform the determination of template priorities.

[0045] The proposal unit can adjust the order of templates based on the relevance of the interactions when making a proposal. For example, the proposal unit may prioritize suggesting templates related to important interactions. The proposal unit analyzes the relevance of interactions and adjusts the order of templates appropriately. For example, the proposal unit may postpone suggesting templates related to general interactions. Alternatively, the proposal unit may prioritize suggesting templates related to urgent interactions. In this way, the proposal unit can suggest more appropriate templates by adjusting the order of templates based on the relevance of the interactions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input interaction relevance data into a generating AI and have the generating AI perform the adjustment of the template order.

[0046] The generation unit can adjust the level of detail in the response based on the importance of the received message during generation. For example, the generation unit generates a detailed response for important messages. The generation unit analyzes the importance of the received message and adjusts the level of detail in the response appropriately. For example, the generation unit generates a simple response for general messages. The generation unit can also generate a response that can be replied to quickly for urgent messages. In this way, the generation unit can generate a more appropriate response by adjusting the level of detail in the response based on the importance of the received message. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance data of the received message into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0047] The generation unit can apply different response generation algorithms depending on the message category during generation. For example, the generation unit generates a formal response for business messages. The generation unit analyzes the message category and applies an appropriate response generation algorithm. For example, the generation unit generates a casual response for private messages. The generation unit can also generate a response that can quickly resolve the problem for support messages. In this way, the generation unit can generate more appropriate responses by applying different response generation algorithms depending on the message category. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message category data into a generation AI and have the generation AI execute the application of the response generation algorithm.

[0048] The generation unit can determine the priority of responses based on the message sending time during generation. For example, the generation unit will prioritize generating responses during times when there are many important messages. The generation unit analyzes the message sending time and determines the appropriate priority of responses. For example, the generation unit will generate simple responses during times when there are many general messages. The generation unit can also generate responses that can be replied to quickly during times when there are many urgent messages. In this way, the generation unit can generate more appropriate responses by determining the priority of responses based on the message sending time. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message sending time data into a generation AI and have the generation AI perform the determination of response priorities.

[0049] The generation unit can adjust the order of responses based on the relevance of the messages during generation. For example, the generation unit can prioritize generating responses related to important messages. The generation unit analyzes the relevance of messages and adjusts the order of responses appropriately. For example, the generation unit may postpone responses related to general messages. The generation unit can also prioritize generating responses related to urgent messages. In this way, the generation unit can generate more appropriate responses by adjusting the order of responses based on the relevance of the messages. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message relevance data into a generation AI and have the generation AI perform the adjustment of the order of responses.

[0050] The reception desk can analyze the user's past input history and select the optimal reception method at the time of reception. For example, the reception desk may prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception desk analyzes the user's past input history and selects an appropriate reception method. For example, the reception desk may suggest relevant input methods by referring to content the user has entered in the past. The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. In this way, the reception desk can perform more appropriate input reception by analyzing the user's past input history and selecting the optimal reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI perform the selection of the reception method.

[0051] The reception unit can prioritize receiving inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize receiving inputs related to that location. The reception unit analyzes the user's geographical location information and prioritizes receiving appropriate inputs. For example, if the user is on the move, the reception unit will prioritize receiving inputs related to the destination. The reception unit can also prioritize receiving inputs related to the user's home if the user is at home. In this way, the reception unit can perform more appropriate input reception by prioritizing highly relevant inputs while taking into account the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location information data into a generating AI and have the generating AI determine the priority of inputs.

[0052] The service provider can analyze the user's past response history and select the optimal service method at the time of service delivery. For example, the service provider may prioritize suggesting response methods (voice, text, etc.) that the user has frequently used in the past. The service provider analyzes the user's past response history and selects an appropriate service method. For example, the service provider may suggest relevant response methods by referring to the content of the user's past responses. The service provider can also predict and suggest response methods to be used during specific time periods based on the user's past response history. In this way, the service provider can provide more appropriate responses by analyzing the user's past response history and selecting the optimal service method. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past response history data into a generating AI and have the generating AI select the service method.

[0053] The service provider can select the optimal service delivery method by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, the service provider will provide a response that is adapted to the screen size. The service provider analyzes the user's device information and selects an appropriate service delivery method. For example, if the user is using a tablet, the service provider will provide a response optimized for a large screen. The service provider can also provide a concise and highly visible response if the user is using a smartwatch. In this way, the service provider can provide a more appropriate response by selecting the optimal service delivery method by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user device information data into a generating AI and have the generating AI perform the selection of the service delivery method.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or text). It can also predict and suggest input methods that the user will use at specific times of the day. Furthermore, it can suggest input methods appropriate to specific situations based on the user's input history. By suggesting the most suitable input method considering the user's past input history, this enables smoother input.

[0056] The learning unit can analyze past message content, reply timing, and writing style, taking into account the relationship between the message sender and recipient. For example, if the message sender and recipient are a boss and a subordinate, the unit can learn appropriate reply patterns based on that relationship. If the message sender and recipient are colleagues, the unit can learn friendly communication. Furthermore, if the message sender and recipient are a customer and a representative, the unit can learn businesslike communication. In this way, by learning while considering the relationship between the message sender and recipient, the unit can learn more appropriate reply patterns.

[0057] The proposal team can apply different template suggestion algorithms depending on the category of the interaction when proposing reply templates based on past exchanges. For example, it can suggest a formal template for business interactions, a casual template for private interactions, and a template that enables quick problem resolution for support interactions. This allows for more effective communication by suggesting the appropriate template according to the category of the interaction.

[0058] The learning unit can learn region-specific communication styles by considering the user's geographical location during the learning process. For example, if the user is in Japan, it can learn Japanese-specific honorifics and etiquette. If the user is in the United States, it can learn casual communication styles. Furthermore, if the user is in France, it can learn French-specific expressions and greetings. By learning region-specific communication styles while considering the user's geographical location, more appropriate communication can be achieved.

[0059] The service provider can select the optimal service delivery method by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, it can provide a response that matches the screen size. If the user is using a tablet, it can provide a response optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible response. By selecting the optimal service delivery method considering the user's device information, a more appropriate response can be provided.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The learning unit learns from past interactions. Specifically, it analyzes the content of past messages, the timing of replies, and the writing style to learn from interactions related to specific projects and interactions with specific members. This collects data to suggest appropriate reply templates. Step 2: The suggestion unit proposes a reply template at the appropriate time based on what the learning unit has learned. For example, when a user receives a new message, it proposes an appropriate reply template based on past interactions, providing a template that allows the user to reply quickly. Step 3: The generation unit generates a natural response based on the template proposed by the proposal unit. Specifically, it analyzes the content of the received message and generates an appropriate response that fits the context. This provides the user with a response that allows them to continue the conversation naturally, enabling fast and accurate communication.

[0062] (Example of form 2) The communication efficiency system according to an embodiment of the present invention is a system for streamlining replies to communication tools by utilizing an AI agent. This system enables rapid and accurate communication by learning past interactions, proposing reply templates at the appropriate time, and generating natural responses by understanding the flow of conversation. For example, the communication efficiency system analyzes and learns the content of past messages, the timing of replies, and the writing style. This allows it to learn interactions related to a specific project or interactions with specific members and propose appropriate reply templates. Next, when a user receives a new message, the communication efficiency system proposes an appropriate reply template based on past interactions. This allows the user to reply quickly. Furthermore, the communication efficiency system analyzes the content of the received message and generates an appropriate response. This allows the user to continue a natural conversation. This mechanism is expected to improve the efficiency and productivity of communication tool responses. For example, users can reduce the time spent replying and concentrate on other important tasks. In addition, the communication efficiency system's generation of natural responses improves the quality of communication and enables reliable interactions. As a result, the communication efficiency system can achieve rapid and accurate communication.

[0063] The communication efficiency system according to the embodiment comprises a learning unit, a suggestion unit, and a generation unit. The learning unit learns past interactions. The learning unit analyzes and learns, for example, the content of past messages, the timing of replies, and the writing style. For example, the learning unit can learn interactions related to a specific project or interactions with specific members. The learning unit analyzes the content of past messages and collects data for suggesting appropriate reply templates. The suggestion unit suggests a reply template at an appropriate time based on the content learned by the learning unit. For example, when a user receives a new message, the suggestion unit suggests an appropriate reply template based on past interactions. The suggestion unit provides a template for the user to reply quickly based on past interactions. The generation unit generates a natural response based on the template suggested by the suggestion unit. For example, the generation unit analyzes the content of a received message and generates an appropriate response. The generation unit generates a response that allows the user to continue a natural conversation. For example, the generation unit generates a contextually appropriate response based on the content of a received message. As a result, the communication efficiency system according to the embodiment can achieve fast and accurate communication.

[0064] The learning unit learns from past interactions. For example, it analyzes and learns from the content of past messages, the timing of replies, and writing style. Specifically, the learning unit uses natural language processing techniques to analyze past messages and extract the intent and emotions of each message. This allows the learning unit to learn about interactions related to specific projects or interactions with specific members. For example, it can understand appropriate replies according to the progress of a project, and the writing style and expressions preferred by specific members. Furthermore, the learning unit analyzes the content of past messages and collects data to suggest appropriate reply templates. This includes message topics, frequently occurring keywords, and reply patterns. Based on this data, the learning unit builds a foundation for generating templates that enable users to reply quickly and effectively. By continuously incorporating new data and updating its learning model, the learning unit can always respond to the latest communication patterns. This allows the learning unit to respond flexibly to the user's communication style and needs, improving the accuracy and usefulness of the entire system.

[0065] The suggestion unit proposes reply templates at the appropriate time based on what it has learned from the learning unit. For example, when a user receives a new message, the suggestion unit proposes an appropriate reply template based on past interactions. Specifically, the suggestion unit analyzes the content of the received message, refers to similar past interactions, and selects the most appropriate reply template. The suggestion unit considers the user's past reply patterns and writing style to provide templates that enable the user to reply quickly. For example, if the suggestion unit receives a message about a specific project, it will propose an appropriate reply template based on past interactions related to that project. The suggestion unit can also optimize the timing of replies based on the user's schedule and priorities. This allows the suggestion unit to support users in communicating efficiently and to achieve quick and accurate replies. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy of its suggestions. For example, it can optimize the suggestion algorithm by evaluating whether the user adopted the suggested template and their satisfaction with the suggestions. This allows the suggestion unit to provide highly accurate suggestions tailored to user needs and support more efficient communication.

[0066] The generation unit generates natural responses based on templates proposed by the suggestion unit. For example, the generation unit analyzes the content of a received message and generates an appropriate response. Specifically, the generation unit uses natural language generation technology to generate contextually appropriate responses based on the proposed templates. The generation unit considers the tone and style of the message in order to generate responses that allow the user to continue a natural conversation. For example, if the received message is formal, the generation unit generates a response in a formal style; if it is casual, it generates a response in a casual style. The generation unit can also generate responses that include appropriate information and suggestions depending on the content of the message. In this way, the generation unit provides support for users to communicate naturally and effectively. Furthermore, the generation unit can continuously improve its generation algorithm based on user feedback. For example, it optimizes the generation algorithm by evaluating whether the user adopted the generated response and their satisfaction with the response content. In this way, the generation unit can provide highly accurate responses tailored to user needs and support the efficiency of communication.

[0067] The reception unit can receive user input. The reception unit can receive user input in the form of, for example, text input, voice input, or gesture input. The reception unit provides an interface for the user to give instructions to the system. For example, the reception unit can provide a text box for the user to enter a text message. The reception unit can also provide a microphone input for the user to give instructions by voice. Furthermore, the reception unit can provide a gesture recognition function for the user to give instructions by gesture. In this way, by receiving user input, the reception unit can enable the system to operate based on the user's instructions. Some or all of the above processing in the reception unit may be performed using, for example, AI, or not using AI. For example, the reception unit can input the user's voice input into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0068] The service provider can provide the generated response. The service provider can provide the generated response in the form of, for example, a text message or an audio message. The service provider can provide a response that allows the user to reply quickly. For example, the service provider can display the generated text message in the user's chat window. The service provider can also play the generated audio message through the user's speaker. Furthermore, the service provider can provide the generated response as an email or push notification. This allows the service provider to provide the generated response, enabling the user to reply quickly. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the generated text message into a generating AI and have the generating AI perform the conversion from text data to audio data.

[0069] The learning unit can analyze and learn from the content of past messages, the timing of replies, and the writing style. For example, the learning unit can analyze the content of past messages and collect data to suggest appropriate reply templates. Based on the content of past messages, the learning unit learns the user's reply patterns. For example, the learning unit can analyze the content of past messages and learn about interactions related to a specific project or interactions with specific members. The learning unit can also analyze the timing of replies to past messages and learn appropriate reply timings. Furthermore, the learning unit can analyze the writing style of past messages and learn appropriate writing styles. As a result, by analyzing and learning from the content of past messages, the timing of replies, and the writing style, the learning unit can suggest more appropriate reply templates. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the content of past messages into a generating AI and have the generating AI perform message analysis.

[0070] The suggestion unit can propose appropriate reply templates based on past interactions. For example, the suggestion unit provides templates that allow users to reply quickly based on past interactions. The suggestion unit analyzes past interactions and selects appropriate reply templates. For example, the suggestion unit analyzes the content and context of past interactions and proposes appropriate reply templates. The suggestion unit can also analyze the timing of replies in past interactions and propose appropriate reply timing. Furthermore, the suggestion unit can analyze the writing style of past interactions and propose reply templates with appropriate writing styles. In this way, the suggestion unit enables users to reply quickly by proposing appropriate reply templates based on past interactions. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or without AI. For example, the suggestion unit can input the content of past interactions into a generation AI and have the generation AI select reply templates.

[0071] The generation unit can analyze the content of a received message and generate a natural response. For example, the generation unit can generate a contextually appropriate response based on the content of the received message. The generation unit analyzes the content of a received message and generates an appropriate response. For example, the generation unit analyzes the content of a received message and generates a grammatically correct and contextually consistent response. The generation unit can also analyze the content of a received message and generate a response with an appropriate tone and style. Furthermore, the generation unit can analyze the content of a received message and generate a response that includes appropriate information. In this way, the generation unit can analyze the content of a received message and generate a natural response, allowing the user to continue a natural conversation. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input the content of a received message into a generation AI and have the generation AI perform the generation of the response.

[0072] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize selecting messages that help reduce stress as training data. The learning unit analyzes the user's emotions and selects appropriate training data. For example, if the user is relaxed, the learning unit will select interactions in a relaxed state as training data. The learning unit can also select interactions in an excited state as training data if the user is excited. This allows the learning unit to perform more appropriate learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0073] The learning unit can learn not only from the content of past messages but also by considering the relationship between the message sender and recipient. For example, if the message sender and recipient are a boss and a subordinate, the learning unit will learn an appropriate reply pattern based on that relationship. The learning unit analyzes the relationship between the message sender and recipient and learns an appropriate reply pattern. For example, if the message sender and recipient are colleagues, the learning unit will learn friendly interactions. The learning unit can also learn businesslike interactions if the message sender and recipient are a customer and a representative. In this way, the learning unit can learn more appropriate reply patterns by considering the relationship between the message sender and recipient. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input relationship data between the message sender and recipient into a generating AI and have the generating AI perform the learning of reply patterns.

[0074] The learning unit can analyze the time of day and frequency of message transmissions during training to learn the optimal timing for replies. For example, the learning unit can analyze the time of day of message transmissions to learn the time of day when replies are most frequent. The learning unit can analyze the time of day and frequency of message transmissions to learn the appropriate timing for replies. For example, the learning unit can analyze the frequency of message transmissions to learn the times when exchanges occur most frequently. The learning unit can also learn the optimal timing for replies by combining the time of day and frequency of message transmissions. As a result, the learning unit can provide more appropriate replies by analyzing the time of day and frequency of message transmissions and learning the optimal timing for replies. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input message transmission time and frequency data into a generating AI and have the generating AI perform the learning of reply timing.

[0075] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency to alleviate the burden. The learning unit analyzes the user's emotions and adjusts the learning frequency appropriately. For example, if the user is relaxed, the learning unit can increase the learning frequency to promote efficient learning. The learning unit can also adjust the learning frequency to perform learning at the appropriate time if the user is excited. In this way, the learning unit can reduce the user's burden and promote efficient learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the learning frequency.

[0076] The learning unit can learn region-specific communication styles by considering the user's geographical location during the learning process. For example, if the user is in Japan, the learning unit will learn Japanese-specific honorifics and manners. The learning unit analyzes the user's geographical location and learns an appropriate communication style. For example, if the user is in the United States, the learning unit will learn a casual communication style. The learning unit can also learn French-specific expressions and greetings if the user is in France. As a result, the learning unit can communicate more appropriately by learning region-specific communication styles by considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's geographical location into a generating AI and have the generating AI perform the communication style learning.

[0077] The learning unit can analyze the user's social media activity during training and learn relevant communication patterns. For example, the learning unit can learn expressions and hashtags that the user frequently uses on social media. The learning unit analyzes the user's social media activity and learns appropriate communication patterns. For example, the learning unit can analyze the user's interactions on social media and learn appropriate reply patterns. The learning unit can also learn the user's comments and message exchanges on social media. As a result, the learning unit can provide more appropriate replies by analyzing the user's social media activity and learning relevant communication patterns. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's social media activity data into a generating AI and have the generating AI perform the learning of communication patterns.

[0078] The suggestion unit can estimate the user's emotions and adjust the presentation of the suggested templates based on the estimated emotions. For example, if the user is stressed, the suggestion unit will suggest a simple and easy-to-understand template. The suggestion unit analyzes the user's emotions and adjusts the presentation of the appropriate template. For example, if the user is relaxed, the suggestion unit will suggest a template containing detailed information. The suggestion unit may also suggest a visually appealing template if the user is excited. In this way, the suggestion unit can suggest a more appropriate template by adjusting the presentation of the template based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI, for example, or not using AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the presentation of the template.

[0079] The proposal unit can adjust the level of detail in templates based on the importance of past interactions when making a proposal. For example, the proposal unit will propose a detailed template for important interactions. The proposal unit analyzes the importance of past interactions and adjusts the level of detail in templates appropriately. For example, the proposal unit will propose a simple template for general interactions. The proposal unit can also propose a template that allows for a quick response for urgent interactions. In this way, the proposal unit can propose more appropriate templates by adjusting the level of detail in templates based on the importance of past interactions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input data on the importance of past interactions into a generating AI and have the generating AI perform the adjustment of the level of detail in templates.

[0080] The proposal unit can apply different template suggestion algorithms depending on the category of the interaction when making a suggestion. For example, in the case of a business interaction, the proposal unit will suggest a formal template. The proposal unit analyzes the category of the interaction and applies an appropriate template suggestion algorithm. For example, in the case of a private interaction, the proposal unit will suggest a casual template. Also, in the case of a support interaction, the proposal unit can suggest a template that enables quick problem solving. In this way, the proposal unit can suggest a more appropriate template by applying different template suggestion algorithms depending on the category of the interaction. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input the category data of the interaction into a generating AI and have the generating AI execute the application of the template suggestion algorithm.

[0081] The suggestion unit can estimate the user's emotions and adjust the length of the suggested template based on the estimated emotions. For example, if the user is stressed, the suggestion unit will suggest a short and concise template. The suggestion unit analyzes the user's emotions and adjusts the appropriate template length. For example, if the user is relaxed, the suggestion unit will suggest a longer template containing more detailed information. The suggestion unit can also suggest a visually appealing template if the user is excited. In this way, the suggestion unit can suggest a more appropriate template by adjusting the template length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the template length.

[0082] The proposal unit can determine template priorities based on the timing of communication transmissions when making a proposal. For example, the proposal unit will prioritize suggesting templates during times when there are many important communications. The proposal unit analyzes the timing of communication transmissions and determines the appropriate template priorities. For example, the proposal unit will suggest simple templates during times when there are many general communications. The proposal unit can also suggest templates that allow for quick replies during times when there are many urgent communications. In this way, the proposal unit can suggest more appropriate templates by determining template priorities based on the timing of communication transmissions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input communication transmission timing data into a generating AI and have the generating AI perform the determination of template priorities.

[0083] The proposal unit can adjust the order of templates based on the relevance of the interactions when making a proposal. For example, the proposal unit may prioritize suggesting templates related to important interactions. The proposal unit analyzes the relevance of interactions and adjusts the order of templates appropriately. For example, the proposal unit may postpone suggesting templates related to general interactions. Alternatively, the proposal unit may prioritize suggesting templates related to urgent interactions. In this way, the proposal unit can suggest more appropriate templates by adjusting the order of templates based on the relevance of the interactions. Some or all of the above processing in the proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can input interaction relevance data into a generating AI and have the generating AI perform the adjustment of the template order.

[0084] The generation unit can estimate the user's emotions and adjust the way it expresses the response based on the estimated emotions. For example, if the user is stressed, the generation unit will generate a simple and easy-to-understand response. The generation unit analyzes the user's emotions and adjusts the way it expresses the response appropriately. For example, if the user is relaxed, the generation unit will generate a response that includes detailed information. The generation unit can also generate a visually appealing response if the user is excited. In this way, the generation unit can generate more appropriate responses by adjusting the way it expresses the response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the way it expresses the response.

[0085] The generation unit can adjust the level of detail in the response based on the importance of the received message during generation. For example, the generation unit generates a detailed response for important messages. The generation unit analyzes the importance of the received message and adjusts the level of detail in the response appropriately. For example, the generation unit generates a simple response for general messages. The generation unit can also generate a response that can be replied to quickly for urgent messages. In this way, the generation unit can generate a more appropriate response by adjusting the level of detail in the response based on the importance of the received message. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the importance data of the received message into a generation AI and have the generation AI perform the adjustment of the level of detail in the response.

[0086] The generation unit can apply different response generation algorithms depending on the message category during generation. For example, the generation unit generates a formal response for business messages. The generation unit analyzes the message category and applies an appropriate response generation algorithm. For example, the generation unit generates a casual response for private messages. The generation unit can also generate a response that can quickly resolve the problem for support messages. In this way, the generation unit can generate more appropriate responses by applying different response generation algorithms depending on the message category. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message category data into a generation AI and have the generation AI execute the application of the response generation algorithm.

[0087] The generation unit can estimate the user's emotions and adjust the length of the response it generates based on the estimated emotions. For example, if the user is stressed, the generation unit will generate a short and concise response. The generation unit analyzes the user's emotions and adjusts the appropriate response length. For example, if the user is relaxed, the generation unit will generate a longer response containing more detailed information. The generation unit can also generate a visually appealing response if the user is excited. This allows the generation unit to generate more appropriate responses by adjusting the response length based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using AI, or not. For example, the generation unit can input user emotion data into the generation AI and have the generation AI adjust the response length.

[0088] The generation unit can determine the priority of responses based on the message sending time during generation. For example, the generation unit will prioritize generating responses during times when there are many important messages. The generation unit analyzes the message sending time and determines the appropriate priority of responses. For example, the generation unit will generate simple responses during times when there are many general messages. The generation unit can also generate responses that can be replied to quickly during times when there are many urgent messages. In this way, the generation unit can generate more appropriate responses by determining the priority of responses based on the message sending time. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message sending time data into a generation AI and have the generation AI perform the determination of response priorities.

[0089] The generation unit can adjust the order of responses based on the relevance of the messages during generation. For example, the generation unit can prioritize generating responses related to important messages. The generation unit analyzes the relevance of messages and adjusts the order of responses appropriately. For example, the generation unit may postpone responses related to general messages. The generation unit can also prioritize generating responses related to urgent messages. In this way, the generation unit can generate more appropriate responses by adjusting the order of responses based on the relevance of the messages. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input message relevance data into a generation AI and have the generation AI perform the adjustment of the order of responses.

[0090] The reception unit can estimate the user's emotions and adjust the timing of input acceptance based on the estimated emotions. For example, if the user is stressed, the reception unit may delay the timing of input acceptance. The reception unit analyzes the user's emotions and adjusts the appropriate timing of input acceptance. For example, if the user is relaxed, the reception unit may speed up the timing of input acceptance. The reception unit can also adjust the timing of input acceptance if the user is excited. In this way, the reception unit can accept input at a more appropriate time by adjusting the timing of input acceptance based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the timing of input acceptance.

[0091] The reception desk can analyze the user's past input history and select the optimal reception method at the time of reception. For example, the reception desk may prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception desk analyzes the user's past input history and selects an appropriate reception method. For example, the reception desk may suggest relevant input methods by referring to content the user has entered in the past. The reception desk can also predict and suggest input methods to be used during specific time periods based on the user's past input history. In this way, the reception desk can perform more appropriate input reception by analyzing the user's past input history and selecting the optimal reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI perform the selection of the reception method.

[0092] The reception unit can estimate the user's emotions and determine the priority of input reception based on the estimated emotions. For example, if the user is stressed, the reception unit will prioritize important inputs. The reception unit analyzes the user's emotions and determines the appropriate priority of input reception. For example, if the user is relaxed, the reception unit will prioritize general inputs. The reception unit can also prioritize urgent inputs if the user is agitated. This allows the reception unit to perform more appropriate input reception by determining the priority of input reception based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input user emotion data into a generative AI and have the generative AI perform the determination of input reception priority.

[0093] The reception unit can prioritize receiving inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize receiving inputs related to that location. The reception unit analyzes the user's geographical location information and prioritizes receiving appropriate inputs. For example, if the user is on the move, the reception unit will prioritize receiving inputs related to the destination. The reception unit can also prioritize receiving inputs related to the user's home if the user is at home. In this way, the reception unit can perform more appropriate input reception by prioritizing highly relevant inputs while taking into account the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location information data into a generating AI and have the generating AI determine the priority of inputs.

[0094] The service provider can estimate the user's emotions and adjust the method of providing responses based on the estimated emotions. For example, if the user is stressed, the service provider will provide a simple and easy-to-understand response. The service provider can analyze the user's emotions and adjust the method of providing appropriate responses. For example, if the user is relaxed, the service provider will provide a response that includes detailed information. The service provider can also provide a visually appealing response if the user is excited. In this way, the service provider can provide more appropriate responses by adjusting the method of providing responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform the adjustment of the method of providing responses.

[0095] The service provider can analyze the user's past response history and select the optimal service method at the time of service delivery. For example, the service provider may prioritize suggesting response methods (voice, text, etc.) that the user has frequently used in the past. The service provider analyzes the user's past response history and selects an appropriate service method. For example, the service provider may suggest relevant response methods by referring to the content of the user's past responses. The service provider can also predict and suggest response methods to be used during specific time periods based on the user's past response history. In this way, the service provider can provide more appropriate responses by analyzing the user's past response history and selecting the optimal service method. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past response history data into a generating AI and have the generating AI select the service method.

[0096] The service provider can estimate the user's emotions and determine the priority of response delivery based on the estimated emotions. For example, if the user is stressed, the service provider will prioritize important responses. The service provider analyzes the user's emotions and determines the priority of appropriate response delivery. For example, if the user is relaxed, the service provider will prioritize general responses. The service provider can also prioritize urgent responses if the user is agitated. This allows the service provider to provide more appropriate responses by prioritizing response delivery based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI perform the determination of response delivery priorities.

[0097] The service provider can select the optimal service delivery method by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, the service provider will provide a response that is adapted to the screen size. The service provider analyzes the user's device information and selects an appropriate service delivery method. For example, if the user is using a tablet, the service provider will provide a response optimized for a large screen. The service provider can also provide a concise and highly visible response if the user is using a smartwatch. In this way, the service provider can provide a more appropriate response by selecting the optimal service delivery method by considering the user's device information. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user device information data into a generating AI and have the generating AI perform the selection of the service delivery method.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The communication efficiency system can estimate the user's emotions and adjust the suggested reply templates based on those emotions. For example, if the user is stressed, it can suggest a simple and easy-to-understand template. If the user is relaxed, it can suggest a template with more detailed information. Furthermore, if the user is excited, it can suggest a visually appealing template. This allows for more effective communication by suggesting appropriate templates based on the user's emotions.

[0100] The reception desk can analyze the user's past input history when receiving user input and suggest the most suitable input method. For example, it can prioritize suggesting input methods that the user has frequently used in the past (such as voice or text). It can also predict and suggest input methods that the user will use at specific times of the day. Furthermore, it can suggest input methods appropriate to specific situations based on the user's input history. By suggesting the most suitable input method considering the user's past input history, this enables smoother input.

[0101] The system can estimate the user's emotions when providing a generated response and adjust the response delivery method based on the estimated emotions. For example, if the user is stressed, a simple and easy-to-understand response can be provided. If the user is relaxed, a response containing more detailed information can be provided. Furthermore, if the user is excited, a visually appealing response can be provided. This enables more effective communication by providing appropriate responses based on the user's emotions.

[0102] The learning unit can analyze past message content, reply timing, and writing style, taking into account the relationship between the message sender and recipient. For example, if the message sender and recipient are a boss and a subordinate, the unit can learn appropriate reply patterns based on that relationship. If the message sender and recipient are colleagues, the unit can learn friendly communication. Furthermore, if the message sender and recipient are a customer and a representative, the unit can learn businesslike communication. In this way, by learning while considering the relationship between the message sender and recipient, the unit can learn more appropriate reply patterns.

[0103] The proposal team can apply different template suggestion algorithms depending on the category of the interaction when proposing reply templates based on past exchanges. For example, it can suggest a formal template for business interactions, a casual template for private interactions, and a template that enables quick problem resolution for support interactions. This allows for more effective communication by suggesting the appropriate template according to the category of the interaction.

[0104] The generation unit analyzes the content of received messages and, in generating natural responses, can estimate the user's emotions and adjust the expression of the response based on the estimated emotions. For example, if the user is stressed, it can generate a simple and easy-to-understand response. If the user is relaxed, it can generate a response that includes detailed information. Furthermore, if the user is excited, it can generate a visually appealing response. This enables more effective communication by generating appropriate responses based on the user's emotions.

[0105] The learning unit can learn region-specific communication styles by considering the user's geographical location during the learning process. For example, if the user is in Japan, it can learn Japanese-specific honorifics and etiquette. If the user is in the United States, it can learn casual communication styles. Furthermore, if the user is in France, it can learn French-specific expressions and greetings. By learning region-specific communication styles while considering the user's geographical location, more appropriate communication can be achieved.

[0106] The suggestion function can estimate the user's emotions and adjust the length of the suggested template based on those emotions. For example, if the user is stressed, a short and concise template can be suggested. If the user is relaxed, a longer template with more detailed information can be suggested. Furthermore, if the user is excited, a visually appealing template can be suggested. This allows for more effective communication by suggesting the appropriate template based on the user's emotions.

[0107] The reception system can estimate the user's emotions and adjust the timing of input acceptance based on those estimates. For example, if the user is stressed, the timing of input acceptance can be delayed. Conversely, if the user is relaxed, the timing of input acceptance can be sped up. Furthermore, if the user is excited, the timing of input acceptance can be adjusted. This allows for smoother operation by accepting input at the appropriate time based on the user's emotions.

[0108] The service provider can select the optimal service delivery method by considering the user's device information at the time of delivery. For example, if the user is using a smartphone, it can provide a response that matches the screen size. If the user is using a tablet, it can provide a response optimized for a larger screen. Furthermore, if the user is using a smartwatch, it can provide a concise and highly visible response. By selecting the optimal service delivery method considering the user's device information, a more appropriate response can be provided.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The learning unit learns from past interactions. Specifically, it analyzes the content of past messages, the timing of replies, and the writing style to learn from interactions related to specific projects and interactions with specific members. This collects data to suggest appropriate reply templates. Step 2: The suggestion unit proposes a reply template at the appropriate time based on what the learning unit has learned. For example, when a user receives a new message, it proposes an appropriate reply template based on past interactions, providing a template that allows the user to reply quickly. Step 3: The generation unit generates a natural response based on the template proposed by the proposal unit. Specifically, it analyzes the content of the received message and generates an appropriate response that fits the context. This provides the user with a response that allows them to continue the conversation naturally, enabling fast and accurate communication.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements described above, including the learning unit, proposal unit, generation unit, reception unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes and learns the content of past messages, the timing of replies, and the writing style. The proposal unit is implemented by the control unit 46A of the smart device 14, which proposes an appropriate reply template based on past interactions when the user receives a new message. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the content of the received message and generates an appropriate response. The reception unit is implemented by the reception device 38 of the smart device 14, which accepts user input in the form of text input, voice input, gesture input, etc. The provision unit is implemented by the output device 40 of the smart device 14, which displays the generated text message in the user's chat window. The correspondence between each unit and the devices and control units is not limited to the example described above, and various changes are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the learning unit, suggestion unit, generation unit, reception unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes and learns the content of past messages, the timing of replies, and the writing style. The suggestion unit is implemented by the control unit 46A of the smart glasses 214, which proposes an appropriate reply template based on past interactions when the user receives a new message. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the content of the received message and generates an appropriate response. The reception unit is implemented by the microphone 238 of the smart glasses 214, which accepts user input in the form of voice input or the like. The provision unit is implemented by the speaker 240 of the smart glasses 214, which provides the generated voice message to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the learning unit, suggestion unit, generation unit, reception unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes and learns the content of past messages, the timing of replies, and the writing style. The suggestion unit is implemented by the control unit 46A of the headset terminal 314, which proposes an appropriate reply template based on past interactions when the user receives a new message. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the content of the received message and generates an appropriate response. The reception unit is implemented by the microphone 238 of the headset terminal 314, which accepts user input in the form of voice input or the like. The provision unit is implemented by the speaker 240 of the headset terminal 314, which provides the generated voice message to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the learning unit, proposal unit, generation unit, reception unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes and learns the content of past messages, the timing of replies, and the writing style. The proposal unit is implemented by the control unit 46A of the robot 414, which proposes an appropriate reply template based on past interactions when the user receives a new message. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the content of the received message and generates an appropriate response. The reception unit is implemented by the microphone 238 of the robot 414, which accepts user input in the form of voice input or the like. The provision unit is implemented by the speaker 240 of the robot 414, which provides the generated voice message to the user. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) The learning section reviews past interactions, Based on the content learned by the aforementioned learning unit, the proposal unit proposes a reply template at an appropriate time, The system comprises a generation unit that generates a natural response based on a template proposed by the proposal unit. A system characterized by the following features. (Note 2) It is equipped with a reception unit that accepts user input. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a providing unit that provides the generated response. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned learning unit, It analyzes and learns from past message content, reply timing, writing style, etc. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Suggest an appropriate reply template based on past interactions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is It analyzes the content of received messages and generates natural-sounding responses. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, During learning, the system considers not only the content of past messages but also the relationship between the message sender and recipient. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, During training, the system analyzes the timing and frequency of message transmissions to learn the optimal timing for replies. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, During training, the system learns region-specific communication styles by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, During training, the system analyzes users' social media activity and learns relevant communication patterns. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned proposal section is, It estimates the user's emotions and adjusts how the suggested templates are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, When making a proposal, adjust the level of detail in the template based on the importance of past interactions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, When making a proposal, different template proposal algorithms are applied depending on the category of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggested templates based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, When making a proposal, prioritize templates based on when the correspondence was sent. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, When making a proposal, adjust the order of templates based on the relevance of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts how the response is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, adjust the level of detail in the response based on the importance of the received message. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, different response generation algorithms are applied depending on the message category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts the length of the response generated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is During generation, the response priority is determined based on when the message was sent. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the order of responses is adjusted based on the relevance of the messages. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned reception unit is At the time of registration, the system analyzes the user's past input history and selects the most suitable registration method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned reception unit is The system estimates the user's emotions and determines the priority of input requests based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned reception unit is During registration, the system prioritizes accepting input that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, It estimates the user's emotions and adjusts the response delivery method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing the service, the system analyzes the user's past response history to select the optimal delivery method. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, The system estimates the user's emotions and determines the priority of response delivery based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, When providing the service, the optimal delivery method will be selected, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The learning section reviews past interactions, Based on the content learned by the aforementioned learning unit, the proposal unit proposes a reply template at an appropriate time, The system comprises a generation unit that generates a natural response based on a template proposed by the proposal unit. A system characterized by the following features.

2. It is equipped with a reception unit that accepts user input. The system according to feature 1.

3. It includes a providing unit that provides the generated response. The system according to feature 1.

4. The aforementioned learning unit, It analyzes and learns from past message content, reply timing, writing style, etc. The system according to feature 1.

5. The aforementioned proposal section is, Suggest an appropriate reply template based on past interactions. The system according to feature 1.

6. The generating unit is It analyzes the content of received messages and generates natural-sounding responses. The system according to feature 1.

7. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

8. The aforementioned learning unit, During learning, the system considers not only the content of past messages but also the relationship between the message sender and recipient. The system according to feature 1.

Images