System

Abstract

To enable an avatar to make an automatic response in accordance with a decision making philosophy and policy of a user in an online meeting.SOLUTION: A system according to an embodiment comprises a learning unit, response unit, and update unit. The learning unit learns a decision-making philosophy and policy of a user. The response unit causes an avatar to respond to conversion in an online meeting according to the information learned by the learning unit. The update unit keeps on learning and updating based on responses made by the response unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have the problem that it is difficult to automatically respond based on a user's decisions and policies in online meetings that the user cannot attend.

[0005] The system according to the embodiment aims to allow an avatar to automatically respond in an online meeting based on a user's decision-making philosophy and policies. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a response unit, and an update unit. The learning unit learns a user's decision-making mindset and policy. The response unit causes an avatar to respond to a conversation in an online meeting based on the information learned by the learning unit. The update unit continuously learns and updates based on the response made by the response unit. Effect of the Invention

[0007] The system according to the embodiment enables an avatar to automatically respond in an online meeting based on a user's decision-making philosophy and policies. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

[0017] 1, a 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. The database 24 and the communication I / F 26 are also 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. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a system in which an AI learns the user's decision-making philosophy and policies, and an avatar automatically responds to conversations and handles them in online meetings that the user cannot attend. In this system, an AI learns the user's decision-making philosophy and policies, and an avatar responds to conversations on behalf of the user in online meetings that the user cannot attend. At this time, the avatar responds appropriately based on the user's decision-making philosophy and policies using AI. This makes it possible to respond appropriately in online meetings even when the user is absent. For example, by collecting records of past meetings held by the user and email exchanges, and having the AI ​​analyze them, the user's decision-making patterns and policies can be learned. Next, in online meetings that the user cannot attend, the avatar responds to conversations on behalf of the user. For example, in a meeting that the user cannot attend, an avatar is displayed on the screen and talks with other participants. At this time, the avatar responds appropriately based on the user's decision-making philosophy and policies using AI. For example, questions from other participants can be answered based on the user's past remarks and decision-making patterns. This mechanism makes it possible to respond appropriately in online meetings even when the user is absent. For example, even if a user is unable to attend a meeting due to an urgent matter, the avatar can respond to the conversation on the user's behalf and support the progress of the meeting. In addition, since responses are based on the user's decision-making philosophy and policies, it is possible to respond consistently to other participants. Furthermore, the avatar can continuously learn and update the user's decision-making philosophy and policies. For example, the accuracy of the avatar's responses can be improved by having the AI ​​learn the user's new decisions and statements. This makes it possible to always respond based on the latest user's philosophy and policies. This allows the system to respond appropriately in online meetings even when the user is absent.

[0029] The system according to the embodiment includes a learning unit, a response unit, and an update unit. The learning unit learns the user's decision-making mindset and policy. The learning unit collects data such as records of meetings held in the past by the user and email exchanges, and analyzes the data using AI. For example, the learning unit can collect minutes of meetings and analyze them using AI. The learning unit can also collect the contents of emails and analyze them using AI. Furthermore, the learning unit can collect reports of projects held in the past by the user and analyze them using AI. The response unit causes an avatar to respond to a conversation in an online meeting based on information learned by the learning unit. The response unit responds to questions from other participants, for example, based on the content of past user remarks and decision-making patterns. For example, the response unit can respond to questions from other participants based on the content of user remarks in past meetings. Furthermore, the response unit can respond to questions from other participants based on the user's decision-making patterns. Furthermore, the response unit can display an avatar on a screen and have a conversation with other participants. For example, the response unit can display an avatar on a screen and have a conversation with other participants. The update unit continuously learns and updates based on the response made by the response unit. The update unit, for example, makes the AI ​​learn the decision-making and statement contents newly made by the user, thereby improving the response accuracy. For example, the update unit can collect records of meetings newly held by the user and make the AI ​​learn them. The update unit can also collect the contents of emails newly sent and received by the user and make the AI ​​learn them. Furthermore, the update unit can collect reports of projects newly started by the user and make the AI ​​learn them. As a result, the system according to the embodiment can learn the user's decision-making thinking and policies, and the avatar can respond to conversations in online meetings, thereby continuously learning and updating.

[0030] The learning unit learns the user's decision-making thinking and policies. Specifically, the learning unit collects data such as records of past meetings and email exchanges held by the user, and analyzes it using AI. For example, the learning unit collects minutes of meetings and analyzes the contents of the minutes using natural language processing technology. This allows for a detailed understanding of what the user said and what decisions were made. The learning unit can also collect the contents of emails and analyze them using AI. For email content analysis, text mining technology is used to extract the user's intentions and emotions. Furthermore, the learning unit can collect reports of projects that the user has previously carried out and analyze them using AI. For analyzing project reports, document classification technology and topic modeling technology are used to grasp the user's decision-making patterns and the progress of the projects. This allows the learning unit to comprehensively learn the user's decision-making thinking and policies, and use them to support future decision-making. Furthermore, the learning unit can centrally manage the collected data and link with other systems and departments as necessary. For example, the learning unit can store data on a cloud server and make the analysis results accessible to other departments. In addition, by adjusting the frequency of data collection and the accuracy of analysis, it is possible to respond flexibly to specific situations and conditions. This allows the learning unit to collect data efficiently and effectively, and improve the performance of the user's overall decision support system.

[0031] The response unit causes the avatar to respond to conversations in online meetings based on the information learned by the learning unit. Specifically, the response unit responds to questions from other participants based on the user's past remarks and decision-making patterns. For example, the response unit can respond to questions from other participants based on the user's remarks in past meetings. For this, natural language generation technology is used to reproduce the user's remark style and language. The response unit can also respond to questions from other participants based on the user's decision-making patterns. For this, a decision support system is used to refer to what decisions the user has made in the past. Furthermore, the response unit can display the avatar on a screen and have a conversation with other participants. The avatar reproduces the user's appearance and facial expressions and operates in real time. This allows other participants to have an experience as if they were talking to the user himself. The response unit uses voice recognition technology to analyze the remarks of other participants in real time and generate an appropriate response. This allows the response unit to quickly and accurately respond to questions from other participants and support the smooth progress of online meetings. Furthermore, the response unit can collect user feedback and continuously improve the accuracy and effectiveness of the response content. For example, after the end of a meeting, feedback from users is collected and the response content is reviewed and improved. The response unit can also reliably transmit information using multiple communication means. This allows the response unit to provide a quick and reliable response to the user and maximize the effectiveness of the online meeting.

[0032] The update unit continuously learns and updates based on the responses made by the response unit. Specifically, the AI ​​learns the new decisions and statements made by the user, improving the response accuracy. For example, the update unit can collect records of new meetings held by the user and have the AI ​​learn from them. This involves analyzing the audio data and minutes of the meetings to extract new statements and decision-making patterns. The update unit can also collect the contents of emails newly sent and received by the user and have the AI ​​learn from them. For email content analysis, text mining technology is used to extract new intentions and emotions. Furthermore, the update unit can collect reports of new projects carried out by the user and have the AI ​​learn from them. For project report analysis, document classification technology and topic modeling technology are used to grasp new decision-making patterns and project progress. This allows the update unit to continuously learn the latest decisions and statements made by the user and improve response accuracy. Furthermore, the update unit can centrally manage the collected data and link with other systems and departments as necessary. For example, the update unit can store data on a cloud server and make the analysis results accessible to other departments. In addition, by adjusting the frequency of data collection and the accuracy of analysis, it is possible to flexibly respond to specific situations and conditions. This allows the update unit to collect data efficiently and effectively, and improve the performance of the entire decision support system for the user.

[0033] The learning unit can collect data on records of meetings or email exchanges conducted by the user in the past and analyze it using AI. The data on records of meetings or email exchanges includes, for example, minutes of meetings and the contents of emails, but is not limited to such examples. The learning unit, for example, collects minutes of meetings and analyzes them using AI. For example, the learning unit can collect minutes of meetings and analyze them using natural language processing technology. The learning unit can also collect the contents of emails and analyze them using AI. For example, the learning unit can collect the contents of emails and analyze them using machine learning algorithms. Furthermore, the learning unit can collect reports of projects conducted by the user in the past and analyze them using AI. For example, the learning unit can collect project reports and analyze them using natural language processing technology. This allows the learning unit to learn the user's decision-making patterns and policies.

[0034] The response unit can respond to questions from other participants based on the content of past user remarks and decision-making patterns. The content of past user remarks and decision-making patterns include, for example, specific keywords, decision-making rules, and the like, but are not limited to such examples. The response unit responds to questions from other participants based on the content of user remarks in past conferences, for example. For example, the response unit can respond to questions from other participants based on the content of user remarks in past conferences. The response unit can also respond to questions from other participants based on the user's decision-making patterns. For example, the response unit can respond to questions from other participants based on the user's decision-making rules. This enables the response unit to respond to other participants in a consistent manner.

[0035] The update unit can improve the response accuracy by making the AI ​​learn the decision-making and statement contents newly made by the user. The newly made decision-making and statement contents include, but are not limited to, for example, the decision of a new project and statements made in a meeting. The update unit, for example, collects records of meetings newly made by the user and makes the AI ​​learn. For example, the update unit can collect records of meetings, analyze them using natural language processing technology, and make the AI ​​learn. The update unit can also collect the contents of emails newly sent and received by the user and make the AI ​​learn. For example, the update unit can collect the contents of emails, analyze them using a machine learning algorithm, and make the AI ​​learn. Furthermore, the update unit can collect reports of projects newly made by the user and make the AI ​​learn. For example, the update unit can collect project reports, analyze them using natural language processing technology, and make the AI ​​learn. This enables the update unit to always respond based on the latest user's thinking and policies.

[0036] The response unit displays an avatar on the screen and can have a conversation with other participants. The method of displaying the avatar on the screen includes, but is not limited to, a 2D avatar, a 3D avatar, and the like. The response unit displays an avatar on the screen and can have a conversation with other participants. For example, the response unit can display a 2D avatar on the screen and can have a conversation with other participants. The response unit can also display a 3D avatar on the screen and can have a conversation with other participants. Furthermore, the response unit can also have the avatar have a conversation with other participants in real time. For example, the response unit can have the avatar have a conversation with other participants in real time. This allows the response unit to support the progress of the conference even when the user is absent.

[0037] The update unit can continuously collect new data and improve the accuracy of the learning unit and the response unit. The new data includes, for example, the latest meeting records, the contents of new emails, etc., but is not limited to such examples. The update unit can, for example, collect the latest meeting records and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect the latest meeting records and analyze them using natural language processing technology to improve the accuracy of the learning unit and the response unit. The update unit can also collect the contents of new emails and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect the contents of new emails and analyze them using a machine learning algorithm to improve the accuracy of the learning unit and the response unit. Furthermore, the update unit can also collect new project reports and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect new project reports and analyze them using natural language processing technology to improve the accuracy of the learning unit and the response unit. This allows the update unit to improve the accuracy of the system.

[0038] The learning unit can collect background information of the user's past decision-making and reflect it in the learning. The background information of the past decision-making includes, for example, details of past projects, reasons for decision-making, etc., but is not limited to such examples. The learning unit, for example, collects minutes of meetings held by the user in the past and learns the background of the decision-making. For example, the learning unit can collect minutes of meetings, analyze them using natural language processing technology, and learn the background of the decision-making. The learning unit can also analyze the contents of emails sent and received by the user in the past and learn the background of the decision-making. For example, the learning unit can collect the contents of the emails, analyze them using a machine learning algorithm, and learn the background of the decision-making. Furthermore, the learning unit can collect reports of projects held by the user in the past and learn the background of the decision-making. For example, the learning unit can collect project reports, analyze them using natural language processing technology, and learn the background of the decision-making. As a result, the learning unit can reflect the background information of the decision-making in the learning, thereby enabling more accurate learning.

[0039] During learning, the learning unit can analyze the priority of the user's decision-making and perform learning according to the importance. The priority of decision-making includes, for example, an evaluation criterion for the importance, a method for determining the priority, and the like, but is not limited to such examples. For example, the learning unit preferentially learns the decision-making made by the user in an important meeting. For example, the learning unit can preferentially learn the decision-making made by the user in an important meeting. In addition, the learning unit can also preferentially learn the decision-making made by the user in an emergency. For example, the learning unit can preferentially learn the decision-making made by the user in an emergency. Furthermore, the learning unit can also preferentially learn the decision-making made by the user in a long-term project. For example, the learning unit can preferentially learn the decision-making made by the user in a long-term project. This enables the learning unit to learn according to the importance.

[0040] The learning unit can perform learning based on the geographical background and cultural background of the user during learning. The geographical background and cultural background include, for example, local customs, cultural values, and the like, but are not limited to such examples. For example, the learning unit can learn decisions made by the user in different cultural spheres and take the cultural background into consideration. For example, the learning unit can learn decisions made by the user in different cultural spheres and take the cultural background into consideration. In addition, the learning unit can also learn decisions made by the user in different regions and take the geographical background into consideration. For example, the learning unit can learn decisions made by the user in different regions and take the geographical background into consideration. Furthermore, the learning unit can also learn decisions made by the user in an international project and take the geographical and cultural background into consideration. For example, the learning unit can learn decisions made by the user in an international project and take the geographical and cultural background into consideration. This enables the learning unit to perform learning taking the geographical and cultural background into consideration.

[0041] During learning, the learning unit can analyze the user's social media activity and learn the tendency of decision-making. Social media activity includes, for example, the content of posts, the reactions of followers, and the like, but is not limited to such examples. The learning unit, for example, analyzes statements made by the user on social media and learns the tendency of decision-making. For example, the learning unit can analyze statements made by the user on social media and learn the tendency of decision-making. In addition, the learning unit can analyze articles and posts shared by the user on social media and learn the tendency of decision-making. For example, the learning unit can analyze articles and posts shared by the user on social media and learn the tendency of decision-making. In addition, the learning unit can analyze discussions in which the user participated on social media and learn the tendency of decision-making. For example, the learning unit can analyze discussions in which the user participated on social media and learn the tendency of decision-making. This enables the learning unit to learn in consideration of social media activity.

[0042] The response unit can analyze the remarks of other participants in real time at the time of response and generate an optimal response. The optimal response includes, for example, a real-time analysis method, a response generation algorithm, and the like, but is not limited to such examples. The response unit can analyze, for example, the remarks of other participants in real time and generate an appropriate response. For example, the response unit can analyze the remarks of other participants in real time and generate an appropriate response. In addition, the response unit can respond to questions of other participants based on past remarks of users. For example, the response unit can respond to questions of other participants based on past remarks of users. Furthermore, the response unit can respond to opinions of other participants based on the decision-making patterns of users. For example, the response unit can respond to opinions of other participants based on the decision-making patterns of users. This makes it possible for the response unit to generate optimal responses in real time.

[0043] The response unit can adjust the timing of the response based on the progress of the conference when responding. The timing of the response includes, for example, an evaluation criterion for the progress of the conference, a delay time of the response, and the like, but is not limited to such examples. The response unit, for example, analyzes the progress of the conference in real time and responds at an appropriate timing. For example, the response unit can analyze the progress of the conference in real time and respond at an appropriate timing. In addition, the response unit can adjust the timing of the response according to the agenda of the conference. For example, the response unit can adjust the timing of the response according to the agenda of the conference. Furthermore, the response unit can respond at the timing when the other participants finish speaking. For example, the response unit can respond at the timing when the other participants finish speaking. This enables the response unit to respond at an appropriate timing according to the progress of the conference.

[0044] The response unit can respond by taking into consideration the geographical background and cultural background of the other participants. The geographical background and cultural background include, but are not limited to, local customs and cultural values. For example, the response unit responds in an appropriate manner of expression by taking into consideration the cultural background of the other participants. For example, the response unit can respond in an appropriate manner of expression by taking into consideration the cultural background of the other participants. In addition, the response unit can provide appropriate information by taking into consideration the geographical background of the other participants. For example, the response unit can provide appropriate information by taking into consideration the geographical background of the other participants. Furthermore, the response unit can respond at an appropriate time by taking into consideration the cultural customs of the other participants. For example, the response unit can respond at an appropriate time by taking into consideration the cultural customs of the other participants. This enables the response unit to respond in consideration of the geographical and cultural backgrounds.

[0045] The response unit can analyze the social media activities of the other participants at the time of response and reflect the relevant information in the response. The social media activities include, for example, the content of posts and the reactions of followers, but are not limited to such examples. The response unit can analyze, for example, the statements of the other participants on social media and reflect the relevant information in the response. For example, the response unit can analyze the statements of the other participants on social media and reflect the relevant information in the response. In addition, the response unit can also make an appropriate response based on articles and posts shared by the other participants. For example, the response unit can make an appropriate response based on articles and posts shared by the other participants. In addition, the response unit can analyze the activities of the other participants on social media and make an appropriate response. For example, the response unit can analyze the activities of the other participants on social media and make an appropriate response. This enables the response unit to respond in consideration of the social media activities.

[0046] The update unit can analyze past response data at the time of updating and optimize the response algorithm. The response algorithm includes, for example, performance evaluation, an algorithm improvement method, and the like, but is not limited to such examples. The update unit can analyze, for example, past response data and optimize the response algorithm. For example, the update unit can analyze past response data and optimize the response algorithm. In addition, the update unit can extract an effective response pattern from the past response data and reflect it in the algorithm. For example, the update unit can extract an effective response pattern from the past response data and reflect it in the algorithm. Furthermore, the update unit can improve the accuracy of the response based on the past response data. For example, the update unit can improve the accuracy of the response based on the past response data. This makes it possible for the update unit to optimize the response algorithm based on the past response data.

[0047] The update unit can collect background information of the user's new decision-making at the time of updating and reflect it in the learning. The background information of the new decision-making includes, for example, details of the new project, reasons for the decision-making, etc., but is not limited to such examples. The update unit can collect, for example, records of a meeting newly held by the user and reflect it in the learning. For example, the update unit can collect records of the meeting, analyze them using natural language processing technology, and reflect them in the learning. The update unit can also analyze the contents of emails newly sent and received by the user and reflect them in the learning. For example, the update unit can collect the contents of the emails, analyze them using a machine learning algorithm, and reflect them in the learning. Furthermore, the update unit can collect reports of projects newly held by the user and reflect them in the learning. For example, the update unit can collect project reports, analyze them using natural language processing technology, and reflect them in the learning. As a result, the update unit can reflect the background information of the new decision-making in the learning, thereby enabling more accurate learning.

[0048] The update unit can perform the update based on the geographical background and cultural background of the user at the time of the update. The geographical background and the cultural background include, for example, local customs, cultural values, and the like, but are not limited to such examples. For example, the update unit can update the decision made by the user in a different cultural sphere and take into account the cultural background. For example, the update unit can update the decision made by the user in a different cultural sphere and take into account the cultural background. The update unit can also update the decision made by the user in a different region and take into account the geographical background. For example, the update unit can update the decision made by the user in a different region and take into account the geographical background. Furthermore, the update unit can update the decision made by the user in an international project and take into account the geographical and cultural background. For example, the update unit can update the decision made by the user in an international project and take into account the geographical and cultural background. This enables the update unit to perform the update taking into account the geographical and cultural background.

[0049] The update unit can analyze the user's social media activity at the time of updating and learn the decision-making tendency. The social media activity includes, for example, the content of the post, the reaction of the followers, and the like, but is not limited to such examples. The update unit can, for example, analyze the remarks made by the user on social media and learn the decision-making tendency. For example, the update unit can analyze the remarks made by the user on social media and learn the decision-making tendency. The update unit can also analyze the articles and posts shared by the user on social media and learn the decision-making tendency. For example, the update unit can analyze the articles and posts shared by the user on social media and learn the decision-making tendency. Furthermore, the update unit can analyze the discussions in which the user participated on social media and learn the decision-making tendency. For example, the update unit can analyze the discussions in which the user participated on social media and learn the decision-making tendency. This enables the update unit to learn in consideration of the social media activity.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The system may further include a feedback unit. The feedback unit collects feedback from other participants after the online meeting ends and provides it to the learning unit. For example, the feedback unit may collect how other participants felt about the avatar's response in the form of a questionnaire. The feedback unit may also collect comments and evaluations made by other participants on the avatar's response. Furthermore, the feedback unit may collect specific improvements made by other participants to the avatar's response. This allows the learning unit to improve the avatar's response based on the feedback from other participants, enabling more appropriate responses.

[0052] The learning unit can analyze the user's past behavior history when learning the user's decision-making thinking and policies. For example, the learning unit can collect and analyze what websites the user has viewed in the past and what applications the user has used. The learning unit can also collect and analyze what purchasing behavior the user has performed in the past. Furthermore, the learning unit can collect and analyze what social media posts the user has made in the past. This allows the learning unit to more accurately learn the decision-making thinking and policies based on the user's behavior history.

[0053] The response unit can translate the content of speech of other participants in real time when the avatar is having a conversation, and support communication with participants who speak different languages. For example, the response unit can translate content spoken in English into Japanese and provide it to the Japanese-speaking participant. The response unit can also translate content spoken in Japanese into English and provide it to the English-speaking participant. Furthermore, the response unit can also translate between other languages. This allows the response unit to support smooth communication with participants who speak different languages.

[0054] The update unit can take into account the success rate of the user's past decisions when learning the user's new decisions and utterances. For example, the update unit can preferentially learn successful decisions made by the user in the past. The update unit can also learn unsuccessful decisions made by the user in the past and use them as data to avoid similar failures. Furthermore, the update unit can preferentially learn particularly important decisions made by the user in the past. This enables the update unit to perform appropriate learning taking into account the success rate of the user's past decisions.

[0055] The learning unit can collect background information of the user's past decision-making and reflect it in the learning. For example, the learning unit can collect minutes of meetings held in the past by the user and learn the background of the decision-making. The learning unit can also analyze the contents of emails sent and received in the past by the user and learn the background of the decision-making. Furthermore, the learning unit can collect reports of projects held in the past by the user and learn the background of the decision-making. In this way, the learning unit can reflect the background information of the decision-making in the learning, thereby enabling more accurate learning.

[0056] During learning, the learning unit can analyze the priority of the user's decision-making and perform learning according to the importance. For example, the learning unit can prioritize learning of decisions made by the user in important meetings. The learning unit can also prioritize learning of decisions made by the user in emergencies. Furthermore, the learning unit can also prioritize learning of decisions made by the user in long-term projects. This enables the learning unit to perform learning according to the importance.

[0057] The process flow of the first embodiment will be briefly described below.

[0058] Step 1: The learning unit learns the user's decision-making thinking and policies. The learning unit collects data such as records of past meetings, email correspondence, and project reports from the user, and analyzes it using AI. Step 2: The response unit responds to conversations in online meetings using the avatar based on the information learned by the learning unit. The response unit responds to questions from other participants based on the user's past comments and decision-making patterns. The avatar is displayed on the screen and engages in conversations with other participants. Step 3: The update unit continuously learns and updates based on the responses made by the response unit. The update unit trains the AI ​​on new decisions and statements made by the user, improving the accuracy of responses. For example, the update unit collects records of new meetings held by the user, the contents of emails sent and received, and project reports, and trains the AI ​​to learn from them.

[0059] (Example 2) The system according to the embodiment of the present invention is a system in which an AI learns the user's decision-making philosophy and policies, and an avatar automatically responds to conversations and handles them in online meetings that the user cannot attend. In this system, an AI learns the user's decision-making philosophy and policies, and an avatar responds to conversations on behalf of the user in online meetings that the user cannot attend. At this time, the avatar responds appropriately based on the user's decision-making philosophy and policies using AI. This makes it possible to respond appropriately in online meetings even when the user is absent. For example, by collecting records of past meetings held by the user and email exchanges, and having the AI ​​analyze them, the user's decision-making patterns and policies can be learned. Next, in online meetings that the user cannot attend, the avatar responds to conversations on behalf of the user. For example, in a meeting that the user cannot attend, an avatar is displayed on the screen and talks with other participants. At this time, the avatar responds appropriately based on the user's decision-making philosophy and policies using AI. For example, questions from other participants can be answered based on the user's past remarks and decision-making patterns. This mechanism makes it possible to respond appropriately in online meetings even when the user is absent. For example, even if a user is unable to attend a meeting due to an urgent matter, the avatar can respond to the conversation on the user's behalf and support the progress of the meeting. In addition, since responses are based on the user's decision-making philosophy and policies, it is possible to respond consistently to other participants. Furthermore, the avatar can continuously learn and update the user's decision-making philosophy and policies. For example, the accuracy of the avatar's responses can be improved by having the AI ​​learn the user's new decisions and statements. This makes it possible to always respond based on the latest user's philosophy and policies. This allows the system to respond appropriately in online meetings even when the user is absent.

[0060] The system according to the embodiment includes a learning unit, a response unit, and an update unit. The learning unit learns the user's decision-making mindset and policy. The learning unit collects data such as records of meetings held in the past by the user and email exchanges, and analyzes the data using AI. For example, the learning unit can collect minutes of meetings and analyze them using AI. The learning unit can also collect the contents of emails and analyze them using AI. Furthermore, the learning unit can collect reports of projects held in the past by the user and analyze them using AI. The response unit causes an avatar to respond to a conversation in an online meeting based on information learned by the learning unit. The response unit responds to questions from other participants, for example, based on the content of past user remarks and decision-making patterns. For example, the response unit can respond to questions from other participants based on the content of user remarks in past meetings. Furthermore, the response unit can respond to questions from other participants based on the user's decision-making patterns. Furthermore, the response unit can display an avatar on a screen and have a conversation with other participants. For example, the response unit can display an avatar on a screen and have a conversation with other participants. The update unit continuously learns and updates based on the response made by the response unit. The update unit, for example, makes the AI ​​learn the decision-making and statement contents newly made by the user, thereby improving the response accuracy. For example, the update unit can collect records of meetings newly held by the user and make the AI ​​learn them. The update unit can also collect the contents of emails newly sent and received by the user and make the AI ​​learn them. Furthermore, the update unit can collect reports of projects newly started by the user and make the AI ​​learn them. As a result, the system according to the embodiment can learn the user's decision-making thinking and policies, and the avatar can respond to conversations in online meetings, thereby continuously learning and updating.

[0061] The learning unit learns the user's decision-making thinking and policies. Specifically, the learning unit collects data such as records of past meetings and email exchanges held by the user, and analyzes it using AI. For example, the learning unit collects minutes of meetings and analyzes the contents of the minutes using natural language processing technology. This allows for a detailed understanding of what the user said and what decisions were made. The learning unit can also collect the contents of emails and analyze them using AI. For email content analysis, text mining technology is used to extract the user's intentions and emotions. Furthermore, the learning unit can collect reports of projects that the user has previously carried out and analyze them using AI. For analyzing project reports, document classification technology and topic modeling technology are used to grasp the user's decision-making patterns and the progress of the projects. This allows the learning unit to comprehensively learn the user's decision-making thinking and policies, and use them to support future decision-making. Furthermore, the learning unit can centrally manage the collected data and link with other systems and departments as necessary. For example, the learning unit can store data on a cloud server and make the analysis results accessible to other departments. In addition, by adjusting the frequency of data collection and the accuracy of analysis, it is possible to respond flexibly to specific situations and conditions. This allows the learning unit to collect data efficiently and effectively, and improve the performance of the user's overall decision support system.

[0062] The response unit causes the avatar to respond to conversations in online meetings based on the information learned by the learning unit. Specifically, the response unit responds to questions from other participants based on the user's past remarks and decision-making patterns. For example, the response unit can respond to questions from other participants based on the user's remarks in past meetings. For this, natural language generation technology is used to reproduce the user's remark style and language. The response unit can also respond to questions from other participants based on the user's decision-making patterns. For this, a decision support system is used to refer to what decisions the user has made in the past. Furthermore, the response unit can display the avatar on a screen and have a conversation with other participants. The avatar reproduces the user's appearance and facial expressions and operates in real time. This allows other participants to have an experience as if they were talking to the user himself. The response unit uses voice recognition technology to analyze the remarks of other participants in real time and generate an appropriate response. This allows the response unit to quickly and accurately respond to questions from other participants and support the smooth progress of online meetings. Furthermore, the response unit can collect user feedback and continuously improve the accuracy and effectiveness of the response content. For example, after the end of a meeting, feedback from users is collected and the response content is reviewed and improved. The response unit can also reliably transmit information using multiple communication means. This allows the response unit to provide a quick and reliable response to the user and maximize the effectiveness of the online meeting.

[0063] The update unit continuously learns and updates based on the responses made by the response unit. Specifically, the AI ​​learns the new decisions and statements made by the user, improving the response accuracy. For example, the update unit can collect records of new meetings held by the user and have the AI ​​learn from them. This involves analyzing the audio data and minutes of the meetings to extract new statements and decision-making patterns. The update unit can also collect the contents of emails newly sent and received by the user and have the AI ​​learn from them. For email content analysis, text mining technology is used to extract new intentions and emotions. Furthermore, the update unit can collect reports of new projects carried out by the user and have the AI ​​learn from them. For project report analysis, document classification technology and topic modeling technology are used to grasp new decision-making patterns and project progress. This allows the update unit to continuously learn the latest decisions and statements made by the user and improve response accuracy. Furthermore, the update unit can centrally manage the collected data and link with other systems and departments as necessary. For example, the update unit can store data on a cloud server and make the analysis results accessible to other departments. In addition, by adjusting the frequency of data collection and the accuracy of analysis, it is possible to flexibly respond to specific situations and conditions. This allows the update unit to collect data efficiently and effectively, and improve the performance of the entire decision support system for the user.

[0064] The learning unit can collect data on records of meetings or email exchanges conducted by the user in the past and analyze it using AI. The data on records of meetings or email exchanges includes, for example, minutes of meetings and the contents of emails, but is not limited to such examples. The learning unit, for example, collects minutes of meetings and analyzes them using AI. For example, the learning unit can collect minutes of meetings and analyze them using natural language processing technology. The learning unit can also collect the contents of emails and analyze them using AI. For example, the learning unit can collect the contents of emails and analyze them using machine learning algorithms. Furthermore, the learning unit can collect reports of projects conducted by the user in the past and analyze them using AI. For example, the learning unit can collect project reports and analyze them using natural language processing technology. This allows the learning unit to learn the user's decision-making patterns and policies.

[0065] The response unit can respond to questions from other participants based on the content of past user remarks and decision-making patterns. The content of past user remarks and decision-making patterns include, for example, specific keywords, decision-making rules, and the like, but are not limited to such examples. The response unit responds to questions from other participants based on the content of user remarks in past conferences, for example. For example, the response unit can respond to questions from other participants based on the content of user remarks in past conferences. The response unit can also respond to questions from other participants based on the user's decision-making patterns. For example, the response unit can respond to questions from other participants based on the user's decision-making rules. This enables the response unit to respond to other participants in a consistent manner.

[0066] The update unit can improve the response accuracy by making the AI ​​learn the decision-making and statement contents newly made by the user. The newly made decision-making and statement contents include, but are not limited to, for example, the decision of a new project and statements made in a meeting. The update unit, for example, collects records of meetings newly made by the user and makes the AI ​​learn. For example, the update unit can collect records of meetings, analyze them using natural language processing technology, and make the AI ​​learn. The update unit can also collect the contents of emails newly sent and received by the user and make the AI ​​learn. For example, the update unit can collect the contents of emails, analyze them using a machine learning algorithm, and make the AI ​​learn. Furthermore, the update unit can collect reports of projects newly made by the user and make the AI ​​learn. For example, the update unit can collect project reports, analyze them using natural language processing technology, and make the AI ​​learn. This enables the update unit to always respond based on the latest user's thinking and policies.

[0067] The response unit displays an avatar on the screen and can have a conversation with other participants. The method of displaying the avatar on the screen includes, but is not limited to, a 2D avatar, a 3D avatar, and the like. The response unit displays an avatar on the screen and can have a conversation with other participants. For example, the response unit can display a 2D avatar on the screen and can have a conversation with other participants. The response unit can also display a 3D avatar on the screen and can have a conversation with other participants. Furthermore, the response unit can also have the avatar have a conversation with other participants in real time. For example, the response unit can have the avatar have a conversation with other participants in real time. This allows the response unit to support the progress of the conference even when the user is absent.

[0068] The update unit can continuously collect new data and improve the accuracy of the learning unit and the response unit. The new data includes, for example, the latest meeting records, the contents of new emails, etc., but is not limited to such examples. The update unit can, for example, collect the latest meeting records and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect the latest meeting records and analyze them using natural language processing technology to improve the accuracy of the learning unit and the response unit. The update unit can also collect the contents of new emails and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect the contents of new emails and analyze them using a machine learning algorithm to improve the accuracy of the learning unit and the response unit. Furthermore, the update unit can also collect new project reports and improve the accuracy of the learning unit and the response unit. For example, the update unit can collect new project reports and analyze them using natural language processing technology to improve the accuracy of the learning unit and the response unit. This allows the update unit to improve the accuracy of the system.

[0069] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, when the user is stressed, the learning unit preferentially learns data of decision-making made in a relaxed state. For example, when the user is stressed, the learning unit can preferentially learn data of decision-making made in a relaxed state. Furthermore, when the user is relaxed, the learning unit can also learn detailed decision-making data. For example, when the user is relaxed, the learning unit can learn detailed decision-making data. Furthermore, when the user is in a hurry, the learning unit can also preferentially learn data of quick decision-making. For example, when the user is in a hurry, the learning unit can preferentially learn data of quick decision-making. This enables the learning unit to select appropriate learning data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0070] The learning unit can collect background information of the user's past decision-making and reflect it in the learning. The background information of the past decision-making includes, for example, details of past projects, reasons for decision-making, etc., but is not limited to such examples. The learning unit, for example, collects minutes of meetings held by the user in the past and learns the background of the decision-making. For example, the learning unit can collect minutes of meetings, analyze them using natural language processing technology, and learn the background of the decision-making. The learning unit can also analyze the contents of emails sent and received by the user in the past and learn the background of the decision-making. For example, the learning unit can collect the contents of the emails, analyze them using a machine learning algorithm, and learn the background of the decision-making. Furthermore, the learning unit can collect reports of projects held by the user in the past and learn the background of the decision-making. For example, the learning unit can collect project reports, analyze them using natural language processing technology, and learn the background of the decision-making. As a result, the learning unit can reflect the background information of the decision-making in the learning, thereby enabling more accurate learning.

[0071] During learning, the learning unit can analyze the priority of the user's decision-making and perform learning according to the importance. The priority of decision-making includes, for example, an evaluation criterion for the importance, a method for determining the priority, and the like, but is not limited to such examples. For example, the learning unit preferentially learns the decision-making made by the user in an important meeting. For example, the learning unit can preferentially learn the decision-making made by the user in an important meeting. In addition, the learning unit can also preferentially learn the decision-making made by the user in an emergency. For example, the learning unit can preferentially learn the decision-making made by the user in an emergency. Furthermore, the learning unit can also preferentially learn the decision-making made by the user in a long-term project. For example, the learning unit can preferentially learn the decision-making made by the user in a long-term project. This enables the learning unit to learn according to the importance.

[0072] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. The frequency of learning includes, for example, periodic learning, event-based learning, and the like, but is not limited to such examples. For example, when the user is stressed, the learning unit can reduce the frequency of learning and prioritize learning in a relaxed state. For example, when the user is stressed, the learning unit can reduce the frequency of learning and prioritize learning in a relaxed state. In addition, the learning unit can increase the frequency of learning and learn detailed data when the user is relaxed. For example, when the user is relaxed, the learning unit can increase the frequency of learning and learn detailed data. Furthermore, when the user is in a hurry, the learning unit can adjust the frequency of learning and prioritize data for quick decision-making. For example, when the user is in a hurry, the learning unit can adjust the frequency of learning and prioritize data for quick decision-making. This enables the learning unit to adjust the learning frequency appropriately according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0073] The learning unit can perform learning based on the geographical background and cultural background of the user during learning. The geographical background and cultural background include, for example, local customs, cultural values, and the like, but are not limited to such examples. For example, the learning unit can learn decisions made by the user in different cultural spheres and take the cultural background into consideration. For example, the learning unit can learn decisions made by the user in different cultural spheres and take the cultural background into consideration. In addition, the learning unit can also learn decisions made by the user in different regions and take the geographical background into consideration. For example, the learning unit can learn decisions made by the user in different regions and take the geographical background into consideration. Furthermore, the learning unit can also learn decisions made by the user in an international project and take the geographical and cultural background into consideration. For example, the learning unit can learn decisions made by the user in an international project and take the geographical and cultural background into consideration. This enables the learning unit to perform learning taking the geographical and cultural background into consideration.

[0074] During learning, the learning unit can analyze the user's social media activity and learn the tendency of decision-making. Social media activity includes, for example, the content of posts, the reactions of followers, and the like, but is not limited to such examples. The learning unit, for example, analyzes statements made by the user on social media and learns the tendency of decision-making. For example, the learning unit can analyze statements made by the user on social media and learn the tendency of decision-making. In addition, the learning unit can analyze articles and posts shared by the user on social media and learn the tendency of decision-making. For example, the learning unit can analyze articles and posts shared by the user on social media and learn the tendency of decision-making. In addition, the learning unit can analyze discussions in which the user participated on social media and learn the tendency of decision-making. For example, the learning unit can analyze discussions in which the user participated on social media and learn the tendency of decision-making. This enables the learning unit to learn in consideration of social media activity.

[0075] The response unit can estimate the user's emotion and adjust the way of expressing the response based on the estimated emotion of the user. The way of expressing the response includes, for example, wording, tone, and the like, but is not limited to such examples. For example, when the user is nervous, the response unit responds in a calm way of expression. For example, when the user is nervous, the response unit can respond in a calm way of expression. In addition, when the user is relaxed, the response unit can also respond in a friendly way of expression. For example, when the user is relaxed, the response unit can respond in a friendly way of expression. Furthermore, when the user is in a hurry, the response unit can also respond in a concise and quick way of expression. For example, when the user is in a hurry, the response unit can respond in a concise and quick way of expression. This enables the response unit to express an appropriate response according to the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0076] The response unit can analyze the remarks of other participants in real time at the time of response and generate an optimal response. The optimal response includes, for example, a real-time analysis method, a response generation algorithm, and the like, but is not limited to such examples. The response unit can analyze, for example, the remarks of other participants in real time and generate an appropriate response. For example, the response unit can analyze the remarks of other participants in real time and generate an appropriate response. In addition, the response unit can respond to questions of other participants based on past remarks of users. For example, the response unit can respond to questions of other participants based on past remarks of users. Furthermore, the response unit can respond to opinions of other participants based on the decision-making patterns of users. For example, the response unit can respond to opinions of other participants based on the decision-making patterns of users. This makes it possible for the response unit to generate optimal responses in real time.

[0077] The response unit can adjust the timing of the response based on the progress of the conference when responding. The timing of the response includes, for example, an evaluation criterion for the progress of the conference, a delay time of the response, and the like, but is not limited to such examples. The response unit, for example, analyzes the progress of the conference in real time and responds at an appropriate timing. For example, the response unit can analyze the progress of the conference in real time and respond at an appropriate timing. In addition, the response unit can adjust the timing of the response according to the agenda of the conference. For example, the response unit can adjust the timing of the response according to the agenda of the conference. Furthermore, the response unit can respond at the timing when the other participants finish speaking. For example, the response unit can respond at the timing when the other participants finish speaking. This enables the response unit to respond at an appropriate timing according to the progress of the conference.

[0078] The response unit can estimate the user's emotion and determine the priority of responses based on the estimated user's emotion. The priority of responses includes, for example, an evaluation criterion of importance, a method of determining priority, and the like, but is not limited to such examples. For example, when the user is nervous, the response unit responds preferentially to important questions. For example, when the user is nervous, the response unit can respond preferentially to important questions. In addition, when the user is relaxed, the response unit can also respond preferentially to detailed questions. For example, when the user is relaxed, the response unit can also respond preferentially to detailed questions. In addition, when the user is in a hurry, the response unit can also respond preferentially to questions that require a quick response. For example, when the user is in a hurry, the response unit can respond preferentially to questions that require a quick response. This enables the response unit to prioritize responses appropriately according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0079] The response unit can respond by taking into consideration the geographical background and cultural background of the other participants. The geographical background and cultural background include, but are not limited to, local customs and cultural values. For example, the response unit responds in an appropriate manner of expression by taking into consideration the cultural background of the other participants. For example, the response unit can respond in an appropriate manner of expression by taking into consideration the cultural background of the other participants. In addition, the response unit can provide appropriate information by taking into consideration the geographical background of the other participants. For example, the response unit can provide appropriate information by taking into consideration the geographical background of the other participants. Furthermore, the response unit can respond at an appropriate time by taking into consideration the cultural customs of the other participants. For example, the response unit can respond at an appropriate time by taking into consideration the cultural customs of the other participants. This enables the response unit to respond in consideration of the geographical and cultural backgrounds.

[0080] The response unit can analyze the social media activities of the other participants at the time of response and reflect the relevant information in the response. The social media activities include, for example, the content of posts and the reactions of followers, but are not limited to such examples. The response unit can analyze, for example, the statements of the other participants on social media and reflect the relevant information in the response. For example, the response unit can analyze the statements of the other participants on social media and reflect the relevant information in the response. In addition, the response unit can also make an appropriate response based on articles and posts shared by the other participants. For example, the response unit can make an appropriate response based on articles and posts shared by the other participants. In addition, the response unit can analyze the activities of the other participants on social media and make an appropriate response. For example, the response unit can analyze the activities of the other participants on social media and make an appropriate response. This enables the response unit to respond in consideration of the social media activities.

[0081] The update unit can estimate the user's emotion and select update data based on the estimated user's emotion. The update data includes, for example, new meeting records, the contents of new emails, and the like, but is not limited to such examples. For example, when the user is stressed, the update unit preferentially updates the data of decision-making made in a relaxed state. For example, when the user is stressed, the update unit can preferentially update the data of decision-making made in a relaxed state. Furthermore, when the user is relaxed, the update unit can also update the data of detailed decision-making. For example, when the user is relaxed, the update unit can update the data of detailed decision-making. Furthermore, when the user is in a hurry, the update unit can also preferentially update the data of quick decision-making. For example, when the user is in a hurry, the update unit can preferentially update the data of quick decision-making. This enables the update unit to select appropriate update data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0082] The update unit can analyze past response data at the time of updating and optimize the response algorithm. The response algorithm includes, for example, performance evaluation, an algorithm improvement method, and the like, but is not limited to such examples. The update unit can analyze, for example, past response data and optimize the response algorithm. For example, the update unit can analyze past response data and optimize the response algorithm. In addition, the update unit can extract an effective response pattern from the past response data and reflect it in the algorithm. For example, the update unit can extract an effective response pattern from the past response data and reflect it in the algorithm. Furthermore, the update unit can improve the accuracy of the response based on the past response data. For example, the update unit can improve the accuracy of the response based on the past response data. This makes it possible for the update unit to optimize the response algorithm based on the past response data.

[0083] The update unit can collect background information of the user's new decision-making at the time of updating and reflect it in the learning. The background information of the new decision-making includes, for example, details of the new project, reasons for the decision-making, etc., but is not limited to such examples. The update unit can collect, for example, records of a meeting newly held by the user and reflect it in the learning. For example, the update unit can collect records of the meeting, analyze them using natural language processing technology, and reflect them in the learning. The update unit can also analyze the contents of emails newly sent and received by the user and reflect them in the learning. For example, the update unit can collect the contents of the emails, analyze them using a machine learning algorithm, and reflect them in the learning. Furthermore, the update unit can collect reports of projects newly held by the user and reflect them in the learning. For example, the update unit can collect project reports, analyze them using natural language processing technology, and reflect them in the learning. As a result, the update unit can reflect the background information of the new decision-making in the learning, thereby enabling more accurate learning.

[0084] The update unit can estimate the user's emotion and adjust the frequency of updates based on the estimated user's emotion. The frequency of updates includes, for example, periodic updates, event-based updates, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the update unit can reduce the frequency of updates and prioritize updates in a relaxed state. For example, when the user is feeling stressed, the update unit can reduce the frequency of updates and prioritize updates in a relaxed state. In addition, the update unit can increase the frequency of updates and update detailed data when the user is relaxed. For example, when the user is relaxed, the update unit can increase the frequency of updates and update detailed data. Furthermore, when the user is in a hurry, the update unit can adjust the frequency of updates and prioritize data for quick decision-making. For example, when the user is in a hurry, the update unit can adjust the frequency of updates and prioritize data for quick decision-making. This enables the update unit to adjust the update frequency appropriately according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0085] The update unit can perform the update based on the geographical background and cultural background of the user at the time of the update. The geographical background and the cultural background include, for example, local customs, cultural values, and the like, but are not limited to such examples. For example, the update unit can update the decision made by the user in a different cultural sphere and take into account the cultural background. For example, the update unit can update the decision made by the user in a different cultural sphere and take into account the cultural background. The update unit can also update the decision made by the user in a different region and take into account the geographical background. For example, the update unit can update the decision made by the user in a different region and take into account the geographical background. Furthermore, the update unit can update the decision made by the user in an international project and take into account the geographical and cultural background. For example, the update unit can update the decision made by the user in an international project and take into account the geographical and cultural background. This enables the update unit to perform the update taking into account the geographical and cultural background.

[0086] The update unit can analyze the user's social media activity at the time of updating and learn the decision-making tendency. The social media activity includes, for example, the content of the post, the reaction of the followers, and the like, but is not limited to such examples. The update unit can, for example, analyze the remarks made by the user on social media and learn the decision-making tendency. For example, the update unit can analyze the remarks made by the user on social media and learn the decision-making tendency. The update unit can also analyze the articles and posts shared by the user on social media and learn the decision-making tendency. For example, the update unit can analyze the articles and posts shared by the user on social media and learn the decision-making tendency. Furthermore, the update unit can analyze the discussions in which the user participated on social media and learn the decision-making tendency. For example, the update unit can analyze the discussions in which the user participated on social media and learn the decision-making tendency. This enables the update unit to learn in consideration of the social media activity.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The system may further include a feedback unit. The feedback unit collects feedback from other participants after the online meeting ends and provides it to the learning unit. For example, the feedback unit may collect how other participants felt about the avatar's response in the form of a questionnaire. The feedback unit may also collect comments and evaluations made by other participants on the avatar's response. Furthermore, the feedback unit may collect specific improvements made by other participants to the avatar's response. This allows the learning unit to improve the avatar's response based on the feedback from other participants, enabling more appropriate responses.

[0089] The learning unit can analyze the user's past behavior history when learning the user's decision-making thinking and policies. For example, the learning unit can collect and analyze what websites the user has viewed in the past and what applications the user has used. The learning unit can also collect and analyze what purchasing behavior the user has performed in the past. Furthermore, the learning unit can collect and analyze what social media posts the user has made in the past. This allows the learning unit to more accurately learn the decision-making thinking and policies based on the user's behavior history.

[0090] When analyzing the content of the speech of the other participants, the response unit can estimate the emotion of the speaker and adjust the response based on the estimated emotion. For example, if the other participant is angry, the response unit can provide a calm and collected response. If the other participant is sad, the response unit can also provide an empathetic response. Furthermore, if the other participant is happy, the response unit can also provide a positive response. This enables the response unit to provide an appropriate response according to the emotion of the other participants.

[0091] The update unit can take into account the user's current emotional state when learning new decisions and utterances of the user. For example, when the user is feeling stressed, the update unit can preferentially learn decisions and utterances made in less stressful situations. In addition, when the user is relaxed, the update unit can also learn detailed decisions and utterances. Furthermore, when the user is in a hurry, the update unit can also preferentially learn quick decisions and utterances. This enables the update unit to perform appropriate learning according to the user's emotional state.

[0092] The response unit can translate the content of speech of other participants in real time when the avatar is having a conversation, and support communication with participants who speak different languages. For example, the response unit can translate content spoken in English into Japanese and provide it to the Japanese-speaking participant. The response unit can also translate content spoken in Japanese into English and provide it to the English-speaking participant. Furthermore, the response unit can also translate between other languages. This allows the response unit to support smooth communication with participants who speak different languages.

[0093] The update unit can take into account the success rate of the user's past decisions when learning the user's new decisions and utterances. For example, the update unit can preferentially learn successful decisions made by the user in the past. The update unit can also learn unsuccessful decisions made by the user in the past and use them as data to avoid similar failures. Furthermore, the update unit can preferentially learn particularly important decisions made by the user in the past. This enables the update unit to perform appropriate learning taking into account the success rate of the user's past decisions.

[0094] The learning unit can estimate the user's emotions and select learning data based on the estimated emotions. For example, when the user is feeling stressed, the learning unit can preferentially learn data of decisions made in a relaxed state. Also, when the user is relaxed, the learning unit can also learn data of detailed decisions. Furthermore, when the user is in a hurry, the learning unit can also preferentially learn data of quick decisions. This enables the learning unit to select appropriate learning data according to the user's emotions.

[0095] The learning unit can collect background information of the user's past decision-making and reflect it in the learning. For example, the learning unit can collect minutes of meetings held in the past by the user and learn the background of the decision-making. The learning unit can also analyze the contents of emails sent and received in the past by the user and learn the background of the decision-making. Furthermore, the learning unit can collect reports of projects held in the past by the user and learn the background of the decision-making. In this way, the learning unit can reflect the background information of the decision-making in the learning, thereby enabling more accurate learning.

[0096] During learning, the learning unit can analyze the priority of the user's decision-making and perform learning according to the importance. For example, the learning unit can prioritize learning of decisions made by the user in important meetings. The learning unit can also prioritize learning of decisions made by the user in emergencies. Furthermore, the learning unit can also prioritize learning of decisions made by the user in long-term projects. This enables the learning unit to perform learning according to the importance.

[0097] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated emotions. For example, when the user is feeling stressed, the learning unit can reduce the frequency of learning and prioritize learning in a relaxed state. Also, when the user is relaxed, the learning unit can increase the frequency of learning and learn detailed data. Furthermore, when the user is in a hurry, the learning unit can adjust the frequency of learning and prioritize data for quick decision-making. This enables the learning unit to adjust the learning frequency appropriately according to the user's emotions.

[0098] The process flow of the second embodiment will be briefly described below.

[0099] Step 1: The learning unit learns the user's decision-making thinking and policies. The learning unit collects data such as records of past meetings, email correspondence, and project reports from the user, and analyzes it using AI. Step 2: The response unit responds to conversations in online meetings using the avatar based on the information learned by the learning unit. The response unit responds to questions from other participants based on the user's past comments and decision-making patterns. The avatar is displayed on the screen and engages in conversations with other participants. Step 3: The update unit continuously learns and updates based on the responses made by the response unit. The update unit trains the AI ​​on new decisions and statements made by the user, improving the accuracy of responses. For example, the update unit collects records of new meetings held by the user, the contents of emails sent and received, and project reports, and trains the AI ​​to learn from them.

[0100] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the 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 voice data.

[0101] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0102] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0103] Each of the multiple elements including the learning unit, the response unit, and the update unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14, and collects the user's past meeting records and email exchanges and analyzes them using AI. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and an avatar responds appropriately to questions from other participants in an online meeting. The update unit is realized, for example, by the control unit 46A of the smart device 14, and continuously learns the user's new decision-making and remarks, improving the response accuracy. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0104] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0105] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0106] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, 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. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0108] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0109] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0110] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0111] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0112] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0114] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0115] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0116] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0117] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0118] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0119] Each of the multiple elements including the learning unit, the response unit, and the update unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214, and collects the user's past meeting records and email exchanges and analyzes them using AI. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and an avatar responds appropriately to questions from other participants in an online meeting. The update unit is realized, for example, by the control unit 46A of the smart glasses 214, and continuously learns the user's new decision-making and remarks to improve response accuracy. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0122] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0123] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. 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. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0124] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0125] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0127] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0128] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0129] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0130] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0131] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0132] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0133] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0134] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0135] Each of the multiple elements including the learning unit, the response unit, and the update unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314, and collects the user's past meeting records and email exchanges, and analyzes them using AI. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and an avatar responds appropriately to questions from other participants in an online meeting. The update unit is realized, for example, by the control unit 46A of the headset type terminal 314, and continuously learns the user's new decision-making and remarks, and improves response accuracy. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, a 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.

[0138] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may 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 a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] Each of the multiple elements including the learning unit, the response unit, and the update unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414, and collects the user's past meeting records and email exchanges, and analyzes them by AI. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and an avatar responds appropriately to questions from other participants in an online meeting. The update unit is realized, for example, by the control unit 46A of the robot 414, and continuously learns the user's new decision-making and remarks, and improves response accuracy. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0153] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0154] FIG. 9 is a diagram showing an emotion map 400 on 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 emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0157] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0158] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] In addition, 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 upon request from the data processing device 12.

[0163] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0165] The hardware resource that executes the specific process may be one of these various processors, or may be 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). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration in which a processor is used that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0169] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0171] (Appendix 1) a learning unit that learns a user's decision-making thinking and policies; A response unit that causes an avatar to respond to a conversation in an online meeting based on the information learned by the learning unit; and an update unit that continuously learns and updates based on the response made by the response unit. A system characterized by: (Appendix 2) The learning unit is Collect data from past meetings or email exchanges held by users and analyze it using AI. 2. The system of claim 1, (Appendix 3) The response unit: Respond to questions from other participants based on past user comments and decision-making patterns 2. The system of claim 1, (Appendix 4) The update unit is The AI ​​learns new decisions and statements made by users to improve response accuracy. 2. The system of claim 1, (Appendix 5) The response unit: Your avatar will appear on screen and you will be able to talk to other participants. 2. The system of claim 1, (Appendix 6) The update unit is Continuously collect new data to improve the accuracy of the learning and response parts 2. The system of claim 1, (Appendix 7) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The learning unit is Gather context about users’ past decisions and incorporate it into learnings 2. The system of claim 1, (Appendix 9) The learning unit is During learning, the system analyzes the user's decision priorities and learns according to their importance. 2. The system of claim 1, (Appendix 10) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 11) The learning unit is When learning, learn based on the user's geographic and cultural background 2. The system of claim 1, (Appendix 12) The learning unit is During training, the system analyzes users' social media activity to learn their decision-making tendencies. 2. The system of claim 1, (Appendix 13) The response unit: Inferring user emotions and adjusting the way responses are expressed based on the inferred user emotions 2. The system of claim 1, (Appendix 14) The response unit: When responding, it analyzes what other participants have said in real time and generates the best response 2. The system of claim 1, (Appendix 15) The response unit: When responding, adjust the timing of your response based on the progress of the meeting 2. The system of claim 1, (Appendix 16) The response unit: Inferring user emotions and prioritizing responses based on the estimated user emotions 2. The system of claim 1, (Appendix 17) The response unit: When responding, consider the geographic and cultural backgrounds of other participants 2. The system of claim 1, (Appendix 18) The response unit: When responding, analyze the social media activity of other participants and incorporate relevant information into your response 2. The system of claim 1, (Appendix 19) The update unit is Estimate the user's emotions and select update data based on the estimated user emotions. 2. The system of claim 1, (Appendix 20) The update unit is When updating, the past response data is analyzed and the response algorithm is optimized. 2. The system of claim 1, (Appendix 21) The update unit is During updates, gather context for new user decisions and incorporate it into your learnings 2. The system of claim 1, (Appendix 22) The update unit is Infer user sentiment and adjust update frequency based on the estimated user sentiment 2. The system of claim 1, (Appendix 23) The update unit is When updating, it will update based on the geographic and cultural background of the user 2. The system of claim 1, (Appendix 24) The update unit is During updates, analyze users' social media activity to learn their decision-making trends 2. The system of claim 1, [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a learning unit that learns a user's decision-making thinking and policies; A response unit that causes an avatar to respond to a conversation in an online meeting based on the information learned by the learning unit; and an update unit that continuously learns and updates based on the response made by the response unit. A system characterized by:

2. The learning unit is Collect data from past meetings or email exchanges held by users and analyze it using AI.

2. The system of claim 1 .

3. The response unit: Respond to questions from other participants based on past user comments and decision-making patterns 2. The system of claim 1 .

4. The update unit is The AI ​​learns new decisions and statements made by the user to improve response accuracy.

2. The system of claim 1 .

5. The response unit: Your avatar will appear on screen and you will be able to talk to other participants.

2. The system of claim 1 .

6. The update unit is Continuously collect new data to improve the accuracy of the learning and response units.

2. The system of claim 1 .

7. The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions.

2. The system of claim 1 .

8. The learning unit is Gather context about users’ past decisions and incorporate it into learnings 2. The system of claim 1 .

Images