System

Abstract

An object of a system according to an embodiment is to enrich the content of a meeting and prevent important problems from being overlooked.SOLUTION: A system includes a role setting part, a participation part, an input part, a supplementary explanation part, and a minutes creation part. The role setting unit sets a role before a conference. The participation unit participates in the conference based on the role set by the role setting unit. The input unit inputs the content of the conference in advance. The supplementary explanation unit makes a supplementary explanation during the conference based on the information input by the input unit. The minutes creating section automatically compiles minutes of the conference.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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques can result in meetings that are not productive and important issues can be overlooked.

[0005] The system according to the embodiment aims to enrich the content of the meeting and to prevent important issues from being overlooked. [Means for solving the problem]

[0006] The system according to the embodiment includes a role setting unit, a participation unit, an input unit, a supplementary explanation unit, and a minutes creation unit. The role setting unit sets roles before a meeting. The participation unit participates in the meeting based on the roles set by the role setting unit. The input unit inputs the contents of the meeting in advance. The supplementary explanation unit provides supplementary explanations during the meeting based on the information input by the input unit. The minutes creation unit automatically compiles minutes of the meeting. [Effects of the Invention]

[0007] The system according to the embodiment can enrich the content of the meeting and prevent important issues from being overlooked. [Brief explanation 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. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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 INVENTION

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

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

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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 coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, 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 symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A meeting support system according to an embodiment of the present invention uses a generation AI to participate in meetings and enhance the quality of the meetings. The meeting support system assigns roles to the generation AI before the meeting, and the generation AI participates in the meeting based on the assigned roles. For example, the role of posing questions or providing supplementary explanations can be assigned. Furthermore, by inputting the meeting content in advance, the generation AI can provide appropriate supplementary explanations. Furthermore, the system automatically compiles meeting minutes and reviews the content of the previous meeting. It is also possible to summarize next-level actions based on the meeting content. Furthermore, the system translates the meeting content in real time and automatically adjusts each participant's schedule. This eliminates language barriers and allows the meeting to proceed smoothly. For example, the meeting support system assigns roles to the generation AI before the meeting. For example, the role of posing questions or providing supplementary explanations can be assigned. This allows the generation AI to pose questions or provide supplementary explanations at appropriate times during the meeting. Next, the meeting content is input into the generation AI in advance. This allows the generation AI to provide appropriate supplementary explanations during the meeting. For example, by inputting background information and related data about a meeting's agenda into the generation AI, the generation AI can provide supplementary explanations based on that information during the meeting. Furthermore, the generation AI automatically compiles meeting minutes. After the meeting, the generation AI creates minutes and provides them to participants. This ensures that the meeting content is accurately recorded and can be referenced later. The generation AI also has a function to review the content of the previous meeting. At the beginning of the meeting, the generation AI briefly reviews the content of the previous meeting and shares it with participants. This allows the meeting to proceed smoothly without forgetting the content of the previous meeting. Furthermore, the generation AI can summarize the next action based on the meeting content. After the meeting ends, the generation AI lists the next action and provides it to participants. This allows specific actions to be planned for the next meeting. The generation AI also translates the meeting content in real time and automatically adjusts each person's schedule. This breaks down language barriers and allows meetings to proceed smoothly. For example, if there are participants who speak different languages, the generation AI translates the meeting content in real time and provides it to participants.The generation AI also automatically adjusts the meeting schedule, aligning the schedules of all participants. This makes the meeting support system a hero for realizing productive meetings. By using the generation AI, it is possible to improve the quality of meetings and realize meetings that satisfy all participants.

[0029] A meeting support system according to an embodiment includes a role setting unit, a participation unit, an input unit, a supplemental explanation unit, and a minutes creation unit. The role setting unit sets roles before a meeting. For example, the role may be a role for raising questions or a role for providing supplemental explanations. For example, the role setting unit may set a role for the generation AI to raise questions or provide supplemental explanations at appropriate times during the meeting. The role setting unit may also set a role for the generation AI to support the progress of the meeting. The participation unit participates in the meeting based on the role set by the role setting unit. For example, the participation unit may allow the generation AI to raise questions or provide supplemental explanations during the meeting. The participation unit may also support the generation AI in the progress of the meeting. The input unit inputs the content of the meeting in advance. For example, the input unit may input background information and related data related to the meeting agenda to the generation AI. The input unit may also input information for the generation AI to provide appropriate supplemental explanations during the meeting. The supplementary explanation unit provides supplementary explanations during the meeting based on the information input by the input unit. For example, the supplementary explanation unit enables the generation AI to provide supplementary explanations based on background information and related data regarding the meeting agenda. The supplementary explanation unit also enables the generation AI to provide appropriate answers to participants' questions during the meeting. The minutes-taking unit automatically compiles meeting minutes. For example, the generation AI can record the contents of the meeting and create the minutes. The minutes-taking unit can also enable the generation AI to provide the minutes to participants after the meeting ends. As a result, the meeting support system according to the embodiment can improve the quality of the meeting by setting roles before the meeting and providing appropriate supplementary explanations and creating minutes during the meeting. For example, the meeting support system can set roles in the generation AI before the meeting and raise questions or provide supplementary explanations at appropriate times during the meeting. The meeting support system can also input the contents of the meeting into the generation AI in advance and provide appropriate supplementary explanations during the meeting. Furthermore, the meeting support system can automatically compile minutes of the meeting and provide them to participants after the meeting has ended.As a result, the conference support system can improve the quality of the conference and realize a conference that satisfies all participants.

[0030] The minutes-taking unit can create minutes after the meeting ends and send them to participants by email. For example, after the meeting ends, the generation AI can create minutes and send them to participants by email. In the minutes-taking unit, the generation AI records the contents of the meeting and creates minutes. For example, the minutes-taking unit can create minutes including summaries of each agenda item, a record of speakers, and a list of action items. In the minutes-taking unit, the generation AI also sends the minutes by email. For example, the minutes-taking unit can automatically create minutes after the meeting ends and send them to participants by email. In this way, by creating minutes after the meeting ends and providing them to participants, the contents of the meeting can be accurately recorded and can be referenced later. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can record the contents of the meeting and input them into a generation AI that creates minutes, and the generation AI can create the minutes and send them by email.

[0031] The supplemental explanation unit can provide supplemental explanations based on background information and related data related to the meeting agenda. The supplemental explanation unit can provide supplemental explanations based on, for example, background information and related data related to the meeting agenda. The supplemental explanation unit can provide supplemental explanations based on, for example, background information and related data related to the meeting agenda by the generation AI. For example, the supplemental explanation unit can provide background information related to the meeting agenda by the generation AI to deepen participants' understanding. The supplemental explanation unit can also provide data related to the meeting agenda by the generation AI to deepen participants' understanding. In this way, by providing supplemental explanations based on background information and related data related to the meeting agenda, it is possible to deepen participants' understanding of the meeting. Some or all of the above-mentioned processing in the supplemental explanation unit can be performed using, or without, the generation AI. For example, the supplemental explanation unit can input background information and related data related to the meeting agenda into the generation AI, and the generation AI can provide supplemental explanations.

[0032] The role setting unit can set a role of posing a question or a role of providing supplementary explanation. The role setting unit, for example, sets a role of posing a question or a role of providing supplementary explanation. The role setting unit can set a role for the generation AI to pose a question or provide supplementary explanation at an appropriate time during the meeting. For example, the role setting unit can also set a role for the generation AI to support the progress of the meeting. In this way, by setting a role of posing a question or a role of providing supplementary explanation, questions or supplementary explanations can be given at an appropriate time during the meeting. Some or all of the above-described processing in the role setting unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the role setting unit sets a role of posing a question or a role of providing supplementary explanation to the generation AI, and the generation AI can play that role during the meeting.

[0033] The participation unit can raise questions or provide supplementary explanations during a meeting based on a set role. For example, the participation unit raises questions or provides supplementary explanations during a meeting based on a set role. The participation unit can have the generation AI raise questions or provide supplementary explanations at appropriate times during the meeting. For example, the participation unit can also have the generation AI support the progress of the meeting. This allows questions or supplementary explanations to be asked at appropriate times during the meeting based on a set role, thereby making it possible to smoothly progress the meeting. Some or all of the above-described processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit inputs data to a generation AI that raises questions or provides supplementary explanations during a meeting based on a set role, and the generation AI can fulfill its role.

[0034] The minutes-taking unit may have a function to summarize and display the contents of the previous meeting. The minutes-taking unit may, for example, have a function to summarize and display the contents of the previous meeting. In the minutes-taking unit, the generation AI may summarize the contents of the previous meeting and display it to participants at the beginning of the meeting. For example, the minutes-taking unit may have the generation AI briefly review the contents of the previous meeting and share it with participants. By reviewing the contents of the previous meeting, participants can avoid forgetting the contents of the previous meeting and the meeting can proceed smoothly. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit may input the contents of the previous meeting into a generation AI that summarizes and displays them, and the generation AI may display the contents.

[0035] The minutes-taking unit can list the next actions and send them to the participants by email. The minutes-taking unit, for example, lists the next actions and sends them to the participants by email. The minutes-taking unit can have the generation AI list the next actions based on the content of the meeting and provide them to the participants. For example, the minutes-taking unit can have the generation AI list the next actions after the end of the meeting and send them by email to the participants. By listing the next actions and providing them to the participants, specific actions can be planned for the next meeting. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can list the next actions and input them into the generation AI, which sends them to the participants by email, and the generation AI then sends the content.

[0036] The supplementary explanation unit can translate and display the contents of the meeting in real time. For example, the supplementary explanation unit can translate and display the contents of the meeting in real time. The supplementary explanation unit can have the generation AI translate the contents of the meeting in real time and provide it to participants. For example, the supplementary explanation unit can have the generation AI translate and display the contents of the meeting in real time for participants who speak different languages. By translating the contents of the meeting in real time, participants who speak different languages ​​can smoothly participate in the meeting. Some or all of the above-mentioned processing in the supplementary explanation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the supplementary explanation unit can input the contents of the meeting to a generation AI that translates and displays the contents in real time, and the generation AI can translate and display the contents.

[0037] The input unit can be equipped with a system that automatically adjusts each person's schedule. The input unit, for example, is equipped with a system that automatically adjusts each person's schedule. In the input unit, the generation AI can automatically adjust each person's schedule and set a meeting schedule. For example, in the input unit, the generation AI can automatically adjust the schedules of all participants and set a meeting schedule. This makes it possible to automatically adjust each person's schedule, thereby making meeting schedule adjustment more efficient. Some or all of the above-mentioned processing in the input unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the input unit can input each person's schedule into the generation AI, and the generation AI can adjust the schedule.

[0038] The role setting unit may include a system that analyzes past meeting data and automatically proposes roles according to the purpose of the meeting. The role setting unit, for example, analyzes past meeting data and automatically proposes roles according to the purpose of the meeting. The role setting unit can use a generation AI to analyze past meeting data and automatically propose roles according to the purpose of the meeting based on the data. For example, the role setting unit may assign a questioner based on questions that frequently came up in past meetings. The role setting unit may also assign a supplementary explanation role to supplement information that was lacking in past meetings. Furthermore, the role setting unit may assign a time management role for topics that were discussed prolongedly in past meetings. In this way, by analyzing past meeting data, optimal roles according to the purpose of the meeting can be automatically proposed. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit may input past meeting data into the generation AI, which may analyze the data and propose roles according to the purpose of the meeting.

[0039] The role setting unit may include a system that customizes roles based on the expertise and titles of meeting participants. The role setting unit customizes roles based on, for example, the expertise and titles of meeting participants. The role setting unit allows a generation AI to customize roles based on the expertise and titles of meeting participants. For example, the role setting unit assigns a role to answer technical questions to a participant with specialized knowledge. The role setting unit can also assign a role to support the progress of the meeting to a participant with a higher title. Furthermore, the role setting unit can assign a role to ask questions for learning purposes to a new employee. In this way, customizing roles based on the expertise and titles of meeting participants makes the progress of the meeting smoother. Some or all of the above-described processing in the role setting unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the role setting unit inputs data into a generation AI that customizes roles based on the expertise and titles of meeting participants, and the generation AI can set the roles.

[0040] The role setting unit may include a system that sets multiple roles in combination according to the theme of the meeting. The role setting unit sets multiple roles in combination according to, for example, the theme of the meeting. The role setting unit allows the generation AI to set multiple roles in combination according to the theme of the meeting. For example, the role setting unit sets a technical questioner and a technical supplementary explanation role in a meeting on a technical theme. The role setting unit can also set a progress manager and a risk manager role in a meeting on project progress. Furthermore, the role setting unit can also set a marketing questioner and a technical supplementary explanation role in a meeting on a new product. In this way, by combining multiple roles according to the theme of the meeting, the progress of the meeting becomes more effective. Some or all of the above-described processing in the role setting unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the role setting unit inputs the information into a generation AI that sets multiple roles in combination according to the theme of the meeting, and the generation AI can set the roles.

[0041] The role setting unit can set roles based on geographical location information of the conference participants. The role setting unit, for example, sets roles based on geographical location information of the conference participants. The role setting unit can allow the generation AI to set roles based on the geographical location information of the conference participants. For example, the role setting unit can set a remote participant to an online questioner role. The role setting unit can also set a local participant to a role of providing local information. Furthermore, the role setting unit can also set a time manager role for a participant in a different time zone. In this way, roles appropriate for remote participants and local participants can be set by taking into account the geographical location information of the conference participants. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit can input geographical location information of the conference participants to the generation AI, and the generation AI can set roles based on that information.

[0042] The role setting unit can customize roles based on past feedback from conference participants. The role setting unit, for example, customizes roles based on past feedback from conference participants. The role setting unit can allow the generation AI to customize roles based on past feedback from conference participants. For example, the role setting unit re-sets roles that were well-received in past conferences. The role setting unit can also set new roles to fill in roles that were lacking in past conferences. Furthermore, the role setting unit can fine-tune the content of roles based on past feedback. This makes it possible to set more effective roles by reflecting past feedback from conference participants. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit can input past feedback from conference participants into the generation AI, and the generation AI can customize roles based on that feedback.

[0043] The role setting unit may include a system that dynamically changes role settings according to the purpose of the meeting. The role setting unit dynamically changes role settings according to, for example, the purpose of the meeting. In the role setting unit, the generation AI can dynamically change role settings according to the purpose of the meeting. For example, if a new problem arises during the progress of the meeting, the role setting unit may set a new role. In addition, if the purpose of the meeting changes, the role setting unit may also cause the generation AI to reassign roles. Furthermore, the role setting unit may cause the generation AI to change the priority of roles according to the progress of the meeting. This makes the progress of the meeting more flexible by dynamically changing role settings according to the purpose of the meeting. Some or all of the above-described processing in the role setting unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the role setting unit may input data to a generation AI that dynamically changes role settings according to the purpose of the meeting, and the generation AI may set the roles.

[0044] The participation unit can analyze the progress of the meeting in real time and make remarks. For example, the participation unit can analyze the progress of the meeting in real time and make remarks. For example, the participation unit can have a generation AI analyze the progress of the meeting in real time and make remarks at the appropriate time. For example, if the meeting is stagnating, the generation AI can raise a new agenda item. Also, if the meeting is progressing too quickly, the generation AI can make a remark summarizing the main points. Furthermore, if the meeting is chaotic, the generation AI can make a remark to organize the progress. In this way, by analyzing the progress of the meeting in real time, remarks can be made at the appropriate time. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can analyze the progress of the meeting in real time and input the information into the generation AI that makes the remarks, and the generation AI can make the remarks.

[0045] The participation unit may include a system that analyzes the content of statements made by meeting participants and provides relevant information. For example, the participation unit may analyze the content of statements made by meeting participants and provide relevant information. The participation unit may have a generation AI that analyzes the content of statements made by meeting participants and provides relevant information based on the content. For example, if a participant asks a technical question, the generation AI may provide relevant technical information. Furthermore, if a participant asks a marketing question, the generation AI may provide relevant marketing data. Furthermore, if a participant asks a question about the progress of a project, the generation AI may provide relevant progress data. This allows the content of statements made by meeting participants to be analyzed, providing relevant information and supporting the progress of the meeting. Some or all of the above-described processing in the participation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the participation unit may input the content of statements made by meeting participants into the generation AI, which may analyze the content and provide relevant information.

[0046] The participation unit may include a system that dynamically changes roles according to the progress of the conference. The participation unit dynamically changes roles according to the progress of the conference, for example. In the participation unit, the generation AI can dynamically change roles according to the progress of the conference. For example, if a new problem arises during the conference, the generation AI can set a new role. In addition, in the participation unit, if the purpose of the conference changes, the generation AI can also reassign roles. Furthermore, in the participation unit, the generation AI can change the priority of roles according to the progress of the conference. This makes the progress of the conference more flexible by dynamically changing roles according to the progress of the conference. Some or all of the above-described processing in the participation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the participation unit can input data to a generation AI that dynamically changes roles according to the progress of the conference, and the generation AI can set the roles.

[0047] The participation unit may include a system that customizes the content of utterances according to the expertise of the meeting participants. The participation unit, for example, customizes the content of utterances according to the expertise of the meeting participants. The participation unit allows a generation AI to customize the content of utterances according to the expertise of the meeting participants. For example, the participation unit may provide technical utterance content to a participant with technical expertise. The participation unit may also provide marketing-related utterance content to a participant with marketing expertise. The participation unit may also provide project management-related utterance content to a participant with project management expertise. This allows the progress of the meeting to be more effective by customizing the content of utterances according to the expertise of the meeting participants. Some or all of the above-described processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit may input the content of utterances into a generation AI that customizes the content of utterances according to the expertise of the meeting participants, and the generation AI may provide the content.

[0048] The participation unit may be equipped with a system that adjusts the order of comments according to the theme of the meeting. The participation unit adjusts the order of comments according to, for example, the theme of the meeting. The participation unit can have a generation AI adjust the order of comments according to the theme of the meeting. For example, the participation unit prioritizes technical comments in a meeting on a technical theme. The participation unit can also prioritize marketing-related comments in a meeting on a marketing theme. The participation unit can also prioritize project management-related comments in a meeting on a project management theme. In this way, adjusting the order of comments according to the theme of the meeting makes the meeting proceed more smoothly. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can input data to a generation AI that adjusts the order of comments according to the theme of the meeting, and the generation AI can adjust the order.

[0049] The participation unit may be equipped with a system that adjusts the frequency of speech depending on the progress of the meeting. The participation unit adjusts the frequency of speech depending on, for example, the progress of the meeting. In the participation unit, the generation AI can adjust the frequency of speech depending on the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of speech. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of speech. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of speech. In this way, adjusting the frequency of speech depending on the progress of the meeting makes the meeting progress more effective. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can input to a generation AI that adjusts the frequency of speech depending on the progress of the meeting, and the generation AI can adjust the frequency.

[0050] The input unit may include a system that automatically selects information to be input according to the theme of the meeting. The input unit automatically selects information to be input according to, for example, the theme of the meeting. The input unit can automatically select information to be input by the generation AI according to the theme of the meeting. For example, the input unit inputs technical information in a technical-themed meeting. The input unit can also input marketing information in a marketing-themed meeting. Furthermore, the input unit can input project management information in a project management-themed meeting. This makes it possible to provide information during meetings more effectively by automatically selecting information to be input according to the theme of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that automatically selects information to be input according to the theme of the meeting, and the generation AI can provide the information.

[0051] The input unit may include a system that customizes the information to be input based on the expertise of the meeting participants. The input unit customizes the information to be input based on, for example, the expertise of the meeting participants. The input unit can customize the information to be input by the generation AI based on the expertise of the meeting participants. For example, the input unit inputs technical information to a participant with technical expertise. The input unit can also input marketing information to a participant with marketing expertise. Furthermore, the input unit can input project management information to a participant with project management expertise. This allows the information to be customized based on the expertise of the meeting participants, thereby providing more appropriate information during the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input the information to be input to a generation AI that customizes the information to be input based on the expertise of the meeting participants, and the generation AI can provide the information.

[0052] The input unit may include a system that dynamically changes the information to be input depending on the progress of the meeting. The input unit dynamically changes the information to be input depending on, for example, the progress of the meeting. The input unit can dynamically change the information to be input by the generation AI depending on the progress of the meeting. For example, if a new problem arises during the progress of the meeting, the input unit inputs new information to the generation AI. The input unit can also reset the information to be input by the generation AI depending on the purpose of the meeting. Furthermore, the input unit can change the priority of the information to be input by the generation AI depending on the progress of the meeting. This allows for more flexible information provision during the meeting by dynamically changing the information to be input depending on the progress of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that dynamically changes the information to be input depending on the progress of the meeting, and the generation AI can provide the information.

[0053] The input unit can select information to be input based on the geographic location information of the conference participants. For example, the input unit selects information to be input based on the geographic location information of the conference participants. The input unit can select information to be input by the generation AI based on the geographic location information of the conference participants. For example, the input unit inputs online information for remote participants. The input unit can also input local information for on-site participants. Furthermore, the input unit can input time information for participants in different time zones. This makes it possible to provide information appropriate for remote participants and on-site participants by taking into account the geographic location information of the conference participants. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input geographic location information of the conference participants to the generation AI, and the generation AI can select information to be input based on that information.

[0054] The input unit may include a system that customizes the information to be input based on past feedback from the meeting participants. For example, the input unit customizes the information to be input based on past feedback from the meeting participants. The input unit can customize the information to be input by the generation AI based on past feedback from the meeting participants. For example, the input unit re-inputs information that was well received in past meetings. The input unit can also input new information to supplement information that was lacking in past meetings. Furthermore, the input unit can fine-tune the content of the information based on past feedback. This makes it possible to provide more effective information by reflecting the past feedback from the meeting participants. Some or all of the above-described processing in the input unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the input unit can input past feedback from the meeting participants into the generation AI, and the generation AI can customize the information based on that feedback.

[0055] The input unit may include a system that changes the format of the input information depending on the purpose of the meeting. The input unit changes the format of the input information depending on, for example, the purpose of the meeting. The input unit can change the format of the information input by the generation AI depending on the purpose of the meeting. For example, the input unit inputs technical information in text format in a technical meeting. The input unit can also input marketing information in graph format in a marketing meeting. Furthermore, the input unit can input project management information in table format in a project management meeting. This makes it possible to provide information more effectively during meetings by changing the format of the input information depending on the purpose of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that changes the format of the input information depending on the purpose of the meeting, and the generation AI can provide the information.

[0056] The supplemental explanation unit can analyze the progress of the meeting in real time and provide supplemental explanations. For example, the supplemental explanation unit can analyze the progress of the meeting in real time and provide supplemental explanations. The supplemental explanation unit can have the generation AI analyze the progress of the meeting in real time and provide supplemental explanations at appropriate times. For example, if the meeting is stagnating, the generation AI can provide supplemental explanations that provide new information. Also, if the meeting is progressing too quickly, the supplemental explanation unit can have the generation AI provide supplemental explanations that summarize the main points. Furthermore, if the meeting is chaotic, the generation AI can provide supplemental explanations that organize the progress. In this way, by analyzing the progress of the meeting in real time, supplemental explanations can be provided at appropriate times. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can analyze the progress of the meeting in real time and input the information to the generation AI that provides supplemental explanations, and the generation AI can provide the supplemental explanations.

[0057] The supplemental explanation unit may include a system that analyzes the content of statements made by meeting participants and provides related information. For example, the supplemental explanation unit may analyze the content of statements made by meeting participants and provide related information. The supplemental explanation unit may use a generation AI to analyze the content of statements made by meeting participants and provide related information based on the content. For example, if a participant asks a technical question, the generation AI may provide supplemental explanations providing related technical information. Furthermore, if a participant asks a marketing question, the generation AI may provide supplemental explanations providing related marketing data. Furthermore, if a participant asks a question about the progress of a project, the generation AI may provide supplemental explanations providing related progress data. This allows the analysis of the content of statements made by meeting participants to provide related information and support the progress of the meeting. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit may input the content of statements made by meeting participants into the generation AI, which may analyze the content and provide related information.

[0058] The supplemental explanation unit may include a system that dynamically changes the content of the supplemental explanation according to the theme of the meeting. The supplemental explanation unit dynamically changes the content of the supplemental explanation according to, for example, the theme of the meeting. In the supplemental explanation unit, the generation AI can dynamically change the content of the supplemental explanation according to the theme of the meeting. For example, the supplemental explanation unit provides technical supplemental explanations in a technical-themed meeting. The supplemental explanation unit can also provide marketing-related supplemental explanations in a marketing-related meeting. The supplemental explanation unit can also provide project management-related supplemental explanations in a project management-related meeting. By dynamically changing the content of the supplemental explanation according to the theme of the meeting, the supplemental explanation during the meeting becomes more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the supplemental explanation unit inputs the content of the supplemental explanation to a generation AI that dynamically changes the content of the supplemental explanation according to the theme of the meeting, and the generation AI can provide the content.

[0059] The supplemental explanation unit can customize the content of the supplemental explanation according to the expertise of the meeting participants. The supplemental explanation unit customizes the content of the supplemental explanation according to, for example, the expertise of the meeting participants. The supplemental explanation unit can customize the content of the supplemental explanation according to the expertise of the meeting participants using a generation AI. For example, the supplemental explanation unit can provide technical supplemental explanations to participants with technical expertise. The supplemental explanation unit can also provide marketing supplemental explanations to participants with marketing expertise. The supplemental explanation unit can also provide project management supplemental explanations to participants with project management expertise. In this way, customizing the content of the supplemental explanation according to the expertise of the meeting participants makes the supplemental explanation during the meeting more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can input the content of the supplemental explanation into a generation AI that customizes the content of the supplemental explanation according to the expertise of the meeting participants, and the generation AI can provide the content.

[0060] The supplemental explanation unit may include a system that adjusts the order of supplemental explanations according to the theme of the meeting. The supplemental explanation unit adjusts the order of supplemental explanations according to, for example, the theme of the meeting. The supplemental explanation unit can adjust the order of supplemental explanations according to the theme of the meeting using a generation AI. For example, the supplemental explanation unit prioritizes technical supplemental explanations in a meeting on a technical theme. The supplemental explanation unit can also prioritize marketing supplemental explanations in a meeting on a marketing theme. The supplemental explanation unit can also prioritize project management supplemental explanations in a meeting on a project management theme. In this way, by adjusting the order of supplemental explanations according to the theme of the meeting, the order of supplemental explanations during the meeting is more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can input data to a generation AI that adjusts the order of supplemental explanations according to the theme of the meeting, and the generation AI can adjust the order.

[0061] The supplemental explanation unit may include a system that adjusts the frequency of supplemental explanations according to the progress of the meeting. The supplemental explanation unit adjusts the frequency of supplemental explanations according to, for example, the progress of the meeting. In the supplemental explanation unit, the generation AI can adjust the frequency of supplemental explanations according to the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of supplemental explanations. Also, if the meeting is progressing too quickly, the supplemental explanation unit can decrease the frequency of supplemental explanations. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of supplemental explanations. In this way, by adjusting the frequency of supplemental explanations according to the progress of the meeting, supplemental explanations during the meeting are provided at a more appropriate frequency. Some or all of the above-described processing in the supplemental explanation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the supplemental explanation unit can input data to a generation AI that adjusts the frequency of supplemental explanations according to the progress of the meeting, and the generation AI can adjust the frequency.

[0062] The minutes-taking unit can analyze the progress of a meeting in real time and create minutes. The minutes-taking unit, for example, analyzes the progress of a meeting in real time and creates minutes. The minutes-taking unit can have the generation AI analyze the progress of a meeting in real time and create minutes at the appropriate time. For example, if the meeting is stagnating, the generation AI can create minutes to encourage progress. Also, if the meeting is progressing too quickly, the minutes-taking unit can create minutes that summarize the main points. Furthermore, if the meeting is chaotic, the generation AI can create minutes that organize the progress. In this way, by analyzing the progress of a meeting in real time, minutes can be created at the appropriate time. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking section can analyze the progress of a meeting in real time and input the information into a generation AI that creates minutes, which then creates the minutes.

[0063] The minutes-taking unit may include a system that analyzes the remarks made by meeting participants and reflects related information in the minutes. For example, the minutes-taking unit analyzes the remarks made by meeting participants and reflects related information in the minutes. The minutes-taking unit may use a generation AI to analyze the remarks made by meeting participants and reflect related information in the minutes based on the analyzed remarks. For example, if a participant asks a technical question, the generation AI may reflect related technical information in the minutes. Furthermore, if a participant asks a marketing question, the generation AI may reflect related marketing data in the minutes. Furthermore, if a participant asks a question about the progress of a project, the generation AI may reflect related progress data in the minutes. This allows the remarks made by meeting participants to be analyzed, thereby reflecting related information in the minutes and resulting in a more accurate record of the meeting. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the minutes-taking department can input the remarks made by meeting participants into the generation AI, which can then analyze the content and reflect relevant information in the minutes.

[0064] The minutes-taking unit may be equipped with a system that dynamically changes the content of the minutes according to the theme of the meeting. The minutes-taking unit dynamically changes the content of the minutes according to, for example, the theme of the meeting. In the minutes-taking unit, the generation AI can dynamically change the content of the minutes according to the theme of the meeting. For example, the minutes-taking unit creates technical minutes for a technical-themed meeting. The minutes-taking unit can also create marketing-related minutes for a marketing-related meeting. The minutes-taking unit can also create project management-related minutes for a project management-related meeting. Dynamically changing the content of the minutes according to the theme of the meeting makes the meeting record more appropriate. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can input the content of the minutes to a generation AI that dynamically changes the content of the minutes according to the theme of the meeting, and the generation AI can provide the content.

[0065] The minutes-taking unit may include a system that customizes the content of the minutes according to the expertise of the meeting participants. The minutes-taking unit customizes the content of the minutes according to, for example, the expertise of the meeting participants. The minutes-taking unit can use a generation AI to customize the content of the minutes according to the expertise of the meeting participants. For example, the minutes-taking unit can create technical minutes for participants with technical expertise. The minutes-taking unit can also create marketing-related minutes for participants with marketing expertise. The minutes-taking unit can also create project management-related minutes for participants with project management expertise. This allows the content of the minutes to be customized according to the expertise of the meeting participants, resulting in more appropriate meeting records. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using or without the generation AI. For example, the minutes-taking unit can input data to a generation AI that customizes the content of the minutes according to the expertise of the meeting participants, and the generation AI can provide the content.

[0066] The minutes-taking unit may be equipped with a system that adjusts the order of the minutes according to the theme of the meeting. The minutes-taking unit adjusts the order of the minutes according to, for example, the theme of the meeting. The minutes-taking unit can adjust the order of the minutes according to the theme of the meeting using a generation AI. For example, the minutes-taking unit may prioritize technical minutes in a meeting on a technical theme. The minutes-taking unit may also prioritize marketing-related minutes in a meeting on a marketing theme. The minutes-taking unit may also prioritize project management-related minutes in a meeting on a project management theme. By adjusting the order of the minutes according to the theme of the meeting, the meeting record is recorded in a more appropriate order. Some or all of the above-described processing in the minutes-taking unit may be performed using, or without, the generation AI. For example, the minutes-taking unit may input the minutes to a generation AI that adjusts the order of the minutes according to the theme of the meeting, and the generation AI may adjust the order.

[0067] The minutes-taking unit may be equipped with a system that adjusts the frequency of minutes according to the progress of the meeting. The minutes-taking unit adjusts the frequency of minutes according to, for example, the progress of the meeting. In the minutes-taking unit, the generation AI can adjust the frequency of minutes according to the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of minutes. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of minutes. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of minutes. In this way, adjusting the frequency of minutes according to the progress of the meeting ensures that the meeting is recorded at a more appropriate frequency. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can input data to a generation AI that adjusts the frequency of minutes according to the progress of the meeting, and the generation AI can adjust the frequency.

[0068] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0069] The meeting support system can further include an information providing unit that analyzes the content of statements made by meeting participants in real time and provides related information. For example, when a participant asks a technical question, the generation AI can provide related technical information. Also, when a participant asks a marketing question, the generation AI can provide related marketing data. Furthermore, when a participant asks about the progress of a project, the generation AI can provide related progress data. In this way, by analyzing the content of statements made by meeting participants, related information can be provided and the progress of the meeting can be supported.

[0070] The meeting support system can further include a speech adjustment unit that analyzes the progress of the meeting in real time and adjusts the timing of remarks. For example, if the meeting is stalling, the generation AI will raise a new agenda item. Also, if the meeting is progressing too quickly, the generation AI can make a statement summarizing the main points. Furthermore, if the meeting is chaotic, the generation AI can make a statement to organize the progress. In this way, by analyzing the progress of the meeting in real time, it is possible to make a statement at the appropriate time.

[0071] The conference support system can further include a utterance customization unit that customizes the content of utterances based on the expertise of conference participants. For example, the utterance customization unit can provide technical utterances to a participant with technical expertise. It can also provide marketing-related utterances to a participant with marketing expertise. It can also provide project management-related utterances to a participant with project management expertise. In this way, the utterance content can be customized according to the expertise of conference participants, making the conference proceed more effective.

[0072] The conference support system can further include a speech order adjustment unit that adjusts the order of comments depending on the conference theme. For example, the speech order adjustment unit can prioritize technical comments in a conference on a technical theme. It can also prioritize marketing-related comments in a conference on a marketing theme. It can also prioritize project management-related comments in a conference on a project management theme. In this way, adjusting the order of comments depending on the conference theme makes the conference proceed more smoothly.

[0073] The meeting support system can further include a speech frequency adjustment unit that adjusts the frequency of speech depending on the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of speech. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of speech. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of speech. In this way, adjusting the frequency of speech depending on the progress of the meeting makes the meeting proceed more effectively.

[0074] The processing flow of the first embodiment will be briefly explained below.

[0075] Step 1: The role setting unit sets roles before the meeting. For example, a role to raise questions or a role to provide supplementary explanations. The role setting unit can set roles for the generation AI to raise questions or provide supplementary explanations at appropriate times during the meeting. It can also set roles for the generation AI to support the progress of the meeting. Step 2: The participants join the meeting based on the roles set by the role setting unit. The participants can ask questions or provide supplementary explanations during the meeting. The generation AI can also support the progress of the meeting. Step 3: The input unit inputs the meeting content in advance. The input unit can input background information and related data about the meeting agenda into the generation AI. It can also input information that will enable the generation AI to provide appropriate supplementary explanations during the meeting. Step 4: The supplementary explanation unit provides supplementary explanations during the meeting based on the information input by the input unit. The supplementary explanation unit allows the generation AI to provide supplementary explanations based on background information and related data on the meeting agenda. The generation AI can also provide appropriate answers to questions from participants during the meeting. Step 5: The minutes-taking unit automatically compiles the minutes of the meeting. The minutes-taking unit allows the generation AI to record the contents of the meeting and create minutes. The generation AI can also provide the minutes to participants after the meeting has ended.

[0076] (Example 2) A meeting support system according to an embodiment of the present invention uses a generation AI to participate in meetings and enhance the quality of the meetings. The meeting support system assigns roles to the generation AI before the meeting, and the generation AI participates in the meeting based on the assigned roles. For example, the role of posing questions or providing supplementary explanations can be assigned. Furthermore, by inputting the meeting content in advance, the generation AI can provide appropriate supplementary explanations. Furthermore, the system automatically compiles meeting minutes and reviews the content of the previous meeting. It is also possible to summarize next-level actions based on the meeting content. Furthermore, the system translates the meeting content in real time and automatically adjusts each participant's schedule. This eliminates language barriers and allows the meeting to proceed smoothly. For example, the meeting support system assigns roles to the generation AI before the meeting. For example, the role of posing questions or providing supplementary explanations can be assigned. This allows the generation AI to pose questions or provide supplementary explanations at appropriate times during the meeting. Next, the meeting content is input into the generation AI in advance. This allows the generation AI to provide appropriate supplementary explanations during the meeting. For example, by inputting background information and related data about a meeting's agenda into the generation AI, the generation AI can provide supplementary explanations based on that information during the meeting. Furthermore, the generation AI automatically compiles meeting minutes. After the meeting, the generation AI creates minutes and provides them to participants. This ensures that the meeting content is accurately recorded and can be referenced later. The generation AI also has a function to review the content of the previous meeting. At the beginning of the meeting, the generation AI briefly reviews the content of the previous meeting and shares it with participants. This allows the meeting to proceed smoothly without forgetting the content of the previous meeting. Furthermore, the generation AI can summarize the next action based on the meeting content. After the meeting ends, the generation AI lists the next action and provides it to participants. This allows specific actions to be planned for the next meeting. The generation AI also translates the meeting content in real time and automatically adjusts each person's schedule. This breaks down language barriers and allows meetings to proceed smoothly. For example, if there are participants who speak different languages, the generation AI translates the meeting content in real time and provides it to participants.The generation AI also automatically adjusts the meeting schedule, aligning the schedules of all participants. This makes the meeting support system a hero for realizing productive meetings. By using the generation AI, it is possible to improve the quality of meetings and realize meetings that satisfy all participants.

[0077] A meeting support system according to an embodiment includes a role setting unit, a participation unit, an input unit, a supplemental explanation unit, and a minutes creation unit. The role setting unit sets roles before a meeting. For example, the role may be a role for raising questions or a role for providing supplemental explanations. For example, the role setting unit may set a role for the generation AI to raise questions or provide supplemental explanations at appropriate times during the meeting. The role setting unit may also set a role for the generation AI to support the progress of the meeting. The participation unit participates in the meeting based on the role set by the role setting unit. For example, the participation unit may allow the generation AI to raise questions or provide supplemental explanations during the meeting. The participation unit may also support the generation AI in the progress of the meeting. The input unit inputs the content of the meeting in advance. For example, the input unit may input background information and related data related to the meeting agenda to the generation AI. The input unit may also input information for the generation AI to provide appropriate supplemental explanations during the meeting. The supplementary explanation unit provides supplementary explanations during the meeting based on the information input by the input unit. For example, the supplementary explanation unit enables the generation AI to provide supplementary explanations based on background information and related data regarding the meeting agenda. The supplementary explanation unit also enables the generation AI to provide appropriate answers to participants' questions during the meeting. The minutes-taking unit automatically compiles meeting minutes. For example, the generation AI can record the contents of the meeting and create the minutes. The minutes-taking unit can also enable the generation AI to provide the minutes to participants after the meeting ends. As a result, the meeting support system according to the embodiment can improve the quality of the meeting by setting roles before the meeting and providing appropriate supplementary explanations and creating minutes during the meeting. For example, the meeting support system can set roles in the generation AI before the meeting and raise questions or provide supplementary explanations at appropriate times during the meeting. The meeting support system can also input the contents of the meeting into the generation AI in advance and provide appropriate supplementary explanations during the meeting. Furthermore, the meeting support system can automatically compile minutes of the meeting and provide them to participants after the meeting has ended.As a result, the conference support system can improve the quality of the conference and realize a conference that satisfies all participants.

[0078] The minutes-taking unit can create minutes after the meeting ends and send them to participants by email. For example, after the meeting ends, the generation AI can create minutes and send them to participants by email. In the minutes-taking unit, the generation AI records the contents of the meeting and creates minutes. For example, the minutes-taking unit can create minutes including summaries of each agenda item, a record of speakers, and a list of action items. In the minutes-taking unit, the generation AI also sends the minutes by email. For example, the minutes-taking unit can automatically create minutes after the meeting ends and send them to participants by email. In this way, by creating minutes after the meeting ends and providing them to participants, the contents of the meeting can be accurately recorded and can be referenced later. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can record the contents of the meeting and input them into a generation AI that creates minutes, and the generation AI can create the minutes and send them by email.

[0079] The supplemental explanation unit can provide supplemental explanations based on background information and related data related to the meeting agenda. The supplemental explanation unit can provide supplemental explanations based on, for example, background information and related data related to the meeting agenda. The supplemental explanation unit can provide supplemental explanations based on, for example, background information and related data related to the meeting agenda by the generation AI. For example, the supplemental explanation unit can provide background information related to the meeting agenda by the generation AI to deepen participants' understanding. The supplemental explanation unit can also provide data related to the meeting agenda by the generation AI to deepen participants' understanding. In this way, by providing supplemental explanations based on background information and related data related to the meeting agenda, it is possible to deepen participants' understanding of the meeting. Some or all of the above-mentioned processing in the supplemental explanation unit can be performed using, or without, the generation AI. For example, the supplemental explanation unit can input background information and related data related to the meeting agenda into the generation AI, and the generation AI can provide supplemental explanations.

[0080] The role setting unit can set a role of posing a question or a role of providing supplementary explanation. The role setting unit, for example, sets a role of posing a question or a role of providing supplementary explanation. The role setting unit can set a role for the generation AI to pose a question or provide supplementary explanation at an appropriate time during the meeting. For example, the role setting unit can also set a role for the generation AI to support the progress of the meeting. In this way, by setting a role of posing a question or a role of providing supplementary explanation, questions or supplementary explanations can be given at an appropriate time during the meeting. Some or all of the above-described processing in the role setting unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the role setting unit sets a role of posing a question or a role of providing supplementary explanation to the generation AI, and the generation AI can play that role during the meeting.

[0081] The participation unit can raise questions or provide supplementary explanations during a meeting based on a set role. For example, the participation unit raises questions or provides supplementary explanations during a meeting based on a set role. The participation unit can have the generation AI raise questions or provide supplementary explanations at appropriate times during the meeting. For example, the participation unit can also have the generation AI support the progress of the meeting. This allows questions or supplementary explanations to be asked at appropriate times during the meeting based on a set role, thereby making it possible to smoothly progress the meeting. Some or all of the above-described processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit inputs data to a generation AI that raises questions or provides supplementary explanations during a meeting based on a set role, and the generation AI can fulfill its role.

[0082] The minutes-taking unit may have a function to summarize and display the contents of the previous meeting. The minutes-taking unit may, for example, have a function to summarize and display the contents of the previous meeting. In the minutes-taking unit, the generation AI may summarize the contents of the previous meeting and display it to participants at the beginning of the meeting. For example, the minutes-taking unit may have the generation AI briefly review the contents of the previous meeting and share it with participants. By reviewing the contents of the previous meeting, participants can avoid forgetting the contents of the previous meeting and the meeting can proceed smoothly. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit may input the contents of the previous meeting into a generation AI that summarizes and displays them, and the generation AI may display the contents.

[0083] The minutes-taking unit can list the next actions and send them to the participants by email. The minutes-taking unit, for example, lists the next actions and sends them to the participants by email. The minutes-taking unit can have the generation AI list the next actions based on the content of the meeting and provide them to the participants. For example, the minutes-taking unit can have the generation AI list the next actions after the end of the meeting and send them by email to the participants. By listing the next actions and providing them to the participants, specific actions can be planned for the next meeting. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can list the next actions and input them into the generation AI, which sends them to the participants by email, and the generation AI then sends the content.

[0084] The supplementary explanation unit can translate and display the contents of the meeting in real time. For example, the supplementary explanation unit can translate and display the contents of the meeting in real time. The supplementary explanation unit can have the generation AI translate the contents of the meeting in real time and provide it to participants. For example, the supplementary explanation unit can have the generation AI translate and display the contents of the meeting in real time for participants who speak different languages. By translating the contents of the meeting in real time, participants who speak different languages ​​can smoothly participate in the meeting. Some or all of the above-mentioned processing in the supplementary explanation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the supplementary explanation unit can input the contents of the meeting to a generation AI that translates and displays the contents in real time, and the generation AI can translate and display the contents.

[0085] The input unit can be equipped with a system that automatically adjusts each person's schedule. The input unit, for example, is equipped with a system that automatically adjusts each person's schedule. In the input unit, the generation AI can automatically adjust each person's schedule and set a meeting schedule. For example, in the input unit, the generation AI can automatically adjust the schedules of all participants and set a meeting schedule. This makes it possible to automatically adjust each person's schedule, thereby making meeting schedule adjustment more efficient. Some or all of the above-mentioned processing in the input unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the input unit can input each person's schedule into the generation AI, and the generation AI can adjust the schedule.

[0086] The role setting unit can estimate the user's emotions and set an optimal role based on the estimated user's emotions. The role setting unit, for example, estimates the user's emotions and sets an optimal role based on the estimated user's emotions. The role setting unit can use a generation AI to estimate the user's emotions and set an optimal role based on the emotions. For example, if the user is nervous, the role setting unit can set the generation AI to a supporting role to help the user relax. Furthermore, if the user is excited, the role setting unit can set the generation AI to a role to calmly support the user in the meeting. Furthermore, if the user is tired, the role setting unit can set the generation AI to a role to succinctly summarize the main points. Thus, by setting an optimal role based on the user's emotions, the allocation of roles during a meeting becomes more appropriate. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the role setting unit may be performed using, for example, the generation AI, or without the generation AI. For example, the role setting unit can estimate the user's emotions, input the estimated emotions into a generation AI that sets an optimal role based on the emotions, and the generation AI can then set the role.

[0087] The role setting unit may include a system that analyzes past meeting data and automatically proposes roles according to the purpose of the meeting. The role setting unit, for example, analyzes past meeting data and automatically proposes roles according to the purpose of the meeting. The role setting unit can use a generation AI to analyze past meeting data and automatically propose roles according to the purpose of the meeting based on the data. For example, the role setting unit may assign a questioner based on questions that frequently came up in past meetings. The role setting unit may also assign a supplementary explanation role to supplement information that was lacking in past meetings. Furthermore, the role setting unit may assign a time management role for topics that were discussed prolongedly in past meetings. In this way, by analyzing past meeting data, optimal roles according to the purpose of the meeting can be automatically proposed. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit may input past meeting data into the generation AI, which may analyze the data and propose roles according to the purpose of the meeting.

[0088] The role setting unit may include a system that customizes roles based on the expertise and titles of meeting participants. The role setting unit customizes roles based on, for example, the expertise and titles of meeting participants. The role setting unit allows a generation AI to customize roles based on the expertise and titles of meeting participants. For example, the role setting unit assigns a role to answer technical questions to a participant with specialized knowledge. The role setting unit can also assign a role to support the progress of the meeting to a participant with a higher title. Furthermore, the role setting unit can assign a role to ask questions for learning purposes to a new employee. In this way, customizing roles based on the expertise and titles of meeting participants makes the progress of the meeting smoother. Some or all of the above-described processing in the role setting unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the role setting unit inputs data into a generation AI that customizes roles based on the expertise and titles of meeting participants, and the generation AI can set the roles.

[0089] The role setting unit may include a system that sets multiple roles in combination according to the theme of the meeting. The role setting unit sets multiple roles in combination according to, for example, the theme of the meeting. The role setting unit allows the generation AI to set multiple roles in combination according to the theme of the meeting. For example, the role setting unit sets a technical questioner and a technical supplementary explanation role in a meeting on a technical theme. The role setting unit can also set a progress manager and a risk manager role in a meeting on project progress. Furthermore, the role setting unit can also set a marketing questioner and a technical supplementary explanation role in a meeting on a new product. In this way, by combining multiple roles according to the theme of the meeting, the progress of the meeting becomes more effective. Some or all of the above-described processing in the role setting unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the role setting unit inputs the information into a generation AI that sets multiple roles in combination according to the theme of the meeting, and the generation AI can set the roles.

[0090] The role setting unit can estimate the user's emotions and determine the priority of roles based on the estimated user's emotions. For example, the role setting unit can estimate the user's emotions and determine the priority of roles based on the estimated user's emotions. The role setting unit can use a generation AI to estimate the user's emotions and determine the priority of roles based on the emotions. For example, if the user is nervous, the role setting unit can prioritize a role that helps the user relax. Also, if the user is excited, the role setting unit can prioritize a role that calmly supports the progress of the meeting. Furthermore, if the user is tired, the role setting unit can prioritize a role that succinctly summarizes the main points. Thus, determining the priority of roles based on the user's emotions results in more appropriate role allocation during a meeting. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the role setting unit can be performed using, for example, the generation AI, or without the generation AI. For example, the role setting unit can estimate the user's emotions, input the emotions into a generation AI that determines the priority of roles based on the emotions, and the generation AI can set the roles.

[0091] The role setting unit can set roles based on geographical location information of the conference participants. The role setting unit, for example, sets roles based on geographical location information of the conference participants. The role setting unit can allow the generation AI to set roles based on the geographical location information of the conference participants. For example, the role setting unit can set a remote participant to an online questioner role. The role setting unit can also set a local participant to a role of providing local information. Furthermore, the role setting unit can also set a time manager role for a participant in a different time zone. In this way, roles appropriate for remote participants and local participants can be set by taking into account the geographical location information of the conference participants. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit can input geographical location information of the conference participants to the generation AI, and the generation AI can set roles based on that information.

[0092] The role setting unit can customize roles based on past feedback from conference participants. The role setting unit, for example, customizes roles based on past feedback from conference participants. The role setting unit can allow the generation AI to customize roles based on past feedback from conference participants. For example, the role setting unit re-sets roles that were well-received in past conferences. The role setting unit can also set new roles to fill in roles that were lacking in past conferences. Furthermore, the role setting unit can fine-tune the content of roles based on past feedback. This makes it possible to set more effective roles by reflecting past feedback from conference participants. Some or all of the above-described processing in the role setting unit may be performed using, or without, the generation AI. For example, the role setting unit can input past feedback from conference participants into the generation AI, and the generation AI can customize roles based on that feedback.

[0093] The role setting unit may include a system that dynamically changes role settings according to the purpose of the meeting. The role setting unit dynamically changes role settings according to, for example, the purpose of the meeting. In the role setting unit, the generation AI can dynamically change role settings according to the purpose of the meeting. For example, if a new problem arises during the progress of the meeting, the role setting unit may set a new role. In addition, if the purpose of the meeting changes, the role setting unit may also cause the generation AI to reassign roles. Furthermore, the role setting unit may cause the generation AI to change the priority of roles according to the progress of the meeting. This makes the progress of the meeting more flexible by dynamically changing role settings according to the purpose of the meeting. Some or all of the above-described processing in the role setting unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the role setting unit may input data to a generation AI that dynamically changes role settings according to the purpose of the meeting, and the generation AI may set the roles.

[0094] The participation unit may include a system that estimates a user's emotions and adjusts the timing of speech during a meeting based on the estimated user emotions. The participation unit, for example, estimates a user's emotions and adjusts the timing of speech during a meeting based on the estimated user emotions. The participation unit can use a generation AI to estimate a user's emotions and adjust the timing of speech during a meeting based on the user's emotions. For example, if the user is nervous, the participation unit adjusts the timing of speech so that the generation AI relaxes the user. Furthermore, if the user is excited, the participation unit can adjust the timing of speech so that the generation AI calmly supports the progress of the meeting. Furthermore, if the user is tired, the participation unit can adjust the timing of speech so that the generation AI succinctly summarizes the main points. Adjusting the timing of speech based on the user's emotions allows speech during a meeting to be more appropriately timed. Emotion estimation is achieved using an emotion estimation function, for example, using 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 these examples. Some or all of the above-described processing in the participation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the participation unit can estimate the user's emotions and input them into a generation AI that adjusts the timing of speech based on those emotions, and the generation AI can then adjust the timing.

[0095] The participation unit can analyze the progress of the meeting in real time and make remarks. For example, the participation unit can analyze the progress of the meeting in real time and make remarks. For example, the participation unit can have a generation AI analyze the progress of the meeting in real time and make remarks at the appropriate time. For example, if the meeting is stagnating, the generation AI can raise a new agenda item. Also, if the meeting is progressing too quickly, the generation AI can make a remark summarizing the main points. Furthermore, if the meeting is chaotic, the generation AI can make a remark to organize the progress. In this way, by analyzing the progress of the meeting in real time, remarks can be made at the appropriate time. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can analyze the progress of the meeting in real time and input the information into the generation AI that makes the remarks, and the generation AI can make the remarks.

[0096] The participation unit may include a system that analyzes the content of statements made by meeting participants and provides relevant information. For example, the participation unit may analyze the content of statements made by meeting participants and provide relevant information. The participation unit may have a generation AI that analyzes the content of statements made by meeting participants and provides relevant information based on the content. For example, if a participant asks a technical question, the generation AI may provide relevant technical information. Furthermore, if a participant asks a marketing question, the generation AI may provide relevant marketing data. Furthermore, if a participant asks a question about the progress of a project, the generation AI may provide relevant progress data. This allows the content of statements made by meeting participants to be analyzed, providing relevant information and supporting the progress of the meeting. Some or all of the above-described processing in the participation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the participation unit may input the content of statements made by meeting participants into the generation AI, which may analyze the content and provide relevant information.

[0097] The participation unit may include a system that dynamically changes roles according to the progress of the conference. The participation unit dynamically changes roles according to the progress of the conference, for example. In the participation unit, the generation AI can dynamically change roles according to the progress of the conference. For example, if a new problem arises during the conference, the generation AI can set a new role. In addition, in the participation unit, if the purpose of the conference changes, the generation AI can also reassign roles. Furthermore, in the participation unit, the generation AI can change the priority of roles according to the progress of the conference. This makes the progress of the conference more flexible by dynamically changing roles according to the progress of the conference. Some or all of the above-described processing in the participation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the participation unit can input data to a generation AI that dynamically changes roles according to the progress of the conference, and the generation AI can set the roles.

[0098] The participation unit may include a system that estimates a user's emotions and adjusts the content of utterances based on the estimated user emotions. For example, the participation unit estimates a user's emotions and adjusts the content of utterances based on the estimated user emotions. The participation unit may use a generation AI to estimate a user's emotions and adjust the content of utterances based on the emotions. For example, if the user is nervous, the participation unit may adjust the content of utterances to help the generation AI relax the user. Furthermore, if the user is excited, the participation unit may adjust the content of utterances to calmly support the progress of the meeting. Furthermore, if the user is tired, the participation unit may adjust the content of utterances to succinctly summarize the main points. Adjusting the content of utterances based on the user's emotions results in more appropriate utterances during the meeting. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the participation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the participation unit can estimate the user's emotions and input them into a generation AI that adjusts the content of the utterance based on those emotions, and the generation AI can then adjust the content.

[0099] The participation unit may include a system that customizes the content of utterances according to the expertise of the meeting participants. The participation unit, for example, customizes the content of utterances according to the expertise of the meeting participants. The participation unit allows a generation AI to customize the content of utterances according to the expertise of the meeting participants. For example, the participation unit may provide technical utterance content to a participant with technical expertise. The participation unit may also provide marketing-related utterance content to a participant with marketing expertise. The participation unit may also provide project management-related utterance content to a participant with project management expertise. This allows the progress of the meeting to be more effective by customizing the content of utterances according to the expertise of the meeting participants. Some or all of the above-described processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit may input the content of utterances into a generation AI that customizes the content of utterances according to the expertise of the meeting participants, and the generation AI may provide the content.

[0100] The participation unit may be equipped with a system that adjusts the order of comments according to the theme of the meeting. The participation unit adjusts the order of comments according to, for example, the theme of the meeting. The participation unit can have a generation AI adjust the order of comments according to the theme of the meeting. For example, the participation unit prioritizes technical comments in a meeting on a technical theme. The participation unit can also prioritize marketing-related comments in a meeting on a marketing theme. The participation unit can also prioritize project management-related comments in a meeting on a project management theme. In this way, adjusting the order of comments according to the theme of the meeting makes the meeting proceed more smoothly. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can input data to a generation AI that adjusts the order of comments according to the theme of the meeting, and the generation AI can adjust the order.

[0101] The participation unit may be equipped with a system that adjusts the frequency of speech depending on the progress of the meeting. The participation unit adjusts the frequency of speech depending on, for example, the progress of the meeting. In the participation unit, the generation AI can adjust the frequency of speech depending on the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of speech. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of speech. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of speech. In this way, adjusting the frequency of speech depending on the progress of the meeting makes the meeting progress more effective. Some or all of the above-mentioned processing in the participation unit may be performed using, or without, the generation AI. For example, the participation unit can input to a generation AI that adjusts the frequency of speech depending on the progress of the meeting, and the generation AI can adjust the frequency.

[0102] The input unit may include a system that estimates a user's emotions and prioritizes information to be input based on the estimated user emotions. The input unit, for example, estimates a user's emotions and prioritizes information to be input based on the estimated user emotions. The input unit may also have a generation AI estimate a user's emotions and prioritize information to be input based on the estimated emotions. For example, if the user is nervous, the input unit may prioritize information that helps the generation AI relax. Furthermore, if the user is excited, the input unit may prioritize information that helps the generation AI calmly proceed. Furthermore, if the user is tired, the input unit may prioritize information that succinctly summarizes the main points. This allows for more appropriate information provision during meetings by prioritizing information to be input based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the input unit may estimate the user's emotions and input the information to a generation AI that determines the priority of information to be input based on the emotions, and the generation AI may provide the information.

[0103] The input unit may include a system that automatically selects information to be input according to the theme of the meeting. The input unit automatically selects information to be input according to, for example, the theme of the meeting. The input unit can automatically select information to be input by the generation AI according to the theme of the meeting. For example, the input unit inputs technical information in a technical-themed meeting. The input unit can also input marketing information in a marketing-themed meeting. Furthermore, the input unit can input project management information in a project management-themed meeting. This makes it possible to provide information during meetings more effectively by automatically selecting information to be input according to the theme of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that automatically selects information to be input according to the theme of the meeting, and the generation AI can provide the information.

[0104] The input unit may include a system that customizes the information to be input based on the expertise of the meeting participants. The input unit customizes the information to be input based on, for example, the expertise of the meeting participants. The input unit can customize the information to be input by the generation AI based on the expertise of the meeting participants. For example, the input unit inputs technical information to a participant with technical expertise. The input unit can also input marketing information to a participant with marketing expertise. Furthermore, the input unit can input project management information to a participant with project management expertise. This allows the information to be customized based on the expertise of the meeting participants, thereby providing more appropriate information during the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input the information to be input to a generation AI that customizes the information to be input based on the expertise of the meeting participants, and the generation AI can provide the information.

[0105] The input unit may include a system that dynamically changes the information to be input depending on the progress of the meeting. The input unit dynamically changes the information to be input depending on, for example, the progress of the meeting. The input unit can dynamically change the information to be input by the generation AI depending on the progress of the meeting. For example, if a new problem arises during the progress of the meeting, the input unit inputs new information to the generation AI. The input unit can also reset the information to be input by the generation AI depending on the purpose of the meeting. Furthermore, the input unit can change the priority of the information to be input by the generation AI depending on the progress of the meeting. This allows for more flexible information provision during the meeting by dynamically changing the information to be input depending on the progress of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that dynamically changes the information to be input depending on the progress of the meeting, and the generation AI can provide the information.

[0106] The input unit may include a system that estimates a user's emotions and adjusts the amount of information to be input based on the estimated user emotions. For example, the input unit estimates a user's emotions and adjusts the amount of information to be input based on the estimated user emotions. The input unit allows the generation AI to estimate a user's emotions and adjust the amount of information to be input based on the user's emotions. For example, if the user is nervous, the input unit adjusts the amount of information to help the generation AI relax. Furthermore, if the user is excited, the input unit can adjust the amount of information to help the generation AI calmly proceed. Furthermore, if the user is tired, the input unit can adjust the amount of information to succinctly summarize the main points. Adjusting the amount of information to be input based on the user's emotions improves the accuracy of information provided during meetings. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the input unit may be performed using, for example, a generation AI. For example, the input unit may estimate the user's emotions and input them to a generation AI that adjusts the amount of information to be input based on those emotions, and the generation AI may provide that information.

[0107] The input unit can select information to be input based on the geographic location information of the conference participants. For example, the input unit selects information to be input based on the geographic location information of the conference participants. The input unit can select information to be input by the generation AI based on the geographic location information of the conference participants. For example, the input unit inputs online information for remote participants. The input unit can also input local information for on-site participants. Furthermore, the input unit can input time information for participants in different time zones. This makes it possible to provide information appropriate for remote participants and on-site participants by taking into account the geographic location information of the conference participants. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input geographic location information of the conference participants to the generation AI, and the generation AI can select information to be input based on that information.

[0108] The input unit may include a system that customizes the information to be input based on past feedback from the meeting participants. For example, the input unit customizes the information to be input based on past feedback from the meeting participants. The input unit can customize the information to be input by the generation AI based on past feedback from the meeting participants. For example, the input unit re-inputs information that was well received in past meetings. The input unit can also input new information to supplement information that was lacking in past meetings. Furthermore, the input unit can fine-tune the content of the information based on past feedback. This makes it possible to provide more effective information by reflecting the past feedback from the meeting participants. Some or all of the above-described processing in the input unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the input unit can input past feedback from the meeting participants into the generation AI, and the generation AI can customize the information based on that feedback.

[0109] The input unit may include a system that changes the format of the input information depending on the purpose of the meeting. The input unit changes the format of the input information depending on, for example, the purpose of the meeting. The input unit can change the format of the information input by the generation AI depending on the purpose of the meeting. For example, the input unit inputs technical information in text format in a technical meeting. The input unit can also input marketing information in graph format in a marketing meeting. Furthermore, the input unit can input project management information in table format in a project management meeting. This makes it possible to provide information more effectively during meetings by changing the format of the input information depending on the purpose of the meeting. Some or all of the above-described processing in the input unit may be performed using, or without, the generation AI. For example, the input unit can input information to a generation AI that changes the format of the input information depending on the purpose of the meeting, and the generation AI can provide the information.

[0110] The supplemental explanation unit may include a system that estimates the user's emotions and adjusts the content of the supplemental explanation based on the estimated user emotions. For example, the supplemental explanation unit estimates the user's emotions and adjusts the content of the supplemental explanation based on the estimated user emotions. The supplemental explanation unit may use a generation AI to estimate the user's emotions and adjust the content of the supplemental explanation based on the user's emotions. For example, if the supplemental explanation unit is nervous, the generation AI may provide supplemental explanation to relax the user. Furthermore, if the user is excited, the generation AI may provide supplemental explanation to calmly support the progress of the meeting. Furthermore, if the user is tired, the generation AI may provide supplemental explanation that succinctly summarizes the main points. Adjusting the content of the supplemental explanation based on the user's emotions makes the supplemental explanation during the meeting more appropriate. Emotion estimation is achieved using an emotion estimation function, for example, using 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 these examples. Some or all of the above-described processing in the supplemental explanation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the supplementary explanation unit can estimate the user's emotions and input the estimated emotions into a generation AI that adjusts the content of the supplementary explanation based on the emotions, and the generation AI can provide the content.

[0111] The supplemental explanation unit can analyze the progress of the meeting in real time and provide supplemental explanations. For example, the supplemental explanation unit can analyze the progress of the meeting in real time and provide supplemental explanations. The supplemental explanation unit can have the generation AI analyze the progress of the meeting in real time and provide supplemental explanations at appropriate times. For example, if the meeting is stagnating, the generation AI can provide supplemental explanations that provide new information. Also, if the meeting is progressing too quickly, the supplemental explanation unit can have the generation AI provide supplemental explanations that summarize the main points. Furthermore, if the meeting is chaotic, the generation AI can provide supplemental explanations that organize the progress. In this way, by analyzing the progress of the meeting in real time, supplemental explanations can be provided at appropriate times. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can analyze the progress of the meeting in real time and input the information to the generation AI that provides supplemental explanations, and the generation AI can provide the supplemental explanations.

[0112] The supplemental explanation unit may include a system that analyzes the content of statements made by meeting participants and provides related information. For example, the supplemental explanation unit may analyze the content of statements made by meeting participants and provide related information. The supplemental explanation unit may use a generation AI to analyze the content of statements made by meeting participants and provide related information based on the content. For example, if a participant asks a technical question, the generation AI may provide supplemental explanations providing related technical information. Furthermore, if a participant asks a marketing question, the generation AI may provide supplemental explanations providing related marketing data. Furthermore, if a participant asks a question about the progress of a project, the generation AI may provide supplemental explanations providing related progress data. This allows the analysis of the content of statements made by meeting participants to provide related information and support the progress of the meeting. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit may input the content of statements made by meeting participants into the generation AI, which may analyze the content and provide related information.

[0113] The supplemental explanation unit may include a system that dynamically changes the content of the supplemental explanation according to the theme of the meeting. The supplemental explanation unit dynamically changes the content of the supplemental explanation according to, for example, the theme of the meeting. In the supplemental explanation unit, the generation AI can dynamically change the content of the supplemental explanation according to the theme of the meeting. For example, the supplemental explanation unit provides technical supplemental explanations in a technical-themed meeting. The supplemental explanation unit can also provide marketing-related supplemental explanations in a marketing-related meeting. The supplemental explanation unit can also provide project management-related supplemental explanations in a project management-related meeting. By dynamically changing the content of the supplemental explanation according to the theme of the meeting, the supplemental explanation during the meeting becomes more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the supplemental explanation unit inputs the content of the supplemental explanation to a generation AI that dynamically changes the content of the supplemental explanation according to the theme of the meeting, and the generation AI can provide the content.

[0114] The supplemental explanation unit may include a system that estimates the user's emotions and adjusts the length of the supplemental explanation based on the estimated user emotions. For example, the supplemental explanation unit estimates the user's emotions and adjusts the length of the supplemental explanation based on the estimated user emotions. The supplemental explanation unit may use a generation AI to estimate the user's emotions and adjust the length of the supplemental explanation based on the emotions. For example, if the user is nervous, the supplemental explanation unit may provide a short, to-the-point supplemental explanation. Furthermore, if the user is relaxed, the supplemental explanation unit may provide a detailed supplemental explanation. Furthermore, if the user is tired, the supplemental explanation unit may provide a succinct, to-the-point supplemental explanation. Adjusting the length of the supplemental explanation based on the user's emotions ensures that the supplemental explanation during the meeting is of a more appropriate length. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the supplemental explanation unit may be performed using, for example, the generation AI, or without the generation AI. For example, the supplementary explanation unit can estimate the user's emotions and input them into a generation AI that adjusts the length of the supplementary explanation based on those emotions, and the generation AI can provide the content.

[0115] The supplemental explanation unit can customize the content of the supplemental explanation according to the expertise of the meeting participants. The supplemental explanation unit customizes the content of the supplemental explanation according to, for example, the expertise of the meeting participants. The supplemental explanation unit can customize the content of the supplemental explanation according to the expertise of the meeting participants using a generation AI. For example, the supplemental explanation unit can provide technical supplemental explanations to participants with technical expertise. The supplemental explanation unit can also provide marketing supplemental explanations to participants with marketing expertise. The supplemental explanation unit can also provide project management supplemental explanations to participants with project management expertise. In this way, customizing the content of the supplemental explanation according to the expertise of the meeting participants makes the supplemental explanation during the meeting more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can input the content of the supplemental explanation into a generation AI that customizes the content of the supplemental explanation according to the expertise of the meeting participants, and the generation AI can provide the content.

[0116] The supplemental explanation unit may include a system that adjusts the order of supplemental explanations according to the theme of the meeting. The supplemental explanation unit adjusts the order of supplemental explanations according to, for example, the theme of the meeting. The supplemental explanation unit can adjust the order of supplemental explanations according to the theme of the meeting using a generation AI. For example, the supplemental explanation unit prioritizes technical supplemental explanations in a meeting on a technical theme. The supplemental explanation unit can also prioritize marketing supplemental explanations in a meeting on a marketing theme. The supplemental explanation unit can also prioritize project management supplemental explanations in a meeting on a project management theme. In this way, by adjusting the order of supplemental explanations according to the theme of the meeting, the order of supplemental explanations during the meeting is more appropriate. Some or all of the above-described processing in the supplemental explanation unit may be performed using, or without, the generation AI. For example, the supplemental explanation unit can input data to a generation AI that adjusts the order of supplemental explanations according to the theme of the meeting, and the generation AI can adjust the order.

[0117] The supplemental explanation unit may include a system that adjusts the frequency of supplemental explanations according to the progress of the meeting. The supplemental explanation unit adjusts the frequency of supplemental explanations according to, for example, the progress of the meeting. In the supplemental explanation unit, the generation AI can adjust the frequency of supplemental explanations according to the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of supplemental explanations. Also, if the meeting is progressing too quickly, the supplemental explanation unit can decrease the frequency of supplemental explanations. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of supplemental explanations. In this way, by adjusting the frequency of supplemental explanations according to the progress of the meeting, supplemental explanations during the meeting are provided at a more appropriate frequency. Some or all of the above-described processing in the supplemental explanation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the supplemental explanation unit can input data to a generation AI that adjusts the frequency of supplemental explanations according to the progress of the meeting, and the generation AI can adjust the frequency.

[0118] The minutes-taking unit may include a system that estimates a user's emotions and adjusts the content of the minutes based on the estimated user emotions. For example, the minutes-taking unit estimates a user's emotions and adjusts the content of the minutes based on the estimated user emotions. The minutes-taking unit may use a generation AI to estimate a user's emotions and adjust the content of the minutes based on the user's emotions. For example, if the minutes-taking unit is nervous, the generation AI may create minutes that help the user relax. Furthermore, if the user is excited, the generation AI may create minutes that calmly support the progress of the meeting. Furthermore, if the user is tired, the generation AI may create minutes that succinctly summarize the main points. Adjusting the content of the minutes based on the user's emotions results in a more appropriate meeting record. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the minutes-taking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the minutes-taking unit may estimate the user's emotions and input them into a generation AI that adjusts the content of the minutes based on those emotions, and the generation AI may provide the content.

[0119] The minutes-taking unit can analyze the progress of a meeting in real time and create minutes. The minutes-taking unit, for example, analyzes the progress of a meeting in real time and creates minutes. The minutes-taking unit can have the generation AI analyze the progress of a meeting in real time and create minutes at the appropriate time. For example, if the meeting is stagnating, the generation AI can create minutes to encourage progress. Also, if the meeting is progressing too quickly, the minutes-taking unit can create minutes that summarize the main points. Furthermore, if the meeting is chaotic, the generation AI can create minutes that organize the progress. In this way, by analyzing the progress of a meeting in real time, minutes can be created at the appropriate time. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking section can analyze the progress of a meeting in real time and input the information into a generation AI that creates minutes, which then creates the minutes.

[0120] The minutes-taking unit may include a system that analyzes the remarks made by meeting participants and reflects related information in the minutes. For example, the minutes-taking unit analyzes the remarks made by meeting participants and reflects related information in the minutes. The minutes-taking unit may use a generation AI to analyze the remarks made by meeting participants and reflect related information in the minutes based on the analyzed remarks. For example, if a participant asks a technical question, the generation AI may reflect related technical information in the minutes. Furthermore, if a participant asks a marketing question, the generation AI may reflect related marketing data in the minutes. Furthermore, if a participant asks a question about the progress of a project, the generation AI may reflect related progress data in the minutes. This allows the remarks made by meeting participants to be analyzed, thereby reflecting related information in the minutes and resulting in a more accurate record of the meeting. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the minutes-taking department can input the remarks made by meeting participants into the generation AI, which can then analyze the content and reflect relevant information in the minutes.

[0121] The minutes-taking unit may be equipped with a system that dynamically changes the content of the minutes according to the theme of the meeting. The minutes-taking unit dynamically changes the content of the minutes according to, for example, the theme of the meeting. In the minutes-taking unit, the generation AI can dynamically change the content of the minutes according to the theme of the meeting. For example, the minutes-taking unit creates technical minutes for a technical-themed meeting. The minutes-taking unit can also create marketing-related minutes for a marketing-related meeting. The minutes-taking unit can also create project management-related minutes for a project management-related meeting. Dynamically changing the content of the minutes according to the theme of the meeting makes the meeting record more appropriate. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can input the content of the minutes to a generation AI that dynamically changes the content of the minutes according to the theme of the meeting, and the generation AI can provide the content.

[0122] The minutes-taking unit may include a system that estimates a user's emotions and adjusts the length of the minutes based on the estimated user emotions. For example, the minutes-taking unit estimates a user's emotions and adjusts the length of the minutes based on the estimated user emotions. The minutes-taking unit may have a generation AI that estimates a user's emotions and adjusts the length of the minutes based on the emotions. For example, if the user is nervous, the minutes-taking unit may create short, concise minutes. The minutes-taking unit may also create detailed minutes if the user is relaxed. Furthermore, if the user is tired, the minutes-taking unit may create minutes that briefly summarize the main points. This allows the length of the minutes to be adjusted based on the user's emotions, resulting in a more appropriate length for the meeting record. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processes in the minutes-taking unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the minutes-taking unit may estimate the user's emotions and input them into a generation AI that adjusts the length of the minutes based on those emotions, and the generation AI may provide the content.

[0123] The minutes-taking unit may include a system that customizes the content of the minutes according to the expertise of the meeting participants. The minutes-taking unit customizes the content of the minutes according to, for example, the expertise of the meeting participants. The minutes-taking unit can use a generation AI to customize the content of the minutes according to the expertise of the meeting participants. For example, the minutes-taking unit can create technical minutes for participants with technical expertise. The minutes-taking unit can also create marketing-related minutes for participants with marketing expertise. The minutes-taking unit can also create project management-related minutes for participants with project management expertise. This allows the content of the minutes to be customized according to the expertise of the meeting participants, resulting in more appropriate meeting records. Some or all of the above-described processing in the minutes-taking unit may be performed, for example, using or without the generation AI. For example, the minutes-taking unit can input data to a generation AI that customizes the content of the minutes according to the expertise of the meeting participants, and the generation AI can provide the content.

[0124] The minutes-taking unit may be equipped with a system that adjusts the order of the minutes according to the theme of the meeting. The minutes-taking unit adjusts the order of the minutes according to, for example, the theme of the meeting. The minutes-taking unit can adjust the order of the minutes according to the theme of the meeting using a generation AI. For example, the minutes-taking unit may prioritize technical minutes in a meeting on a technical theme. The minutes-taking unit may also prioritize marketing-related minutes in a meeting on a marketing theme. The minutes-taking unit may also prioritize project management-related minutes in a meeting on a project management theme. By adjusting the order of the minutes according to the theme of the meeting, the meeting record is recorded in a more appropriate order. Some or all of the above-described processing in the minutes-taking unit may be performed using, or without, the generation AI. For example, the minutes-taking unit may input the minutes to a generation AI that adjusts the order of the minutes according to the theme of the meeting, and the generation AI may adjust the order.

[0125] The minutes-taking unit may be equipped with a system that adjusts the frequency of minutes according to the progress of the meeting. The minutes-taking unit adjusts the frequency of minutes according to, for example, the progress of the meeting. In the minutes-taking unit, the generation AI can adjust the frequency of minutes according to the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of minutes. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of minutes. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of minutes. In this way, adjusting the frequency of minutes according to the progress of the meeting ensures that the meeting is recorded at a more appropriate frequency. Some or all of the above-mentioned processing in the minutes-taking unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the minutes-taking unit can input data to a generation AI that adjusts the frequency of minutes according to the progress of the meeting, and the generation AI can adjust the frequency. === Hard Collateral 1-1 === Each of the multiple elements, including the role setting unit, participation unit, input unit, supplementary explanation unit, and minutes creation unit, described above, is realized by at least one of the smart device 14 and the data processing device 12. For example, the role setting unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI estimates the user's emotions and sets an optimal role based on those emotions. The participation unit is realized by the control unit 46A of the smart device 14, and the generation AI poses questions and provides supplementary explanations during the meeting. The input unit is realized by the specific processing unit 290 of the data processing device 12, and inputs the contents of the meeting to the generation AI in advance. The supplementary explanation unit is realized by the control unit 46A of the smart device 14, and the generation AI provides appropriate supplementary explanations during the meeting. The minutes creation unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI automatically compiles minutes of the meeting. === Hard Collateral 1-2 === Each of the multiple elements, including the role setting unit, participation unit, input unit, supplementary explanation unit, and minutes creation unit, described above, is realized by at least one of the smart glasses 214 and the data processing device 12. For example, the role setting unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI estimates the user's emotions and sets an optimal role based on those emotions. The participation unit is realized by the control unit 46A of the smart glasses 214, and the generation AI poses questions and provides supplementary explanations during the meeting. The input unit is realized by the specific processing unit 290 of the data processing device 12, and inputs the contents of the meeting to the generation AI in advance. The supplementary explanation unit is realized by the control unit 46A of the smart glasses 214, and the generation AI provides appropriate supplementary explanations during the meeting. The minutes creation unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI automatically compiles minutes of the meeting. === Hard Collateral 1-3 === Each of the multiple elements, including the role setting unit, participation unit, input unit, supplementary explanation unit, and minutes creation unit, described above, is realized by at least one of the headset-type terminal 314 and the data processing device 12. For example, the role setting unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI estimates the user's emotions and sets an optimal role based on those emotions. The participation unit is realized by the control unit 46A of the headset-type terminal 314, and the generation AI poses questions and provides supplementary explanations during the conference. The input unit is realized by the specific processing unit 290 of the data processing device 12, and inputs the contents of the conference to the generation AI in advance. The supplementary explanation unit is realized by the control unit 46A of the headset-type terminal 314, and the generation AI provides appropriate supplementary explanations during the conference. The minutes creation unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI automatically compiles the minutes of the conference. === Hard Collateral 1-4 === Each of the multiple elements, including the role setting unit, participation unit, input unit, supplementary explanation unit, and minutes creation unit, described above, is realized by at least one of the robot 414 and the data processing device 12. For example, the role setting unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI estimates the user's emotions and sets an optimal role based on those emotions. The participation unit is realized by the control unit 46A of the robot 414, and the generation AI poses questions and provides supplementary explanations during the meeting. The input unit is realized by the specific processing unit 290 of the data processing device 12, and inputs the contents of the meeting to the generation AI in advance. The supplementary explanation unit is realized by the control unit 46A of the robot 414, and the generation AI provides appropriate supplementary explanations during the meeting. The minutes creation unit is realized by the specific processing unit 290 of the data processing device 12, and the generation AI automatically compiles minutes of the meeting.

[0126] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0127] The meeting support system can further include an information providing unit that analyzes the content of statements made by meeting participants in real time and provides related information. For example, when a participant asks a technical question, the generation AI can provide related technical information. Also, when a participant asks a marketing question, the generation AI can provide related marketing data. Furthermore, when a participant asks about the progress of a project, the generation AI can provide related progress data. In this way, by analyzing the content of statements made by meeting participants, related information can be provided and the progress of the meeting can be supported.

[0128] The meeting support system can further include a speech adjustment unit that analyzes the progress of the meeting in real time and adjusts the timing of remarks. For example, if the meeting is stalling, the generation AI will raise a new agenda item. Also, if the meeting is progressing too quickly, the generation AI can make a statement summarizing the main points. Furthermore, if the meeting is chaotic, the generation AI can make a statement to organize the progress. In this way, by analyzing the progress of the meeting in real time, it is possible to make a statement at the appropriate time.

[0129] The conference support system can further include a utterance customization unit that customizes the content of utterances based on the expertise of conference participants. For example, the utterance customization unit can provide technical utterances to a participant with technical expertise. It can also provide marketing-related utterances to a participant with marketing expertise. It can also provide project management-related utterances to a participant with project management expertise. In this way, the utterance content can be customized according to the expertise of conference participants, making the conference proceed more effective.

[0130] The conference support system can further include a speech order adjustment unit that adjusts the order of comments depending on the conference theme. For example, the speech order adjustment unit can prioritize technical comments in a conference on a technical theme. It can also prioritize marketing-related comments in a conference on a marketing theme. It can also prioritize project management-related comments in a conference on a project management theme. In this way, adjusting the order of comments depending on the conference theme makes the conference proceed more smoothly.

[0131] The meeting support system can further include a speech frequency adjustment unit that adjusts the frequency of speech depending on the progress of the meeting. For example, if the meeting is stagnating, the generation AI can increase the frequency of speech. Also, if the meeting is progressing too quickly, the generation AI can decrease the frequency of speech. Furthermore, if the meeting is chaotic, the generation AI can adjust the frequency of speech. In this way, adjusting the frequency of speech depending on the progress of the meeting makes the meeting proceed more effectively.

[0132] The meeting support system can further include a speech content adjustment unit that estimates the user's emotions and adjusts the content of speech based on the estimated user emotions. For example, if the user is nervous, the speech content adjustment unit adjusts the speech content so that the generation AI will relax the user. Also, if the user is excited, the generation AI can adjust the speech content to calmly support the progress of the meeting. Furthermore, if the user is tired, the generation AI can adjust the speech content to succinctly summarize the main points. In this way, by adjusting the content of speech based on the user's emotions, speech during the meeting becomes more appropriate.

[0133] The meeting support system can further include an input priority determination unit that estimates the user's emotions and determines the priority of information to be input based on the estimated user emotions. For example, if the user is nervous, the input priority determination unit can cause the generation AI to prioritize information that helps the user relax. Also, if the user is excited, the generation AI can prioritize information that helps the user stay calm and proceed. Furthermore, if the user is tired, the generation AI can prioritize information that succinctly summarizes the main points. In this way, by determining the priority of information to be input based on the user's emotions, information provision during meetings becomes more appropriate.

[0134] The meeting support system can further include an input amount adjustment unit that estimates the user's emotions and adjusts the amount of information to be input based on the estimated user emotions. For example, if the user is nervous, the input amount adjustment unit adjusts the amount of information that the generation AI uses to relax the user. Also, if the user is excited, the input amount adjustment unit can adjust the amount of information that the generation AI uses to calmly support the user in proceeding. Furthermore, if the user is tired, the generation AI can adjust the amount of information that concisely summarizes the main points. In this way, by adjusting the amount of information to be input based on the user's emotions, information provision during meetings becomes more appropriate.

[0135] The meeting support system can further include a supplementary explanation content adjustment unit that estimates the user's emotions and adjusts the content of the supplementary explanation based on the estimated user's emotions. For example, if the user is nervous, the generation AI can provide supplementary explanation to relax the user. Also, if the user is excited, the generation AI can provide supplementary explanation to calmly support the progress of the meeting. Furthermore, if the user is tired, the generation AI can provide supplementary explanation that succinctly summarizes the main points. In this way, by adjusting the content of the supplementary explanation based on the user's emotions, the supplementary explanation during the meeting can be made more appropriate.

[0136] The meeting support system can further include a minutes content adjustment unit that estimates the user's emotions and adjusts the content of the minutes based on the estimated user emotions. For example, if the user is nervous, the generation AI can create minutes to help the user relax. Also, if the user is excited, the generation AI can create minutes that calmly support the progress of the meeting. Furthermore, if the user is tired, the generation AI can create minutes that concisely summarize the main points. In this way, by adjusting the content of the minutes based on the user's emotions, the meeting record will have more appropriate content.

[0137] The processing flow of the second embodiment will be briefly explained below.

[0138] Step 1: The role setting unit sets roles before the meeting. For example, a role to raise questions or a role to provide supplementary explanations. The role setting unit can set roles for the generation AI to raise questions or provide supplementary explanations at appropriate times during the meeting. It can also set roles for the generation AI to support the progress of the meeting. Step 2: The participants join the meeting based on the roles set by the role setting unit. The participants can ask questions or provide supplementary explanations during the meeting. The generation AI can also support the progress of the meeting. Step 3: The input unit inputs the meeting content in advance. The input unit can input background information and related data about the meeting agenda into the generation AI. It can also input information that will enable the generation AI to provide appropriate supplementary explanations during the meeting. Step 4: The supplementary explanation unit provides supplementary explanations during the meeting based on the information input by the input unit. The supplementary explanation unit allows the generation AI to provide supplementary explanations based on background information and related data on the meeting agenda. The generation AI can also provide appropriate answers to questions from participants during the meeting. Step 5: The minutes-taking unit automatically compiles the minutes of the meeting. The minutes-taking unit allows the generation AI to record the contents of the meeting and create minutes. The generation AI can also provide the minutes to participants after the meeting has ended.

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0140] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0143] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0144] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0145] 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, RAM 30, and 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.

[0146] 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.

[0147] 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 audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] 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 carried out in a secure state.

[0150] Fig. 4 shows an example of the 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.

[0151] 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.

[0152] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0154] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0156] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0159] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0160] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0161] 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, RAM 30, and 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.

[0162] 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.

[0163] 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 audio according to instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0165] 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 carried out in a secure state.

[0166] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0167] 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.

[0168] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0169] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0170] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0171] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0172] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0173] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0175] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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, RAM 30, and 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.

[0178] 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.

[0179] 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 audio according to instructions from the processor 46.

[0180] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0181] 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 carried out in a secure state.

[0182] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0183] 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.

[0184] 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.

[0185] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0186] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0187] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0188] 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 voice indicating a user input regarding 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.

[0189] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0190] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0191] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0192] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0193] FIG. 9 illustrates 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. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0194] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically 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.

[0195] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0196] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0197] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0198] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of 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, "relieved," "calm," and "reassuring," have similar emotion values.

[0199] 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.

[0200] 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 USB (Universal Serial Bus) 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.

[0201] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0202] 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.

[0203] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0204] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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.

[0205] As an example of a system configured with a single 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 system that uses a processor that realizes the functions of an 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.

[0206] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0207] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0208] The above-described description and illustrations are a detailed explanation 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, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects 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 replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0209] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0210] [Explanation of symbols]

[0211] 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 role setting unit for setting roles before a conference; a participation unit that participates in a conference based on the role set by the role setting unit; The input section inputs the contents of the meeting in advance, a supplementary explanation unit that provides supplementary explanations during the conference based on the information input by the input unit; A minutes creation unit that automatically compiles minutes of meetings. A system characterized by:

2. The minutes-taking department After the meeting, create meeting minutes and email them to participants 2. The system of claim 1.

3. The supplementary explanation section Provide background information and relevant data to support the meeting agenda 2. The system of claim 1.

4. The role setting unit Assign roles to raise questions or provide additional explanations 2. The system of claim 1.

5. The participating unit: Raise questions and provide additional explanations during the meeting based on your assigned role 2. The system of claim 1.

6. The minutes-taking department Equipped with a function to display a summary of the previous meeting 2. The system of claim 1.

7. The minutes-taking department List upcoming actions and email them to participants 2. The system of claim 1.

8. The supplementary explanation section Translate and display meeting content in real time 2. The system of claim 1.

Images