System

Abstract

An object of the system according to the embodiment is to enable everyone to participate in a discussion equally by allowing an AI to manage roles in the discussion in an integrated manner.SOLUTION: A system includes a facilitator management unit, a secretary management unit, and a timekeeper management unit. The facilitator manager manages the progress of the discussion. The secretary management unit records the contents of the discussion. The timekeeper manager manages the time of the discussion.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] In conventional techniques, the division of roles in a discussion can hinder participants from concentrating on the discussion.

[0005] The system of the embodiment aims to enable everyone to participate in the discussion equally by having AI centrally manage roles in the discussion. [Means for solving the problem]

[0006] The system according to the embodiment includes a facilitator management unit, a secretary management unit, and a timekeeper management unit. The facilitator management unit manages the progress of the discussion. The secretary management unit records the content of the discussion. The timekeeper management unit manages the time of the discussion. [Effects of the Invention]

[0007] The system according to the embodiment allows everyone to participate equally in the discussion by having AI centrally manage roles in the discussion. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The discussion management system according to an embodiment of the present invention uses generative AI to centrally manage and execute the roles of discussion moderator, secretary, and timekeeper. This allows everyone to participate in the discussion equally, creating great synergy even when working at the same time.

[0029] The discussion management system according to the embodiment comprises a facilitator management unit, a secretary management unit, and a timekeeper management unit. The facilitator management unit manages the progress of the discussion. For example, the facilitator management unit manages the progress of the discussion from start to finish, and adjusts the order in which topics are presented and comments are made. The facilitator management unit can also analyze the facial expressions and tone of voice of participants as the discussion progresses and suggest breaks at appropriate times. The facilitator management unit can also supplement the flow of the discussion by referring to related past discussions and data in real time. The secretary management unit records the content of the discussion. For example, the secretary management unit converts comments made during the discussion into text in real time and creates minutes. The secretary management unit can also automatically highlight important keywords and phrases when recording the content of the discussion. Furthermore, the secretary management unit can color-code each speaker when recording the content of the discussion to make it easier to understand visually. The timekeeper management unit manages the time spent on the discussion. For example, the timekeeper management unit manages the time allocated to each topic and prompts participants to move on to the next topic when the time has passed. The timekeeper management unit can also visualize the progress of the discussion, allowing participants to intuitively understand it. Furthermore, the timekeeper management unit can share the progress of the discussion with other meeting participants and adjust time allocation based on their feedback. This allows everyone to participate equally in the discussion, creating significant synergy even with the same amount of time. For example, if the generation AI smoothly progresses the discussion, the content of the discussion can be deepened and a better conclusion can be reached. Furthermore, if the generation AI creates minutes in real time, the content of the discussion can be accurately recorded and can be referenced later.

[0030] The facilitator management unit can complement the flow of the discussion by referencing past discussions and data in real time. For example, the generation AI in the facilitator management unit searches a database of past discussions in real time and provides information relevant to the current discussion. For example, it refers to conclusions and proposals reached in past discussions. The generation AI in the facilitator management unit also analyzes keywords spoken during a discussion and automatically displays related past data. For example, it provides information on specific technologies or market data. The generation AI in the facilitator management unit also collects data in real time as the discussion is underway and complements the flow of the discussion. For example, it provides the latest research results and news related to the current discussion. This improves the quality of the discussion by referring to past discussions and data.

[0031] The facilitator management unit can provide expert opinions in real time according to the topic of the discussion. For example, the generation AI searches a database for expert opinions according to the topic of the discussion and provides them in real time. For example, it refers to papers and interviews with experts in a specific technical field. The facilitator management unit also analyzes keywords spoken during a discussion and automatically displays related expert opinions. For example, it provides expert views on specific market trends. The facilitator management unit also collects expert opinions in real time as the generation AI is in progress, complementing the flow of the discussion. For example, it provides the latest research results and news related to the current discussion. This improves the quality of discussions by providing expert opinions in real time.

[0032] The facilitator management unit can visualize the progress of the discussion, allowing participants to intuitively understand. In the facilitator management unit, for example, the generation AI visualizes the progress of the discussion in real time and displays it to participants. For example, the progress of the agenda and the order of comments are shown in graphs and charts. The facilitator management unit also analyzes keywords spoken by the generation AI during the discussion and visualizes and displays related information. For example, it shows information about specific technologies or market data in graphs and charts. In addition, the facilitator management unit visualizes the progress of the discussion, allowing participants to intuitively understand. For example, the progress of the agenda and the order of comments are shown in graphs and charts. In this way, the progress of the discussion is visualized, allowing participants to intuitively understand.

[0033] The secretary management unit can automatically highlight important keywords and phrases when recording the content of a discussion. For example, the secretary management unit analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. The secretary management unit also analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. The secretary management unit also analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. This visually emphasizes important information, making the content of the discussion easier to refer to later.

[0034] When recording the content of a discussion, the secretary management unit can color-code each speaker to make it visually easier to understand. For example, the secretary management unit records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. The secretary management unit also records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. The secretary management unit also records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. In this way, by color-coding each speaker, the content of the discussion is visually easier to understand.

[0035] When recording the content of a discussion, the secretary management unit can simultaneously save the audio data so that it can be played back later. For example, the secretary management unit records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. The secretary management unit also records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. The secretary management unit also records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. In this way, by saving the audio data, the content of a discussion can be played back later.

[0036] The secretary management unit can automatically link related external data when recording the content of a discussion. For example, the secretary management unit records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. The secretary management unit also records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. The secretary management unit also records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. In this way, the content of the discussion is complemented by linking related external data.

[0037] The timekeeper management unit can analyze the progress of each agenda item in real time and dynamically adjust time allocation when managing discussion time. For example, the timekeeper management unit analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is behind schedule, the time is extended. The timekeeper management unit also analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is progressing too quickly, the time to move on to the next agenda item is adjusted. The timekeeper management unit also analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is progressing slowly, the time is extended, and if progress is progressing too quickly, the time to move on to the next agenda item is adjusted. This dynamically adjusts time allocation according to the progress on the agenda items, improving the efficiency of discussions.

[0038] When managing discussion time, the timekeeper management unit can propose optimal time allocation based on past discussion data. In the timekeeper management unit, for example, the generation AI analyzes past discussion data and proposes optimal time allocation for each agenda item. For example, more time is allocated to agenda items that did not have enough time in past discussions. In addition, the timekeeper management unit predicts the progress of each agenda item based on past discussion data and proposes optimal time allocation. For example, time allocation for each agenda item is adjusted based on past data. In addition, the timekeeper management unit analyzes past discussion data and proposes optimal time allocation for each agenda item. For example, more time is allocated to agenda items that did not have enough time in past discussions. In this way, the efficiency of discussions is improved by proposing optimal time allocation based on past discussion data.

[0039] When managing the time of a discussion, the timekeeper management unit can visualize the progress of each agenda item, allowing participants to intuitively understand. In the timekeeper management unit, for example, the generation AI visualizes the progress of the discussion in real time and displays it to participants. For example, the progress of the agenda items and the order of comments are shown in graphs and charts. The timekeeper management unit also analyzes keywords spoken by the generation AI during a discussion and visualizes and displays related information. For example, it shows information about specific technologies or market data in graphs and charts. The timekeeper management unit also visualizes the progress of the discussion by the generation AI, allowing participants to intuitively understand. For example, it shows the progress of the agenda items and the order of comments in graphs and charts. In this way, the progress of the agenda items is visualized, allowing participants to intuitively understand.

[0040] When managing the time of a discussion, the timekeeper management unit can share the progress of the discussion with other meeting participants and adjust time allocation based on the feedback. In the timekeeper management unit, for example, the generation AI shares the progress of the discussion with other meeting participants in real time and adjusts time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In addition, the timekeeper management unit can share the progress of the discussion with other meeting participants in real time and adjust time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In addition, the timekeeper management unit can share the progress of the discussion with other meeting participants in real time and adjust time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In this way, by sharing the progress of the discussion and adjusting time allocation based on the feedback, the efficiency of the discussion is improved.

[0041] When adjusting the order of speech, the facilitator management unit takes into account the number of times and duration of speeches in the past to ensure that everyone has an equal chance to speak. For example, the generation AI analyzes past speech data and adjusts the order of speech taking into account the number of times and duration of speeches. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. The generation AI also adjusts the order of speech taking into account the number of times and duration of speeches based on past speech data. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. The generation AI also adjusts the order of speech taking into account the number of times and duration of speeches based on past speech data. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. This allows everyone to speak equally, improving the fairness of the discussion.

[0042] When adjusting the order of speech, the facilitator management unit can promote dialogue between participants with different opinions and deepen the discussion. For example, the generation AI adjusts the order of speech to promote dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. Also, when the generation AI adjusts the order of speech, the facilitator management unit promotes dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. Also, when the generation AI adjusts the order of speech, the facilitator management unit promotes dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. This promotes dialogue between participants with different opinions and deepens the discussion.

[0043] When adjusting the order of speech, the facilitator management unit can analyze the content of participants' speech in real time and provide related information. For example, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. Also, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. Also, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. In this way, the content of participants' speech is analyzed in real time and related information is provided, improving the quality of discussion.

[0044] The facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time, and provide feedback to the participants. In the facilitator management unit, for example, the generation AI smoothly progresses the discussion and summarizes the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In addition, the facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In addition, the facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In this way, the content of the discussion can be summarized in real time and feedback can be provided to the participants, thereby improving the quality of the discussion.

[0045] The facilitator management unit smoothly advances the discussion, automatically clustering the content of the discussion and linking related ideas. In the facilitator management unit, for example, the generation AI smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In addition, the facilitator management unit smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In addition, the facilitator management unit smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In this way, the generation AI smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In this way, the content of the discussion is automatically clustered and related ideas are linked, improving the quality of the discussion.

[0046] The facilitator management unit allows the discussion to proceed smoothly, allowing the content of the discussion to be shared with other projects and teams, creating synergy. For example, the generation AI in the facilitator management unit will smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. The facilitator management unit also allows the generation AI to smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. The facilitator management unit also allows the generation AI to smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. In this way, the content of the discussion can be shared with other projects and teams, creating synergy.

[0047] The facilitator management unit smoothly advances the discussion, visualizing the content of the discussion so that participants can intuitively understand it. For example, the generation AI in the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In addition, the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In addition, the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In this way, the content of the discussion is visualized so that participants can intuitively understand it.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The discussion management system can also be equipped with a translation unit that translates participants' comments in real time. For example, if there are participants who speak different languages, the translation unit can instantly translate the comments and display them to the other participants. The translation unit can also translate comments into multiple languages ​​while the discussion is in progress and save them as minutes. Furthermore, the translation unit can accurately translate technical and specialized terms to improve the quality of the discussion. This allows participants who speak different languages ​​to participate smoothly in the discussion and functions effectively even in international discussion forums.

[0050] The facilitator management module can monitor the health status of participants during the discussion and suggest breaks as necessary. For example, the generative AI can monitor participants' heart rate and blood pressure and suggest breaks if any abnormalities are detected. The facilitator management module can also suggest breaks at appropriate times based on participants' health data if a discussion continues for a long period of time. Furthermore, the facilitator management module can adjust the progress of the discussion taking into account the participants' health status. This allows for efficient discussions while maintaining the health of participants.

[0051] The Facilitator Management module can assess the skill levels of participants as the discussion progresses and assign appropriate roles. For example, the generative AI analyzes participants' past comments and achievements to suggest roles that are best suited to the discussion topic. The Facilitator Management module can also adjust the progress of the discussion based on the participants' skill levels. For example, it can increase speaking opportunities for participants with specific skills. The Facilitator Management module can also assess participants' skill levels and provide feedback to improve the quality of the discussion. This makes it possible to make the most of participants' skills and promote effective discussions.

[0052] The facilitator management unit can anonymously collect participants' opinions as the discussion progresses, promoting unbiased discussions. For example, the generative AI can anonymously collect participants' opinions and present them to other participants. The facilitator management unit can also adjust the progress of the discussion based on the anonymously collected opinions. For example, if a particular opinion is the majority opinion, the facilitator management unit can focus the discussion on that opinion. The facilitator management unit can also analyze the anonymously collected opinions and suggest the direction of the discussion. This allows participants to freely express their opinions, leading to fair discussions.

[0053] The facilitator management unit can summarize what participants say in real time as the discussion progresses and provide feedback to other participants. For example, the generative AI can analyze what is being said, summarize the main points, and present them to other participants. The facilitator management unit can also adjust the progress of the discussion based on the summarized content. For example, it can decide when to move on to the next topic based on the summarized content. The facilitator management unit can also save the summarized content as minutes and refer to them later. This makes it possible to efficiently grasp the content of the discussion and improve the quality of the discussion.

[0054] The facilitator management unit can cluster participants' comments in real time as the discussion progresses and link related ideas. For example, the generative AI analyzes the comments and displays them as groups of related ideas. The facilitator management unit can also adjust the progress of the discussion based on the clustered content. For example, it can set the next agenda item based on related ideas. The facilitator management unit can also save the clustered content as minutes and refer to them later. This makes it possible to efficiently organize the content of the discussion and improve the quality of the discussion.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The facilitator manager manages the progress of the discussion. For example, the facilitator manager manages the progress of the discussion from start to finish, and adjusts the order in which topics are presented and people speak. The facilitator manager can also analyze the facial expressions and tone of voice of participants as the discussion progresses and suggest breaks at appropriate times. Furthermore, the facilitator manager can refer to related past discussions and data in real time to supplement the flow of the discussion. Step 2: The secretarial management unit records the contents of the discussion. For example, the secretarial management unit converts comments made during the discussion into text in real time and creates minutes. The secretarial management unit can also automatically highlight important keywords and phrases when recording the contents of the discussion. Furthermore, when recording the contents of the discussion, the secretarial management unit can color-code each speaker to make it easier to understand visually. Step 3: The Timekeeper Management Unit manages the time for the discussion. For example, the Timekeeper Management Unit manages the time allocation for each agenda item and prompts participants to move on to the next agenda item when time has passed. The Timekeeper Management Unit can also visualize the progress of the discussion so that participants can intuitively understand it. Furthermore, the Timekeeper Management Unit can share the progress of the discussion with other meeting participants and adjust the time allocation based on their feedback.

[0057] (Example 2) The discussion management system according to an embodiment of the present invention uses generative AI to centrally manage and execute the roles of discussion moderator, secretary, and timekeeper. This allows everyone to participate in the discussion equally, creating great synergy even when working at the same time.

[0058] The discussion management system according to the embodiment comprises a facilitator management unit, a secretary management unit, and a timekeeper management unit. The facilitator management unit manages the progress of the discussion. For example, the facilitator management unit manages the progress of the discussion from start to finish, and adjusts the order in which topics are presented and comments are made. The facilitator management unit can also analyze the facial expressions and tone of voice of participants as the discussion progresses and suggest breaks at appropriate times. The facilitator management unit can also supplement the flow of the discussion by referring to related past discussions and data in real time. The secretary management unit records the content of the discussion. For example, the secretary management unit converts comments made during the discussion into text in real time and creates minutes. The secretary management unit can also automatically highlight important keywords and phrases when recording the content of the discussion. Furthermore, the secretary management unit can color-code each speaker when recording the content of the discussion to make it easier to understand visually. The timekeeper management unit manages the time spent on the discussion. For example, the timekeeper management unit manages the time allocated to each topic and prompts participants to move on to the next topic when the time has passed. The timekeeper management unit can also visualize the progress of the discussion, allowing participants to intuitively understand it. Furthermore, the timekeeper management unit can share the progress of the discussion with other meeting participants and adjust time allocation based on their feedback. This allows everyone to participate equally in the discussion, creating significant synergy even with the same amount of time. For example, if the generation AI smoothly progresses the discussion, the content of the discussion can be deepened and a better conclusion can be reached. Furthermore, if the generation AI creates minutes in real time, the content of the discussion can be accurately recorded and can be referenced later.

[0059] The facilitator management unit analyzes participants' facial expressions and tone of voice and can suggest breaks at appropriate times. For example, the generation AI in the facilitator management unit uses a camera to analyze participants' facial expressions to detect signs of fatigue and stress. For example, it determines the need for a break based on eye movements and facial muscle tension. The generation AI in the facilitator management unit also uses a microphone to analyze participants' tone of voice and detect changes in voice pitch and speed. For example, it suggests a break if their voice gets lower or their speaking speed slows down. The generation AI in the facilitator management unit also analyzes participants' facial expressions and tone of voice in combination to comprehensively determine the timing of a break. For example, it suggests a break if their facial expressions look tired and their voice tone is low. This reduces participants' fatigue and stress and improves the efficiency of discussions.

[0060] The facilitator management unit can complement the flow of the discussion by referencing past discussions and data in real time. For example, the generation AI in the facilitator management unit searches a database of past discussions in real time and provides information relevant to the current discussion. For example, it refers to conclusions and proposals reached in past discussions. The generation AI in the facilitator management unit also analyzes keywords spoken during a discussion and automatically displays related past data. For example, it provides information on specific technologies or market data. The generation AI in the facilitator management unit also collects data in real time as the discussion is underway and complements the flow of the discussion. For example, it provides the latest research results and news related to the current discussion. This improves the quality of the discussion by referring to past discussions and data.

[0061] The facilitator management unit uses the emotion estimation function to grasp the emotional state of participants and make adjustments to prevent discussions from getting too heated. For example, the generation AI analyzes participants' facial expressions and tone of voice to grasp their emotional state in real time. For example, it detects signs of anger or excitement. The facilitator management unit also uses the emotion estimation data to adjust discussions to prevent them from getting too heated. For example, it urges participants who are getting emotional to calm down. The facilitator management unit also uses the emotion estimation data to adjust the progress of the discussion. For example, if emotions are getting too high, it will temporarily pause the discussion and allow time for participants to calm down. This prevents the discussion from getting too heated and maintains a calm discussion.

[0062] The facilitator management unit can provide expert opinions in real time according to the topic of the discussion. For example, the generation AI searches a database for expert opinions according to the topic of the discussion and provides them in real time. For example, it refers to papers and interviews with experts in a specific technical field. The facilitator management unit also analyzes keywords spoken during a discussion and automatically displays related expert opinions. For example, it provides expert views on specific market trends. The facilitator management unit also collects expert opinions in real time as the generation AI is in progress, complementing the flow of the discussion. For example, it provides the latest research results and news related to the current discussion. This improves the quality of discussions by providing expert opinions in real time.

[0063] The facilitator management unit can visualize the progress of the discussion, allowing participants to intuitively understand. In the facilitator management unit, for example, the generation AI visualizes the progress of the discussion in real time and displays it to participants. For example, the progress of the agenda and the order of comments are shown in graphs and charts. The facilitator management unit also analyzes keywords spoken by the generation AI during the discussion and visualizes and displays related information. For example, it shows information about specific technologies or market data in graphs and charts. In addition, the facilitator management unit visualizes the progress of the discussion, allowing participants to intuitively understand. For example, the progress of the agenda and the order of comments are shown in graphs and charts. In this way, the progress of the discussion is visualized, allowing participants to intuitively understand.

[0064] The facilitator management unit can use the emotion estimation function to suggest incentives to increase participants' motivation as the discussion progresses. For example, the generation AI analyzes the emotional state of participants and suggests incentives to increase their motivation. For example, it provides positive feedback or praise. The facilitator management unit also suggests incentives to increase participants' motivation based on the emotion estimation data. For example, it monitors the emotional state of participants as the discussion progresses and provides incentives at the appropriate time. The facilitator management unit also suggests incentives to increase participants' motivation based on the emotion estimation data. For example, it monitors the emotional state of participants as the discussion progresses and provides incentives at the appropriate time. This increases participants' motivation and improves the quality of the discussion.

[0065] The secretary management unit can automatically highlight important keywords and phrases when recording the content of a discussion. For example, the secretary management unit analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. The secretary management unit also analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. The secretary management unit also analyzes keywords spoken by the generation AI during a discussion and automatically highlights important keywords and phrases. For example, it highlights information related to specific technologies or market data. This visually emphasizes important information, making the content of the discussion easier to refer to later.

[0066] When recording the content of a discussion, the secretary management unit can color-code each speaker to make it visually easier to understand. For example, the secretary management unit records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. The secretary management unit also records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. The secretary management unit also records the content spoken by the generation AI during a discussion and color-codes it by speaker to make it visually easier to understand. For example, comments by person A are displayed in blue and comments by person B are displayed in red. In this way, by color-coding each speaker, the content of the discussion is visually easier to understand.

[0067] The secretary management unit can use the emotion estimation function to record participants' emotional reactions to the content of the discussion so that they can be referenced later. For example, the secretary management unit records what the generation AI says during the discussion and uses the emotion estimation function to record the participants' emotional reactions. For example, it records an emotion score along with the content of the remarks. The secretary management unit also records what the generation AI says during the discussion and uses the emotion estimation function to record the participants' emotional reactions. For example, it records an emotion score along with the content of the remarks. The secretary management unit also records what the generation AI says during the discussion and uses the emotion estimation function to record the participants' emotional reactions. For example, it records an emotion score along with the content of the remarks. In this way, by recording the participants' emotional reactions, the content of the discussion can be easily referenced later.

[0068] When recording the content of a discussion, the secretary management unit can simultaneously save the audio data so that it can be played back later. For example, the secretary management unit records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. The secretary management unit also records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. The secretary management unit also records what the generation AI says during a discussion and simultaneously saves the audio data. For example, it can record the audio of a discussion so that it can be played back later. In this way, by saving the audio data, the content of a discussion can be played back later.

[0069] The secretary management unit can automatically link related external data when recording the content of a discussion. For example, the secretary management unit records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. The secretary management unit also records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. The secretary management unit also records what the generation AI says during a discussion and automatically links related external data. For example, it links patent data and market data. In this way, the content of the discussion is complemented by linking related external data.

[0070] The secretary management unit uses the emotion estimation function to display the participants' emotional reactions to the content of the discussion in real time, thereby adjusting the direction of the discussion. For example, the secretary management unit records the content spoken by the generation AI during the discussion and uses the emotion estimation function to display the participants' emotional reactions in real time. For example, it displays an emotion score along with the content of the speech. The secretary management unit also records the content spoken by the generation AI during the discussion and uses the emotion estimation function to display the participants' emotional reactions in real time. For example, it displays an emotion score along with the content of the speech. The secretary management unit also records the content spoken by the generation AI during the discussion and uses the emotion estimation function to display the participants' emotional reactions in real time. For example, it displays an emotion score along with the content of the speech. In this way, by displaying the participants' emotional reactions in real time, the direction of the discussion can be appropriately adjusted.

[0071] The timekeeper management unit can analyze the progress of each agenda item in real time and dynamically adjust time allocation when managing discussion time. For example, the timekeeper management unit analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is behind schedule, the time is extended. The timekeeper management unit also analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is progressing too quickly, the time to move on to the next agenda item is adjusted. The timekeeper management unit also analyzes the progress of each agenda item in real time while the generation AI is discussing and dynamically adjusts time allocation. For example, if progress on an agenda item is progressing slowly, the time is extended, and if progress is progressing too quickly, the time to move on to the next agenda item is adjusted. This dynamically adjusts time allocation according to the progress on the agenda items, improving the efficiency of discussions.

[0072] When managing discussion time, the timekeeper management unit can propose optimal time allocation based on past discussion data. In the timekeeper management unit, for example, the generation AI analyzes past discussion data and proposes optimal time allocation for each agenda item. For example, more time is allocated to agenda items that did not have enough time in past discussions. In addition, the timekeeper management unit predicts the progress of each agenda item based on past discussion data and proposes optimal time allocation. For example, time allocation for each agenda item is adjusted based on past data. In addition, the timekeeper management unit analyzes past discussion data and proposes optimal time allocation for each agenda item. For example, more time is allocated to agenda items that did not have enough time in past discussions. In this way, the efficiency of discussions is improved by proposing optimal time allocation based on past discussion data.

[0073] The timekeeper management unit can use the emotion estimation function to suggest a break when a participant's concentration starts to wane. For example, the generation AI in the timekeeper management unit analyzes the participants' facial expressions and tone of voice to detect signs of a decrease in concentration. For example, it can suggest a break based on changes in eye movements or tone of voice. The timekeeper management unit also uses emotion estimation data to suggest a break when a participant's concentration starts to wane. For example, it can suggest a break if the emotion score drops. The timekeeper management unit also uses the generation AI in the timekeeper management unit analyzes the participants' facial expressions and tone of voice to detect signs of a decrease in concentration. For example, it can suggest a break based on changes in eye movements or tone of voice. This improves the efficiency of discussions by suggesting a break when a participant's concentration starts to wane.

[0074] When managing the time of a discussion, the timekeeper management unit can visualize the progress of each agenda item, allowing participants to intuitively understand. In the timekeeper management unit, for example, the generation AI visualizes the progress of the discussion in real time and displays it to participants. For example, the progress of the agenda items and the order of comments are shown in graphs and charts. The timekeeper management unit also analyzes keywords spoken by the generation AI during a discussion and visualizes and displays related information. For example, it shows information about specific technologies or market data in graphs and charts. The timekeeper management unit also visualizes the progress of the discussion by the generation AI, allowing participants to intuitively understand. For example, it shows the progress of the agenda items and the order of comments in graphs and charts. In this way, the progress of the agenda items is visualized, allowing participants to intuitively understand.

[0075] When managing the time of a discussion, the timekeeper management unit can share the progress of the discussion with other meeting participants and adjust time allocation based on the feedback. In the timekeeper management unit, for example, the generation AI shares the progress of the discussion with other meeting participants in real time and adjusts time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In addition, the timekeeper management unit can share the progress of the discussion with other meeting participants in real time and adjust time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In addition, the timekeeper management unit can share the progress of the discussion with other meeting participants in real time and adjust time allocation based on the feedback. For example, the time allocation is adjusted based on opinions from the participants. In this way, by sharing the progress of the discussion and adjusting time allocation based on the feedback, the efficiency of the discussion is improved.

[0076] The timekeeper management unit can use the emotion estimation function to monitor the emotional state of participants as the discussion progresses and move on to the next agenda item at the appropriate time. For example, the generation AI in the timekeeper management unit analyzes the participants' facial expressions and tone of voice to monitor their emotional state in real time. For example, if the emotion score drops, the unit will move on to the next agenda item. The timekeeper management unit also uses the emotion estimation data to monitor the participants' emotional state as the discussion progresses and move on to the next agenda item at the appropriate time. For example, if the emotion score drops, the unit will move on to the next agenda item. The timekeeper management unit also uses the generation AI to analyze the participants' facial expressions and tone of voice to monitor their emotional state in real time. For example, if the emotion score drops, the unit will move on to the next agenda item. In this way, by monitoring the participants' emotional state and moving on to the next agenda item at the appropriate time, the efficiency of discussions is improved.

[0077] When adjusting the order of speech, the facilitator management unit takes into account the number of times and duration of speeches in the past to ensure that everyone has an equal chance to speak. For example, the generation AI analyzes past speech data and adjusts the order of speech taking into account the number of times and duration of speeches. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. The generation AI also adjusts the order of speech taking into account the number of times and duration of speeches based on past speech data. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. The generation AI also adjusts the order of speech taking into account the number of times and duration of speeches based on past speech data. For example, priority is given to participants who have spoken less frequently to give the opportunity to speak. This allows everyone to speak equally, improving the fairness of the discussion.

[0078] The facilitator management unit uses the emotion estimation function to take into account the emotional state of participants when adjusting the order of speech, providing an environment in which it is easy to speak. For example, the generation AI in the facilitator management unit analyzes the facial expressions and tone of voice of participants to grasp their emotional state in real time. For example, it may encourage a nervous participant to relax. The generation AI in the facilitator management unit also adjusts the order of speech based on the emotion estimation data. For example, it may encourage an emotionally excited participant to calm down. The generation AI in the facilitator management unit also adjusts the order of speech based on the emotion estimation data. For example, it may encourage an emotionally excited participant to calm down. This provides an environment in which it is easy to speak, taking into account the emotional state of participants, improving the quality of discussions.

[0079] When adjusting the order of speech, the facilitator management unit can promote dialogue between participants with different opinions and deepen the discussion. For example, the generation AI adjusts the order of speech to promote dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. Also, when the generation AI adjusts the order of speech, the facilitator management unit promotes dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. Also, when the generation AI adjusts the order of speech, the facilitator management unit promotes dialogue between participants with different opinions. For example, it gives participants with conflicting opinions an opportunity to speak. This promotes dialogue between participants with different opinions and deepens the discussion.

[0080] When adjusting the order of speech, the facilitator management unit can analyze the content of participants' speech in real time and provide related information. For example, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. Also, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. Also, the facilitator management unit has the generation AI adjust the order of speech and analyze the content of participants' speech in real time. For example, it provides information related to the content of speech. In this way, the content of participants' speech is analyzed in real time and related information is provided, improving the quality of discussion.

[0081] The facilitator management unit uses the emotion estimation function to display the emotional states of participants in real time when adjusting the order of remarks, and can adjust the direction of the discussion. For example, the facilitator management unit has the generation AI adjust the order of remarks and use the emotion estimation function to display the emotional states of participants in real time. For example, it displays an emotion score along with the content of remarks. The facilitator management unit also has the generation AI adjust the order of remarks and use the emotion estimation function to display the emotional states of participants in real time. For example, it displays an emotion score along with the content of remarks. The facilitator management unit has the generation AI adjust the order of remarks and use the emotion estimation function to display the emotional states of participants in real time. For example, it displays an emotion score along with the content of remarks. In this way, the quality of the discussion is improved by displaying the emotional states of participants in real time and adjusting the direction of the discussion.

[0082] The facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time, and provide feedback to the participants. In the facilitator management unit, for example, the generation AI smoothly progresses the discussion and summarizes the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In addition, the facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In addition, the facilitator management unit can smoothly progress the discussion, summarize the content of the discussion in real time. For example, it summarizes the main points of the discussion and provides feedback to the participants. In this way, the content of the discussion can be summarized in real time and feedback can be provided to the participants, thereby improving the quality of the discussion.

[0083] The facilitator management unit smoothly advances the discussion, automatically clustering the content of the discussion and linking related ideas. In the facilitator management unit, for example, the generation AI smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In addition, the facilitator management unit smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In addition, the facilitator management unit smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In this way, the generation AI smoothly advances the discussion and automatically clusters the content of the discussion. For example, related ideas are grouped and displayed. In this way, the content of the discussion is automatically clustered and related ideas are linked, improving the quality of the discussion.

[0084] The facilitator management unit uses the emotion estimation function to smoothly progress the discussion, taking into account the emotional states of the participants and proposing the optimal direction for the discussion. In the facilitator management unit, for example, the generation AI uses the emotion estimation function to grasp the emotional states of the participants in real time and smoothly progress the discussion. For example, it adjusts the direction of the discussion based on the emotion score. In addition, the facilitator management unit uses the emotion estimation function to grasp the emotional states of the participants in real time and smoothly progress the discussion. For example, it adjusts the direction of the discussion based on the emotion score. In addition, the facilitator management unit uses the emotion estimation function to grasp the emotional states of the participants in real time and smoothly progress the discussion. For example, it adjusts the direction of the discussion based on the emotion score. In this way, the quality of the discussion is improved by taking into account the emotional states of the participants and proposing the optimal direction for the discussion.

[0085] The facilitator management unit allows the discussion to proceed smoothly, allowing the content of the discussion to be shared with other projects and teams, creating synergy. For example, the generation AI in the facilitator management unit will smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. The facilitator management unit also allows the generation AI to smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. The facilitator management unit also allows the generation AI to smoothly proceed with the discussion and share the content of the discussion with other projects and teams. For example, it will summarize the main points of the discussion and provide them to other teams. In this way, the content of the discussion can be shared with other projects and teams, creating synergy.

[0086] The facilitator management unit smoothly advances the discussion, visualizing the content of the discussion so that participants can intuitively understand it. For example, the generation AI in the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In addition, the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In addition, the facilitator management unit smoothly advances the discussion and visualizes the content of the discussion. For example, the main points of the discussion are displayed in graphs and charts. In this way, the content of the discussion is visualized so that participants can intuitively understand it.

[0087] The facilitator management unit uses the emotion estimation function to smoothly progress the discussion, thereby monitoring the emotional states of participants in real time and adjusting the direction of the discussion. In the facilitator management unit, for example, the generation AI uses the emotion estimation function to monitor the emotional states of participants in real time and smoothly progress the discussion. For example, the direction of the discussion is adjusted based on the emotion score. In addition, the facilitator management unit uses the emotion estimation function to monitor the emotional states of participants in real time and smoothly progress the discussion. For example, the direction of the discussion is adjusted based on the emotion score. In addition, the facilitator management unit uses the emotion estimation function to monitor the emotional states of participants in real time and smoothly progress the discussion. For example, the direction of the discussion is adjusted based on the emotion score. In this way, by monitoring the emotional states of participants in real time and adjusting the direction of the discussion, the quality of the discussion is improved.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The discussion management system can also be equipped with a translation unit that translates participants' comments in real time. For example, if there are participants who speak different languages, the translation unit can instantly translate the comments and display them to the other participants. The translation unit can also translate comments into multiple languages ​​while the discussion is in progress and save them as minutes. Furthermore, the translation unit can accurately translate technical and specialized terms to improve the quality of the discussion. This allows participants who speak different languages ​​to participate smoothly in the discussion and functions effectively even in international discussion forums.

[0090] The facilitator management module can monitor the health status of participants during the discussion and suggest breaks as necessary. For example, the generative AI can monitor participants' heart rate and blood pressure and suggest breaks if any abnormalities are detected. The facilitator management module can also suggest breaks at appropriate times based on participants' health data if a discussion continues for a long period of time. Furthermore, the facilitator management module can adjust the progress of the discussion taking into account the participants' health status. This allows for efficient discussions while maintaining the health of participants.

[0091] The Facilitator Management module can assess the skill levels of participants as the discussion progresses and assign appropriate roles. For example, the generative AI analyzes participants' past comments and achievements to suggest roles that are best suited to the discussion topic. The Facilitator Management module can also adjust the progress of the discussion based on the participants' skill levels. For example, it can increase speaking opportunities for participants with specific skills. The Facilitator Management module can also assess participants' skill levels and provide feedback to improve the quality of the discussion. This makes it possible to make the most of participants' skills and promote effective discussions.

[0092] The facilitator management unit can use the emotion estimation function to grasp the emotional state of participants as the discussion progresses and provide refreshments at appropriate times. For example, the generative AI analyzes participants' facial expressions and tone of voice to detect signs of fatigue or stress. The facilitator management unit can also adjust the timing of providing refreshments based on the emotion estimation data, taking into account the participants' emotional state. For example, it can provide refreshments to participants who are feeling emotional to help them relax. Furthermore, the facilitator management unit can select the type of refreshment based on the emotion estimation data. This allows for appropriate management of participants' emotional states and improves the efficiency of discussions.

[0093] The facilitator management unit can anonymously collect participants' opinions as the discussion progresses, promoting unbiased discussions. For example, the generative AI can anonymously collect participants' opinions and present them to other participants. The facilitator management unit can also adjust the progress of the discussion based on the anonymously collected opinions. For example, if a particular opinion is the majority opinion, the facilitator management unit can focus the discussion on that opinion. The facilitator management unit can also analyze the anonymously collected opinions and suggest the direction of the discussion. This allows participants to freely express their opinions, leading to fair discussions.

[0094] The facilitator management unit can use the emotion estimation function to grasp the emotional state of participants as the discussion progresses and adjust the direction of the discussion at the appropriate time. For example, the generative AI analyzes participants' facial expressions and tone of voice to grasp their emotional state in real time. The facilitator management unit can also adjust the progress of the discussion based on the emotion estimation data. For example, it can urge participants who are getting emotional to calm down. The facilitator management unit can also adjust the direction of the discussion based on the emotion estimation data. For example, if emotions are getting high, it can temporarily pause the discussion and allow time for participants to calm down. This allows the emotional state of participants to be appropriately managed and the discussion to remain calm.

[0095] The facilitator management unit can summarize what participants say in real time as the discussion progresses and provide feedback to other participants. For example, the generative AI can analyze what is being said, summarize the main points, and present them to other participants. The facilitator management unit can also adjust the progress of the discussion based on the summarized content. For example, it can decide when to move on to the next topic based on the summarized content. The facilitator management unit can also save the summarized content as minutes and refer to them later. This makes it possible to efficiently grasp the content of the discussion and improve the quality of the discussion.

[0096] The facilitator management unit can use the emotion estimation function to grasp the emotional state of participants as the discussion progresses and adjust the progress of the discussion at appropriate times. For example, the generative AI analyzes participants' facial expressions and tone of voice to grasp their emotional state in real time. The facilitator management unit can also adjust the progress of the discussion based on the emotion estimation data. For example, it can urge participants who are getting emotional to calm down. The facilitator management unit can also adjust the direction of the discussion based on the emotion estimation data. For example, if emotions are getting high, it can temporarily pause the discussion and allow time for participants to calm down. This allows the emotional state of participants to be appropriately managed and the discussion to remain calm.

[0097] The facilitator management unit can cluster participants' comments in real time as the discussion progresses and link related ideas. For example, the generative AI analyzes the comments and displays them as groups of related ideas. The facilitator management unit can also adjust the progress of the discussion based on the clustered content. For example, it can set the next agenda item based on related ideas. The facilitator management unit can also save the clustered content as minutes and refer to them later. This makes it possible to efficiently organize the content of the discussion and improve the quality of the discussion.

[0098] The facilitator management unit can use the emotion estimation function to grasp the emotional state of participants as the discussion progresses and adjust the direction of the discussion at the appropriate time. For example, the generative AI analyzes participants' facial expressions and tone of voice to grasp their emotional state in real time. The facilitator management unit can also adjust the progress of the discussion based on the emotion estimation data. For example, it can urge participants who are getting emotional to calm down. The facilitator management unit can also adjust the direction of the discussion based on the emotion estimation data. For example, if emotions are getting high, it can temporarily pause the discussion and allow time for participants to calm down. This allows the emotional state of participants to be appropriately managed and the discussion to remain calm.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The facilitator manager manages the progress of the discussion. For example, the facilitator manager manages the progress of the discussion from start to finish, and adjusts the order in which topics are presented and people speak. The facilitator manager can also analyze the facial expressions and tone of voice of participants as the discussion progresses and suggest breaks at appropriate times. Furthermore, the facilitator manager can refer to related past discussions and data in real time to supplement the flow of the discussion. Step 2: The secretarial management unit records the contents of the discussion. For example, the secretarial management unit converts comments made during the discussion into text in real time and creates minutes. The secretarial management unit can also automatically highlight important keywords and phrases when recording the contents of the discussion. Furthermore, when recording the contents of the discussion, the secretarial management unit can color-code each speaker to make it easier to understand visually. Step 3: The Timekeeper Management Unit manages the time for the discussion. For example, the Timekeeper Management Unit manages the time allocation for each agenda item and prompts participants to move on to the next agenda item when time has passed. The Timekeeper Management Unit can also visualize the progress of the discussion so that participants can intuitively understand it. Furthermore, the Timekeeper Management Unit can share the progress of the discussion with other meeting participants and adjust the time allocation based on their feedback.

[0101] 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.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0103] 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.

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

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

[0106] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0107] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

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

[0109] 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).

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

[0111] 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.

[0112] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0113] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0114] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0115] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0116] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires 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.

[0117] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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 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.

[0118] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may 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.

[0119] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0120] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0127] 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.

[0128] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0129] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0130] 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.

[0131] 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.

[0132] 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 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.

[0133] 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.

[0134] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0145] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0146] 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.

[0147] 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.

[0148] 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 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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, to avoid confusion and 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.

[0167] 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. [Explanation of symbols]

[0168] 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 system that uses generative AI to centrally manage and execute the roles of discussion moderator, secretary, and timekeeper, The moderator management department manages the progress of the discussion, A secretarial management department that records the contents of the discussions; A timekeeper management unit that manages the time of the discussion. A system characterized by:

2. The facilitator management unit Analyze participants' facial expressions and tone of voice to suggest breaks at appropriate times 2. The system of claim 1.

3. The secretary management unit Automatically highlight important keywords and phrases as you record the content of said discussions 2. The system of claim 1.

4. The timekeeper management unit When managing the time for the discussion, the progress of each agenda item is analyzed in real time and the time allocation is dynamically adjusted.

2. The system of claim 1.

5. The facilitator management unit When adjusting the order of speaking, consider the emotional state of the participants and provide an environment where they can speak easily.

2. The system of claim 1.

6. The facilitator management unit Understand the emotional state of the participants and manage the discussion to prevent it from becoming too heated.

2. The system of claim 1.

7. The secretary management unit Recording participants' emotional responses to the content of the discussion for future reference 2. The system of claim 1.

8. The timekeeper management unit Suggesting breaks when participants lose focus 2. The system of claim 1.

Images