system

Abstract

The system according to this embodiment aims to improve the efficiency of meetings and enhance participant engagement. [Solution] The system according to the embodiment comprises an analysis unit, an extraction unit, a monitoring unit, a facilitation unit, and a whiteboard unit. The analysis unit analyzes the meeting content in real time. The extraction unit extracts important points and action items based on the content analyzed by the analysis unit. The monitoring unit monitors the frequency of each member's speech and their emotions. The facilitation unit promotes a balanced discussion based on the information monitored by the monitoring unit. The whiteboard unit visualizes ideas using a virtual whiteboard.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the efficiency of meetings and the engagement of participants have not been sufficiently achieved, and there is room for improvement.

[0005] The system according to the embodiment aims to improve the efficiency of meetings and the engagement of participants.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an extraction unit, a monitoring unit, a facilitation unit, and a whiteboard unit. The analysis unit analyzes the meeting content in real time. The extraction unit extracts important points and action items based on the content analyzed by the analysis unit. The monitoring unit monitors the frequency of each member's contributions and their emotions. The facilitation unit promotes a balanced discussion based on the information monitored by the monitoring unit. The whiteboard unit visualizes ideas using a virtual whiteboard. [Effects of the Invention]

[0007] The system according to this embodiment can improve meeting efficiency and enhance participant engagement. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

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

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

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

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The hybrid facilitator according to an embodiment of the present invention is an innovative meeting support system that integrates a satellite office with generative AI. The hybrid facilitator aims to reduce unnecessary meetings, improve meeting efficiency, and enhance participant engagement. Specifically, it has the following functions: First, it has a function to analyze meeting content in real time and automatically extract important points and action items. This reduces wasted time in meetings and enables efficient communication. For example, the generative AI analyzes what is said during a meeting and automatically lists important discussion points. Next, it has a function to monitor the frequency of participation and emotions of each member and promote balanced discussion. This makes it easier for members in remote locations to actively participate. For example, the generative AI analyzes the number of times each member has participated and their emotions, and encourages members who have not participated to speak up. Furthermore, it has a function to visualize and share ideas using a virtual whiteboard. This promotes creative brainstorming. For example, the generative AI reflects what has been said on the whiteboard in real time, visually organizing ideas. It also has a function to provide privacy protection options and ensure data security. This prevents meeting content from being leaked to external parties. For example, the generating AI encrypts meeting content, ensuring only specific members can access it. Furthermore, it has a feature that allows users to adjust the level of AI intervention according to their needs. This enables customization to match the level of support users require. For instance, the generating AI adjusts the frequency and level of detail in analyzing speech based on user settings. Finally, it provides a user-friendly interface to reduce user stress, making the system easy for anyone to use. For example, the generating AI provides intuitive operation guides, ensuring users can operate it without confusion. Thus, Hybrid Facilitator is an innovative meeting support system designed to reduce unnecessary meetings, improve meeting efficiency, and enhance participant engagement. As a result, Hybrid Facilitator can improve meeting quality and achieve effective facilitation.

[0029] The hybrid facilitator according to this embodiment comprises an analysis unit, an extraction unit, a monitoring unit, a facilitation unit, and a whiteboard unit. The analysis unit analyzes the meeting content in real time. The analysis unit analyzes the content of statements made during the meeting using, for example, a generative AI, and extracts important information. The analysis unit can have the generative AI analyze the content of statements and automatically list important discussion points. The analysis unit can also have the generative AI analyze the content of statements, estimate the speaker's intent, and highlight important points based on the estimated intent. The analysis unit can also have the generative AI analyze the content of statements and identify new discussion points by comparing them with past meeting content. The extraction unit extracts important points and action items based on the content analyzed by the analysis unit. The extraction unit extracts important points and action items using, for example, a generative AI, and lists them. The extraction unit can have the generative AI estimate the speaker's intent, extract important points, and list them. The extraction unit can also have the generative AI identify new action items by comparing them with past meeting content. The extraction unit can use a generating AI to estimate the speaker's level of expertise and adjust the extraction results based on the estimated expertise level. The monitoring unit monitors the frequency of each member's speech and their emotions. The monitoring unit, for example, uses a generating AI to analyze each member's frequency of speech and emotions to promote a balanced discussion. The monitoring unit can use a generating AI to analyze each member's number of speeches and emotions and encourage members who speak less to speak. The monitoring unit can also use a generating AI to monitor each member's frequency of speech and emotions, estimate the speaker's intention, and adjust the monitoring results based on the estimated intention. The monitoring unit can also use a generating AI to monitor each member's frequency of speech and emotions and identify new speech patterns by comparing them with past speech history. The facilitation unit promotes a balanced discussion based on the information monitored by the monitoring unit. The facilitation unit, for example, uses a generating AI to estimate the speaker's intention and promotes the discussion based on the estimated intention. The facilitation unit can use a generating AI to estimate the speaker's intention and adjust the order of speeches to promote a balanced discussion.The facilitator unit can use generative AI to estimate the speaker's intent and prompt them to speak at the appropriate time to ensure smooth discussion. The facilitator unit can also use generative AI to estimate the speaker's intent and adjust the content of their statements to balance the discussion. The whiteboard unit utilizes a virtual whiteboard to visualize ideas. For example, the whiteboard unit can use generative AI to reflect the content of statements on the whiteboard in real time, visually organizing ideas. The whiteboard unit can use generative AI to reflect the content of statements on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method based on the estimated intent. The whiteboard unit can also use generative AI to reflect the content of statements on the whiteboard in real time and identify new visualization methods by comparing them with past whiteboard content. The whiteboard unit can also use generative AI to reflect the content of statements on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on the estimated level of expertise. As a result, the hybrid facilitator according to the embodiment can perform real-time analysis of meeting content, extract key points and action items, monitor speaking frequency and sentiment, facilitate balanced discussions, and visualize ideas.

[0030] The analysis unit analyzes meeting content in real time. For example, it uses generative AI to analyze what is said during a meeting and extract important information. Specifically, the generative AI uses speech recognition technology to convert what is said into text, and then analyzes that text using natural language processing technology. The generative AI understands the context of what is said and extracts important keywords and phrases. Furthermore, the generative AI can also analyze the tone and emotion of what is said in order to estimate the speaker's intent. For example, it can identify points or concerns that the speaker wants to emphasize and list important discussion points based on that. The analysis unit can also use the generative AI's analysis of what is said to identify new discussion points by comparing it with past meeting content. This allows for a real-time understanding of the meeting's progress and enables efficient discussion without missing important information. In addition, the analysis unit can use the generative AI's analysis of what is said to estimate the speaker's intent and highlight important points based on that estimated intent. For example, it can highlight ideas or solutions proposed by the speaker and convey their importance to other members. This allows the analysis unit to improve the efficiency of meetings and effectively share important information.

[0031] The extraction unit extracts key points and action items based on the analysis performed by the analysis unit. For example, the extraction unit uses generative AI to extract and list key points and action items. Specifically, the generative AI identifies important keywords and phrases based on data provided by the analysis unit and lists them. The generative AI can also estimate the speaker's intent and extract and list key points. For example, it can identify specific action items and next steps proposed by the speaker and add them to the list. Furthermore, the generative AI can identify new action items by comparing them with past meeting content. This allows for understanding the progress of the meeting and clarifying the specific actions to take next. The extraction unit can also use the generative AI to estimate the speaker's level of expertise and adjust the extraction results based on the estimated expertise level. For example, it can prioritize the opinions of highly knowledgeable speakers and list them as key points. This allows the extraction unit to improve meeting efficiency and effectively share important information.

[0032] The monitoring unit monitors the frequency of each member's participation and their emotions. For example, it uses generative AI to analyze each member's participation and emotions, promoting balanced discussions. Specifically, the generative AI uses speech recognition technology to convert each member's statements into text, analyzes that text, and measures participation frequency. Furthermore, the generative AI analyzes the tone and emotion of the statements to understand each member's emotional state. For example, to encourage a less active member to participate, the generative AI analyzes that member's emotional state and prompts them to speak at the appropriate time. The monitoring unit can also use the generative AI to monitor each member's participation and emotions, estimate the speaker's intent, and adjust the monitoring results based on the estimated intent. For example, if a particular member wants to emphasize an important point, the monitoring unit can understand that intent and communicate its importance to other members. This allows the monitoring unit to promote balanced discussions and improve meeting efficiency. Additionally, the monitoring unit can use the generative AI to monitor each member's participation and emotions, and compare it with past participation history to identify new participation patterns. This allows for real-time monitoring of the meeting's progress, enabling efficient discussions without missing important information.

[0033] The Facilitation Department promotes balanced discussion based on information monitored by the Monitoring Department. For example, the Facilitation Department uses Generative AI to estimate the speaker's intent and facilitates the discussion based on that estimated intent. Specifically, the Generative AI understands the context of what is said and estimates the speaker's intent. For example, it can emphasize ideas or solutions proposed by the speaker and convey their importance to other members. The Facilitation Department can adjust the order of statements to facilitate a balanced discussion based on the Generative AI's estimation of the speaker's intent. For example, if a particular member wants to emphasize an important point, the Facilitation Department can understand that intent and convey its importance to other members. Furthermore, the Generative AI can prompt participation at the appropriate time to ensure the smooth progress of the discussion. For example, to encourage a member who is not speaking much, the Generative AI can analyze that member's emotional state and prompt them to speak at the appropriate time. The Facilitation Department can also adjust the content of statements to balance the discussion based on the Generative AI's estimation of the speaker's intent. In this way, the Facilitation Department can promote balanced discussion and improve the efficiency of meetings.

[0034] The Whiteboard Department utilizes virtual whiteboards to visualize ideas. For example, it uses generative AI to reflect spoken content on a whiteboard in real time, visually organizing ideas. Specifically, the generative AI converts spoken content into text, analyzes that text, and identifies important keywords and phrases. The generative AI can estimate the speaker's intent and adjust the visualization method based on that estimation. For example, it can visually highlight ideas and solutions proposed by the speaker to emphasize their importance and communicate it to other members. The Whiteboard Department can also use the generative AI to reflect spoken content on the whiteboard in real time and compare it with past whiteboard content to identify new visualization methods. This allows for real-time monitoring of the meeting's progress and efficient discussion without missing important information. Furthermore, the Whiteboard Department can use the generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on that estimation. For example, it can prioritize the opinions of highly knowledgeable speakers and visualize them as important points. This allows the Whiteboard Department to improve meeting efficiency and effectively share important information.

[0035] The encryption unit provides privacy protection options and ensures data security. For example, the encryption unit can encrypt meeting content using generative AI, allowing only specific members to access it. The encryption unit can also have generative AI encrypt meeting content and anonymize the data. The encryption unit can also have generative AI encrypt meeting content and implement access control. The encryption unit can also have generative AI encrypt meeting content and ensure data security using encryption algorithms. This ensures data security and prevents meeting content from being leaked externally. Some or all of the above processes in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input meeting content into generative AI and have the generative AI perform the encryption process.

[0036] The adjustment unit adjusts the level of AI intervention according to the user's needs. The adjustment unit adjusts the level of intervention according to the user's settings, for example, using a generating AI. The adjustment unit allows the generating AI to adjust the frequency and level of detail of speech analysis according to the user's settings. The adjustment unit also allows the generating AI to set the frequency of intervention according to the user's needs. The adjustment unit also allows the generating AI to adjust the depth of intervention according to the user's needs. This makes it possible to customize the system according to the level of support the user desires. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input user setting data into the generating AI and have the generating AI perform the adjustment of the intervention level.

[0037] The interface unit provides a user-friendly interface, reducing user stress. For example, the interface unit uses generative AI to provide intuitive operation guides, enabling users to operate without confusion. The interface unit's generative AI can analyze user actions and provide optimal operation guides. The interface unit's generative AI can also analyze user action history and customize operation guides. Furthermore, the interface unit's generative AI can analyze user actions in real time and provide operation guides. This makes the system easily accessible to everyone. Some or all of the above-described processes in the interface unit may be performed using AI, or without AI. For example, the interface unit can input user action data into the generative AI and have the generative AI provide operation guides.

[0038] The analysis unit can analyze the content of speeches during a meeting and automatically list important discussion points. For example, the analysis unit can use a generative AI to analyze the content of speeches and extract important discussion points. The analysis unit can use a generative AI to analyze the content of speeches and list important discussion points. The analysis unit can also use a generative AI to analyze the content of speeches and identify the focus of the discussion. The analysis unit can also use a generative AI to analyze the content of speeches and evaluate the depth of the discussion. This makes meetings more efficient by automatically listing important discussion points. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of speeches during a meeting into a generative AI and have the generative AI extract important discussion points.

[0039] The monitoring unit can analyze the number of times each member speaks and their emotions, and encourage members who speak infrequently to speak. For example, the monitoring unit can use a generative AI to analyze the number of times each member speaks and encourage members who speak infrequently to speak. The monitoring unit can use a generative AI to analyze the number of times each member speaks and encourage members who speak infrequently to speak. The monitoring unit can also use a generative AI to analyze the emotions of each member and encourage members who speak infrequently to speak. The monitoring unit can use a generative AI to analyze the number of times each member speaks and their emotions, and encourage members who speak infrequently to speak. This promotes a balanced discussion by encouraging members who speak infrequently to speak. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform speech promotion.

[0040] The whiteboard section can reflect spoken content on the whiteboard in real time, allowing for the visual organization of ideas. For example, the whiteboard section can use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. The whiteboard section can use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. The whiteboard section can also use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. This allows for the visual organization of ideas by reflecting spoken content on the whiteboard in real time. Some or all of the above-described processes in the whiteboard section may be performed using AI, for example, or without AI. For example, the whiteboard section can input spoken content into a generative AI and have the generative AI perform the visual organization.

[0041] The analysis unit can analyze the content of speeches during a meeting, estimate the speaker's intent, and highlight important points based on the estimated intent. For example, the analysis unit can use a generative AI to analyze the content of speeches, estimate the speaker's intent, and highlight important points. The analysis unit can have the generative AI analyze the content of speeches, automatically extract points that the speaker wants to emphasize, and reflect them in the meeting summary. The analysis unit can also have the generative AI estimate the speaker's intent and display important discussion points in real time. The analysis unit can also have the generative AI analyze the content of speeches and automatically present relevant materials and data based on the speaker's intent. This clarifies the main points of the meeting by highlighting important points based on the speaker's intent. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of speeches into a generative AI and have the generative AI perform the estimation of the speaker's intent and the highlighting of important points.

[0042] The analysis unit can analyze the content of statements made during a meeting and identify new discussion points by comparing them with past meeting content. For example, the analysis unit can use a generative AI to analyze the content of statements and identify new discussion points by comparing them with past meeting content. The analysis unit can have the generative AI retrieve past meeting content from a database and identify new discussion points by comparing them with the current meeting content. The analysis unit can also have the generative AI extract unresolved discussion points from past meetings and suggest that they be discussed again in the current meeting. The analysis unit can also have the generative AI analyze past meeting content and highlight new discussion points that have emerged in the current meeting. This allows for the identification of new discussion points by comparing them with past meeting content. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past meeting content into the generative AI and have the generative AI identify new discussion points.

[0043] The analysis unit can analyze the content of statements made during a meeting, estimate the speaker's level of expertise, and adjust the analysis results based on the estimated level of expertise. For example, the analysis unit can use a generative AI to analyze the content of statements, estimate the speaker's level of expertise, and adjust the analysis results. The analysis unit can use a generative AI to analyze the content of statements and estimate the level of expertise from the frequency of the speaker's use of technical terms. The analysis unit can also use a generative AI to refer to the speaker's past statement history, estimate the level of expertise, and adjust the analysis results. The analysis unit can also use a generative AI to display the analysis results in an easy-to-understand manner based on the speaker's level of expertise. This makes the analysis results more appropriate by adjusting them based on the speaker's level of expertise. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of statements into a generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the analysis results.

[0044] The analysis unit can analyze the content of statements made during a meeting and adjust the analysis results considering the geographical background of the speaker. For example, the analysis unit can use a generative AI to analyze the content of statements and adjust the analysis results considering the geographical background of the speaker. The analysis unit can have the generative AI consider the geographical background of the speaker and reflect region-specific information in the analysis results. The analysis unit can also have the generative AI consider the geographical background of the speaker and automatically present region-related data. The analysis unit can also have the generative AI consider the geographical background of the speaker and display the analysis results in a format appropriate for the region. In this way, by considering the geographical background of the speaker, analysis results that reflect region-specific information can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the content of statements into the generative AI and have the generative AI perform the consideration of geographical background and the adjustment of analysis results.

[0045] The analysis unit can analyze the content of statements made during a meeting and supplement the analysis results by referring to the speaker's social media activity. For example, the analysis unit can use a generative AI to analyze the content of statements and supplement the analysis results by referring to the speaker's social media activity. The analysis unit can have the generative AI refer to the speaker's social media activity and supplement information related to the content of the statements. The analysis unit can also have the generative AI analyze the speaker's social media activity and present topics related to the content of the statements. The analysis unit can also have the generative AI refer to the speaker's social media activity and automatically display data related to the content of the statements. This allows information related to the content of the statements to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of statements into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of analysis results.

[0046] The extraction unit can estimate the speaker's intent when extracting important points and action items, and adjust the extraction results based on the estimated intent. For example, the extraction unit can use a generative AI to estimate the speaker's intent and extract important points and action items. The extraction unit can use a generative AI to estimate the speaker's intent, extract important points, and list them. The extraction unit can also use a generative AI to estimate the speaker's intent, extract action items, and reflect them in the meeting summary. The extraction unit can also use a generative AI to estimate the speaker's intent and adjust the extraction results based on that intent. By adjusting the extraction results based on the speaker's intent, more appropriate points and action items are extracted. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into a generative AI and have the generative AI perform intent estimation and adjustment of the extraction results.

[0047] The extraction unit can identify new action items by comparing them with past meeting content when extracting important points and action items. For example, the extraction unit can use a generative AI to analyze the content of statements and identify new action items by comparing them with past meeting content. The extraction unit can have the generative AI retrieve past meeting content from a database and identify new action items by comparing them with the current meeting content. The extraction unit can also have the generative AI extract unresolved action items from past meetings and suggest that they be discussed again in the current meeting. The extraction unit can also have the generative AI analyze past meeting content and highlight action items that have newly emerged in the current meeting. This allows for the identification of new action items by comparing them with past meeting content. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past meeting content into the generative AI and have the generative AI identify new action items.

[0048] The extraction unit can estimate the speaker's level of expertise when extracting important points and action items, and adjust the extraction results based on the estimated level of expertise. For example, the extraction unit can use a generative AI to analyze the content of the speech, estimate the speaker's level of expertise, and adjust the extraction results. The extraction unit can use the generative AI to estimate the speaker's level of expertise, extract important points, and list them. The extraction unit can also use the generative AI to estimate the speaker's level of expertise, extract action items, and reflect them in the meeting summary. The extraction unit can also use the generative AI to estimate the speaker's level of expertise and adjust the extraction results based on that level of expertise. By adjusting the extraction results based on the speaker's level of expertise, more appropriate points and action items are extracted. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into the generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the extraction results.

[0049] The extraction unit can adjust the extraction results by considering the speaker's geographical background when extracting important points and action items. For example, the extraction unit can analyze the content of the speech using a generation AI and adjust the extraction results by considering the speaker's geographical background. The extraction unit can have the generation AI consider the speaker's geographical background and reflect region-specific information in the extraction results. The extraction unit can also have the generation AI consider the speaker's geographical background and automatically present region-related data. The extraction unit can also have the generation AI consider the speaker's geographical background and display the extraction results in a format appropriate for the region. As a result, by considering the speaker's geographical background, extraction results that reflect region-specific information can be obtained. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into the generation AI and have the generation AI perform the consideration of geographical background and adjustment of the extraction results.

[0050] The extraction unit can supplement its extraction results by referring to the speaker's social media activity when extracting important points and action items. For example, the extraction unit can analyze the content of a statement using a generative AI and supplement the extraction results by referring to the speaker's social media activity. The extraction unit can use the generative AI to refer to the speaker's social media activity and supplement information related to the content of the statement. The extraction unit can also use the generative AI to analyze the speaker's social media activity and present topics related to the content of the statement. The extraction unit can also use the generative AI to refer to the speaker's social media activity and automatically display data related to the content of the statement. This allows for supplementation of information related to the content of the statement by referring to the speaker's social media activity. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of a statement into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of the extraction results.

[0051] The monitoring unit can monitor the frequency of each member's speech and their emotions, estimate the speaker's intent, and adjust the monitoring results based on the estimated intent. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor each member's emotions, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's intent. By adjusting the monitoring results based on the speaker's intent, more appropriate monitoring becomes possible. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform intent estimation and adjustment of the monitoring results.

[0052] The monitoring unit can monitor each member's frequency of speaking and emotions, and identify new speaking patterns by comparing them with their past speaking history. For example, the monitoring unit can use a generative AI to monitor each member's frequency of speaking and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can use a generative AI to monitor each member's frequency of speaking and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can also use a generative AI to monitor each member's emotions and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can also use a generative AI to monitor each member's frequency of speaking and emotions and identify new speaking patterns by comparing them with their past speaking history. This allows for the identification of new speaking patterns by comparing them with past speaking history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speaking data into a generative AI and have the generative AI perform the identification of speaking patterns.

[0053] The monitoring unit can monitor the frequency of each member's speech and their emotions, estimate the speaker's level of expertise, and adjust the monitoring results based on the estimated level of expertise. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor each member's emotions, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's level of expertise. This allows for more appropriate monitoring by adjusting the monitoring results based on the speaker's level of expertise. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform the estimation of expertise levels and the adjustment of monitoring results.

[0054] The monitoring unit can monitor the frequency of each member's speech and their emotions, and adjust the monitoring results considering the speaker's geographical background. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can use a generative AI to monitor the frequency of each member's speech and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can also use a generative AI to monitor each member's emotions and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's geographical background. By considering the speaker's geographical background, monitoring results that reflect region-specific information can be obtained. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform the consideration of geographical background and the adjustment of monitoring results.

[0055] The monitoring unit can monitor each member's frequency of speaking and their emotions, and supplement the monitoring results by referring to the speaker's social media activity. For example, the monitoring unit can use a generative AI to monitor each member's frequency of speaking and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can have the generative AI monitor each member's frequency of speaking and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can also have the generative AI monitor each member's emotions and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can have the generative AI monitor each member's frequency of speaking and their emotions and supplement the monitoring results based on the speaker's social media activity. This allows information related to the content of the statements to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's statement data into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of monitoring results.

[0056] The facilitator can estimate the speaker's intent and adjust the facilitation method based on the estimated intent when promoting a balanced discussion. For example, the facilitator can use generative AI to estimate the speaker's intent and adjust the order of statements to promote a balanced discussion. The facilitator can use generative AI to estimate the speaker's intent and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's intent and prompt statements at the appropriate time to ensure a smooth discussion. The facilitator can also use generative AI to estimate the speaker's intent and adjust the content of statements to balance the discussion. This allows for more effective discussion facilitation by adjusting the facilitation method based on the speaker's intent. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into generative AI and have the generative AI perform intent estimation and adjustment of the facilitation method.

[0057] The facilitator can identify new discussion points by comparing them with past discussion history when promoting a balanced discussion. For example, the facilitator can use generative AI to retrieve past discussion history from a database and identify new discussion points by comparing them with the current discussion content. The facilitator can also have the generative AI extract unresolved discussion points from past discussions and suggest that they be discussed again in the current discussion. The facilitator can also have the generative AI analyze past discussion history and highlight new discussion points that have emerged in the current discussion. This allows for the identification of new discussion points by comparing them with past discussion history. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input past discussion history into the generative AI and have the generative AI identify new discussion points.

[0058] The facilitator can estimate the speaker's level of expertise and adjust the facilitation method based on the estimated level of expertise when promoting a balanced discussion. For example, the facilitator can use generative AI to estimate the speaker's level of expertise and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and prompt statements at appropriate times to ensure a smooth discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and adjust the content of statements to balance the discussion. This allows for more appropriate discussion facilitation by adjusting the facilitation method based on the speaker's level of expertise. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into generative AI and have the generative AI perform the estimation of expertise levels and adjustment of facilitation methods.

[0059] The facilitator can adjust its facilitation methods by considering the geographical background of the speakers when promoting a balanced discussion. For example, the facilitator can use generative AI to consider the geographical background of the speakers and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and reflect region-specific information in the discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and automatically present region-related data. This makes it possible to promote a discussion that reflects region-specific information by considering the geographical background of the speakers. Some or all of the above processing in the facilitator may be performed using AI, for example, or not using AI. For example, the facilitator can input the content of the statements into the generative AI and have the generative AI perform the consideration of geographical background and adjustment of the facilitation method.

[0060] The facilitator can supplement its facilitation methods by referencing the speakers' social media activity when promoting a balanced discussion. For example, the facilitator can use generative AI to reference the speakers' social media activity and adjust the order of statements to promote a balanced discussion. The facilitator can have the generative AI reference the speakers' social media activity and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI reference the speakers' social media activity and reflect information related to the content of the statements in the discussion. The facilitator can also have the generative AI reference the speakers' social media activity and automatically present data related to the content of the statements. This allows for supplementation of information related to the content of the statements by referencing the speakers' social media activity. Some or all of the above processing in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of facilitation methods.

[0061] The whiteboard unit can reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method based on the estimated intent. For example, the whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method. The whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method. The whiteboard unit can also use a generative AI to estimate the speaker's intent and visually organize the spoken content based on that intent. The whiteboard unit can also use a generative AI to estimate the speaker's intent and display relevant materials and data on the whiteboard based on that intent. This allows for more appropriate visualization by adjusting the visualization method based on the speaker's intent. Some or all of the above-described processes in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generative AI and have the generative AI perform intent estimation and visualization method adjustment.

[0062] The whiteboard unit can reflect spoken content on the whiteboard in real time and identify new visualization methods by comparing it with past whiteboard content. For example, the whiteboard unit can use a generation AI to retrieve past whiteboard content from a database and identify new visualization methods by comparing it with the current spoken content. The whiteboard unit can also have the generation AI retrieve past whiteboard content from a database and identify new visualization methods by comparing it with the current spoken content. The whiteboard unit can also have the generation AI analyze past whiteboard content and propose new visualization methods based on the current spoken content. The whiteboard unit can also have the generation AI refer to past whiteboard content and present visualization methods related to the current spoken content. This allows for the identification of new visualization methods by comparing them with past whiteboard content. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input past whiteboard content into the generation AI and have the generation AI identify new visualization methods.

[0063] The whiteboard unit can reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on the estimated level of expertise. For example, the whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method. The whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method. The whiteboard unit can also use a generative AI to estimate the speaker's level of expertise and visually organize the spoken content based on that level of expertise. The whiteboard unit can also use a generative AI to estimate the speaker's level of expertise and display relevant materials and data on the whiteboard based on that level of expertise. This allows for more appropriate visualization by adjusting the visualization method based on the speaker's level of expertise. Some or all of the above-described processes in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the visualization method.

[0064] The whiteboard unit can reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. For example, the whiteboard unit can use a generation AI to reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. The whiteboard unit can use a generation AI to reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. The whiteboard unit can also use a generation AI to consider the speaker's geographical background and display region-specific information on the whiteboard. The whiteboard unit can also use a generation AI to consider the speaker's geographical background and display region-related data on the whiteboard. This makes it possible to visualize region-specific information by considering the speaker's geographical background. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generation AI and have the generation AI consider geographical background and adjust the visualization method.

[0065] The whiteboard unit can reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. For example, the whiteboard unit can use a generative AI to reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. The whiteboard unit can have a generative AI reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. The whiteboard unit can also have a generative AI refer to the speaker's social media activity and display information related to the content of the statement on the whiteboard. The whiteboard unit can also have a generative AI refer to the speaker's social media activity and display data related to the content of the statement on the whiteboard. This allows information related to the content of the statement to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input the content of a statement into a generative AI and have the generative AI perform the referencing of social media activity and the supplementation of the visualization method.

[0066] The encryption unit can estimate the speaker's intent when encrypting meeting content and adjust the encryption method based on the estimated intent. For example, the encryption unit can use a generative AI to estimate the speaker's intent and encrypt the meeting content. The encryption unit can use a generative AI to estimate the speaker's intent and encrypt the meeting content based on that intent. The encryption unit can also use a generative AI to estimate the speaker's intent and adjust the encryption strength based on that intent. The encryption unit can also use a generative AI to estimate the speaker's intent and set the encryption range based on that intent. This allows for more appropriate encryption by adjusting the encryption method based on the speaker's intent. Some or all of the above-described processes in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input the meeting content into a generative AI and have the generative AI perform intent estimation and encryption method adjustment.

[0067] The encryption unit can identify a new encryption method by comparing it with past encryption history when encrypting meeting content. For example, the encryption unit can use a generative AI to retrieve past encryption history from a database and identify a new encryption method by comparing it with the current meeting content. The encryption unit can also have the generative AI analyze past encryption history and propose the optimal encryption method based on the current meeting content. The encryption unit can also have the generative AI refer to past encryption history and present encryption methods relevant to the current meeting content. This allows for the identification of a new encryption method by comparing it with past encryption history. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input past encryption history into the generative AI and have the generative AI identify a new encryption method.

[0068] The encryption unit can adjust the encryption method when encrypting meeting content, taking into account the geographical background of the speakers. For example, the encryption unit can use a generation AI to consider the geographical background of the speakers and encrypt the meeting content. The encryption unit can use a generation AI to consider the geographical background of the speakers and reflect region-specific information in the encryption. The encryption unit can also use a generation AI to consider the geographical background of the speakers and encrypt region-related data. The encryption unit can also use a generation AI to consider the geographical background of the speakers and set an encryption method appropriate for the region. This makes it possible to encrypt data that reflects region-specific information by considering the geographical background of the speakers. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input the meeting content into a generation AI and have the generation AI perform the consideration of geographical background and adjustment of the encryption method.

[0069] The adjustment unit can estimate the speaker's intent and adjust the intervention level based on the estimated intent when adjusting the AI ​​intervention level. For example, the adjustment unit can use a generative AI to estimate the speaker's intent and adjust the AI ​​intervention level. The adjustment unit can have the generative AI estimate the speaker's intent and adjust the AI ​​intervention level based on that intent. The adjustment unit can also have the generative AI estimate the speaker's intent and set the frequency of intervention based on that intent. The adjustment unit can also have the generative AI estimate the speaker's intent and adjust the level of detail of the intervention based on that intent. By adjusting the intervention level based on the speaker's intent, more appropriate intervention becomes possible. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the utterance into the generative AI and have the generative AI perform intent estimation and intervention level adjustment.

[0070] The adjustment unit can identify a new intervention level by comparing it with past intervention history when adjusting the AI's intervention level. For example, the adjustment unit can use a generating AI to retrieve past intervention history from a database and identify a new intervention level by comparing it with the current meeting content. The adjustment unit can have the generating AI retrieve past intervention history from a database and identify a new intervention level by comparing it with the current meeting content. The adjustment unit can also have the generating AI analyze past intervention history and propose an optimal intervention level based on the current meeting content. The adjustment unit can also have the generating AI refer to past intervention history and present an intervention level relevant to the current meeting content. This allows for the identification of a new intervention level by comparing it with past intervention history. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input past intervention history into the generating AI and have the generating AI perform the identification of a new intervention level.

[0071] The adjustment unit can adjust the AI ​​intervention level by considering the speaker's geographical background when adjusting the AI ​​intervention level. For example, the adjustment unit can use a generative AI to consider the speaker's geographical background and adjust the AI ​​intervention level. The adjustment unit can have the generative AI consider the speaker's geographical background and reflect region-specific information in the intervention level. The adjustment unit can also have the generative AI consider the speaker's geographical background and reflect region-related data in the intervention level. The adjustment unit can also have the generative AI consider the speaker's geographical background and set an intervention level appropriate for the region. This makes it possible to implement interventions that reflect region-specific information by considering the speaker's geographical background. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the utterance into the generative AI and have the generative AI perform the consideration of geographical background and the adjustment of the intervention level.

[0072] The interface unit can estimate the speaker's intent and adjust the display method based on the estimated intent when adjusting the interface display method. For example, the interface unit can use a generative AI to estimate the speaker's intent and adjust the interface display method. The interface unit can use a generative AI to estimate the speaker's intent and adjust the interface display method based on that intent. The interface unit can also use a generative AI to estimate the speaker's intent and set the display layout based on that intent. The interface unit can also use a generative AI to estimate the speaker's intent and adjust the level of detail of the display based on that intent. This makes it possible to display more appropriately by adjusting the display method based on the speaker's intent. Some or all of the above processing in the interface unit may be performed using AI, for example, or without using AI. For example, the interface unit can input the utterance content into a generative AI and have the generative AI perform intent estimation and display method adjustment.

[0073] The interface unit can identify new display methods by comparing them with past display history when adjusting the interface display method. For example, the interface unit can use a generation AI to retrieve past display history from a database and identify new display methods by comparing them with the current meeting content. The interface unit can have the generation AI retrieve past display history from a database and identify new display methods by comparing them with the current meeting content. The interface unit can also have the generation AI analyze past display history and propose the optimal display method based on the current meeting content. The interface unit can also have the generation AI refer to past display history and present display methods related to the current meeting content. This allows for the identification of new display methods by comparing them with past display history. Some or all of the above processing in the interface unit may be performed using AI, for example, or without AI. For example, the interface unit can input past display history into the generation AI and have the generation AI perform the identification of new display methods.

[0074] The interface unit can adjust the display method of the interface by taking into account the speaker's geographical background when adjusting the display method. For example, the interface unit can use a generation AI to take into account the speaker's geographical background and adjust the display method of the interface. The interface unit can have the generation AI take into account the speaker's geographical background and reflect region-specific information in the display method. The interface unit can also have the generation AI take into account the speaker's geographical background and reflect region-related data in the display method. The interface unit can also have the generation AI take into account the speaker's geographical background and set a display method appropriate for the region. This makes it possible to display information that reflects region-specific information by taking into account the speaker's geographical background. Some or all of the above processing in the interface unit may be performed using AI, for example, or without using AI. For example, the interface unit can input the content of the speech into the generation AI and have the generation AI perform the consideration of geographical background and adjustment of the display method.

[0075] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0076] Hybrid facilitators can have features that automatically adjust participants' schedules before a meeting starts to make the meeting run more smoothly. For example, a generative AI can analyze each participant's calendar and suggest the optimal meeting time. Furthermore, the generative AI can refer to participants' past meeting history to identify the most efficient meeting times. It can also adjust meeting times considering participants' workloads. This ensures that all participants can participate in the meeting as efficiently as possible.

[0077] Hybrid facilitators can be equipped with features to automatically transcribe and translate meeting content in real time, enabling more effective recording of meeting proceedings. For example, a generative AI can analyze the content of the speech and transcribe it in real time. Furthermore, the generative AI can translate the content into multiple languages ​​and provide it to participants. It can also summarize the content of the speech and distribute it to participants after the meeting. This enables effective communication across language barriers.

[0078] Hybrid facilitators can incorporate features that allow participants to conduct real-time polls and surveys, making meetings more interactive. For example, a generative AI can automatically create polls and surveys during the meeting and distribute them to participants. Furthermore, the generative AI can compile the poll results in real time and display them during the meeting. It can also analyze the survey results and incorporate them into the meeting's progress. This allows all participants to actively engage in the meeting.

[0079] Hybrid facilitators can be equipped with the ability to automatically collect and analyze participant feedback to improve the quality of meetings. For example, a generative AI can send feedback questionnaires to participants after the meeting and collect responses. Furthermore, the generative AI can analyze the feedback to identify areas for improvement in the meeting. It can also adjust the plan for the next meeting based on the feedback. This allows for continuous improvement in the quality of meetings.

[0080] Hybrid facilitators can be equipped with features to automate document sharing during meetings, further enhancing meeting efficiency. For example, a generative AI can automatically collect and distribute documents used during the meeting. Furthermore, the generative AI can analyze the document content and highlight key points. It can also reflect document updates in real time and notify participants. This ensures smooth document sharing and improves meeting efficiency.

[0081] The following briefly describes the processing flow for example form 1.

[0082] Step 1: The analysis unit analyzes the meeting content in real time. The analysis unit uses generative AI to analyze the content spoken during the meeting and extract important information. The analysis unit can use the generative AI to analyze the content spoken and automatically list important discussion points. It can also estimate the speaker's intent and highlight important points based on that estimated intent. Furthermore, it can identify new discussion points by comparing them with past meeting content. Step 2: The extraction unit extracts key points and action items based on the analysis performed by the analysis unit. The extraction unit uses generative AI to extract and list key points and action items. It can estimate the speaker's intent and extract and list key points. It can also identify new action items by comparing them with past meeting content. Furthermore, it can estimate the speaker's level of expertise and adjust the extraction results based on the estimated level of expertise. Step 3: The monitoring unit monitors the frequency of each member's contributions and their emotions. The monitoring unit uses generative AI to analyze the frequency of each member's contributions and their emotions, promoting balanced discussions. By analyzing the number of contributions and emotions, it can encourage members who are not contributing much to speak up. It can also estimate the speaker's intentions and adjust the monitoring results based on those estimations. Furthermore, it can identify new conversational patterns by comparing them with past conversational history. Step 4: The Facilitation Unit promotes a balanced discussion based on the information monitored by the Monitoring Unit. The Facilitation Unit uses Generative AI to estimate the speaker's intent and promotes the discussion based on the estimated intent. It can adjust the order of statements and prompt for statements at the appropriate time to ensure the smooth progress of the discussion. It can also adjust the content of statements to balance the discussion. Step 5: The whiteboard section visualizes ideas using a virtual whiteboard. The whiteboard section uses generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. It can estimate the speaker's intent and adjust the visualization method based on that estimation. It can also identify new visualization methods by comparing them with past whiteboard content. Furthermore, it can estimate the speaker's level of expertise and adjust the visualization method based on that estimation.

[0083] (Example of form 2) The hybrid facilitator according to an embodiment of the present invention is an innovative meeting support system that integrates a satellite office with generative AI. The hybrid facilitator aims to reduce unnecessary meetings, improve meeting efficiency, and enhance participant engagement. Specifically, it has the following functions: First, it has a function to analyze meeting content in real time and automatically extract important points and action items. This reduces wasted time in meetings and enables efficient communication. For example, the generative AI analyzes what is said during a meeting and automatically lists important discussion points. Next, it has a function to monitor the frequency of participation and emotions of each member and promote balanced discussion. This makes it easier for members in remote locations to actively participate. For example, the generative AI analyzes the number of times each member has participated and their emotions, and encourages members who have not participated to speak up. Furthermore, it has a function to visualize and share ideas using a virtual whiteboard. This promotes creative brainstorming. For example, the generative AI reflects what has been said on the whiteboard in real time, visually organizing ideas. It also has a function to provide privacy protection options and ensure data security. This prevents meeting content from being leaked to external parties. For example, the generating AI encrypts meeting content, ensuring only specific members can access it. Furthermore, it has a feature that allows users to adjust the level of AI intervention according to their needs. This enables customization to match the level of support users require. For instance, the generating AI adjusts the frequency and level of detail in analyzing speech based on user settings. Finally, it provides a user-friendly interface to reduce user stress, making the system easy for anyone to use. For example, the generating AI provides intuitive operation guides, ensuring users can operate it without confusion. Thus, Hybrid Facilitator is an innovative meeting support system designed to reduce unnecessary meetings, improve meeting efficiency, and enhance participant engagement. As a result, Hybrid Facilitator can improve meeting quality and achieve effective facilitation.

[0084] The hybrid facilitator according to this embodiment comprises an analysis unit, an extraction unit, a monitoring unit, a facilitation unit, and a whiteboard unit. The analysis unit analyzes the meeting content in real time. The analysis unit analyzes the content of statements made during the meeting using, for example, a generative AI, and extracts important information. The analysis unit can have the generative AI analyze the content of statements and automatically list important discussion points. The analysis unit can also have the generative AI analyze the content of statements, estimate the speaker's intent, and highlight important points based on the estimated intent. The analysis unit can also have the generative AI analyze the content of statements and identify new discussion points by comparing them with past meeting content. The extraction unit extracts important points and action items based on the content analyzed by the analysis unit. The extraction unit extracts important points and action items using, for example, a generative AI, and lists them. The extraction unit can have the generative AI estimate the speaker's intent, extract important points, and list them. The extraction unit can also have the generative AI identify new action items by comparing them with past meeting content. The extraction unit can use a generating AI to estimate the speaker's level of expertise and adjust the extraction results based on the estimated expertise level. The monitoring unit monitors the frequency of each member's speech and their emotions. The monitoring unit, for example, uses a generating AI to analyze each member's frequency of speech and emotions to promote a balanced discussion. The monitoring unit can use a generating AI to analyze each member's number of speeches and emotions and encourage members who speak less to speak. The monitoring unit can also use a generating AI to monitor each member's frequency of speech and emotions, estimate the speaker's intention, and adjust the monitoring results based on the estimated intention. The monitoring unit can also use a generating AI to monitor each member's frequency of speech and emotions and identify new speech patterns by comparing them with past speech history. The facilitation unit promotes a balanced discussion based on the information monitored by the monitoring unit. The facilitation unit, for example, uses a generating AI to estimate the speaker's intention and promotes the discussion based on the estimated intention. The facilitation unit can use a generating AI to estimate the speaker's intention and adjust the order of speeches to promote a balanced discussion.The facilitator unit can use generative AI to estimate the speaker's intent and prompt them to speak at the appropriate time to ensure smooth discussion. The facilitator unit can also use generative AI to estimate the speaker's intent and adjust the content of their statements to balance the discussion. The whiteboard unit utilizes a virtual whiteboard to visualize ideas. For example, the whiteboard unit can use generative AI to reflect the content of statements on the whiteboard in real time, visually organizing ideas. The whiteboard unit can use generative AI to reflect the content of statements on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method based on the estimated intent. The whiteboard unit can also use generative AI to reflect the content of statements on the whiteboard in real time and identify new visualization methods by comparing them with past whiteboard content. The whiteboard unit can also use generative AI to reflect the content of statements on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on the estimated level of expertise. As a result, the hybrid facilitator according to the embodiment can perform real-time analysis of meeting content, extract key points and action items, monitor speaking frequency and sentiment, facilitate balanced discussions, and visualize ideas.

[0085] The analysis unit analyzes meeting content in real time. For example, it uses generative AI to analyze what is said during a meeting and extract important information. Specifically, the generative AI uses speech recognition technology to convert what is said into text, and then analyzes that text using natural language processing technology. The generative AI understands the context of what is said and extracts important keywords and phrases. Furthermore, the generative AI can also analyze the tone and emotion of what is said in order to estimate the speaker's intent. For example, it can identify points or concerns that the speaker wants to emphasize and list important discussion points based on that. The analysis unit can also use the generative AI's analysis of what is said to identify new discussion points by comparing it with past meeting content. This allows for a real-time understanding of the meeting's progress and enables efficient discussion without missing important information. In addition, the analysis unit can use the generative AI's analysis of what is said to estimate the speaker's intent and highlight important points based on that estimated intent. For example, it can highlight ideas or solutions proposed by the speaker and convey their importance to other members. This allows the analysis unit to improve the efficiency of meetings and effectively share important information.

[0086] The extraction unit extracts key points and action items based on the analysis performed by the analysis unit. For example, the extraction unit uses generative AI to extract and list key points and action items. Specifically, the generative AI identifies important keywords and phrases based on data provided by the analysis unit and lists them. The generative AI can also estimate the speaker's intent and extract and list key points. For example, it can identify specific action items and next steps proposed by the speaker and add them to the list. Furthermore, the generative AI can identify new action items by comparing them with past meeting content. This allows for understanding the progress of the meeting and clarifying the specific actions to take next. The extraction unit can also use the generative AI to estimate the speaker's level of expertise and adjust the extraction results based on the estimated expertise level. For example, it can prioritize the opinions of highly knowledgeable speakers and list them as key points. This allows the extraction unit to improve meeting efficiency and effectively share important information.

[0087] The monitoring unit monitors the frequency of each member's participation and their emotions. For example, it uses generative AI to analyze each member's participation and emotions, promoting balanced discussions. Specifically, the generative AI uses speech recognition technology to convert each member's statements into text, analyzes that text, and measures participation frequency. Furthermore, the generative AI analyzes the tone and emotion of the statements to understand each member's emotional state. For example, to encourage a less active member to participate, the generative AI analyzes that member's emotional state and prompts them to speak at the appropriate time. The monitoring unit can also use the generative AI to monitor each member's participation and emotions, estimate the speaker's intent, and adjust the monitoring results based on the estimated intent. For example, if a particular member wants to emphasize an important point, the monitoring unit can understand that intent and communicate its importance to other members. This allows the monitoring unit to promote balanced discussions and improve meeting efficiency. Additionally, the monitoring unit can use the generative AI to monitor each member's participation and emotions, and compare it with past participation history to identify new participation patterns. This allows for real-time monitoring of the meeting's progress, enabling efficient discussions without missing important information.

[0088] The Facilitation Department promotes balanced discussion based on information monitored by the Monitoring Department. For example, the Facilitation Department uses Generative AI to estimate the speaker's intent and facilitates the discussion based on that estimated intent. Specifically, the Generative AI understands the context of what is said and estimates the speaker's intent. For example, it can emphasize ideas or solutions proposed by the speaker and convey their importance to other members. The Facilitation Department can adjust the order of statements to facilitate a balanced discussion based on the Generative AI's estimation of the speaker's intent. For example, if a particular member wants to emphasize an important point, the Facilitation Department can understand that intent and convey its importance to other members. Furthermore, the Generative AI can prompt participation at the appropriate time to ensure the smooth progress of the discussion. For example, to encourage a member who is not speaking much, the Generative AI can analyze that member's emotional state and prompt them to speak at the appropriate time. The Facilitation Department can also adjust the content of statements to balance the discussion based on the Generative AI's estimation of the speaker's intent. In this way, the Facilitation Department can promote balanced discussion and improve the efficiency of meetings.

[0089] The Whiteboard Department utilizes virtual whiteboards to visualize ideas. For example, it uses generative AI to reflect spoken content on a whiteboard in real time, visually organizing ideas. Specifically, the generative AI converts spoken content into text, analyzes that text, and identifies important keywords and phrases. The generative AI can estimate the speaker's intent and adjust the visualization method based on that estimation. For example, it can visually highlight ideas and solutions proposed by the speaker to emphasize their importance and communicate it to other members. The Whiteboard Department can also use the generative AI to reflect spoken content on the whiteboard in real time and compare it with past whiteboard content to identify new visualization methods. This allows for real-time monitoring of the meeting's progress and efficient discussion without missing important information. Furthermore, the Whiteboard Department can use the generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on that estimation. For example, it can prioritize the opinions of highly knowledgeable speakers and visualize them as important points. This allows the Whiteboard Department to improve meeting efficiency and effectively share important information.

[0090] The encryption unit provides privacy protection options and ensures data security. For example, the encryption unit can encrypt meeting content using generative AI, allowing only specific members to access it. The encryption unit can also have generative AI encrypt meeting content and anonymize the data. The encryption unit can also have generative AI encrypt meeting content and implement access control. The encryption unit can also have generative AI encrypt meeting content and ensure data security using encryption algorithms. This ensures data security and prevents meeting content from being leaked externally. Some or all of the above processes in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input meeting content into generative AI and have the generative AI perform the encryption process.

[0091] The adjustment unit adjusts the level of AI intervention according to the user's needs. The adjustment unit adjusts the level of intervention according to the user's settings, for example, using a generating AI. The adjustment unit allows the generating AI to adjust the frequency and level of detail of speech analysis according to the user's settings. The adjustment unit also allows the generating AI to set the frequency of intervention according to the user's needs. The adjustment unit also allows the generating AI to adjust the depth of intervention according to the user's needs. This makes it possible to customize the system according to the level of support the user desires. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input user setting data into the generating AI and have the generating AI perform the adjustment of the intervention level.

[0092] The interface unit provides a user-friendly interface, reducing user stress. For example, the interface unit uses generative AI to provide intuitive operation guides, enabling users to operate without confusion. The interface unit's generative AI can analyze user actions and provide optimal operation guides. The interface unit's generative AI can also analyze user action history and customize operation guides. Furthermore, the interface unit's generative AI can analyze user actions in real time and provide operation guides. This makes the system easily accessible to everyone. Some or all of the above-described processes in the interface unit may be performed using AI, or without AI. For example, the interface unit can input user action data into the generative AI and have the generative AI provide operation guides.

[0093] The analysis unit can analyze the content of speeches during a meeting and automatically list important discussion points. For example, the analysis unit can use a generative AI to analyze the content of speeches and extract important discussion points. The analysis unit can use a generative AI to analyze the content of speeches and list important discussion points. The analysis unit can also use a generative AI to analyze the content of speeches and identify the focus of the discussion. The analysis unit can also use a generative AI to analyze the content of speeches and evaluate the depth of the discussion. This makes meetings more efficient by automatically listing important discussion points. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of speeches during a meeting into a generative AI and have the generative AI extract important discussion points.

[0094] The monitoring unit can analyze the number of times each member speaks and their emotions, and encourage members who speak infrequently to speak. For example, the monitoring unit can use a generative AI to analyze the number of times each member speaks and encourage members who speak infrequently to speak. The monitoring unit can use a generative AI to analyze the number of times each member speaks and encourage members who speak infrequently to speak. The monitoring unit can also use a generative AI to analyze the emotions of each member and encourage members who speak infrequently to speak. The monitoring unit can use a generative AI to analyze the number of times each member speaks and their emotions, and encourage members who speak infrequently to speak. This promotes a balanced discussion by encouraging members who speak infrequently to speak. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform speech promotion.

[0095] The whiteboard section can reflect spoken content on the whiteboard in real time, allowing for the visual organization of ideas. For example, the whiteboard section can use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. The whiteboard section can use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. The whiteboard section can also use a generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. This allows for the visual organization of ideas by reflecting spoken content on the whiteboard in real time. Some or all of the above-described processes in the whiteboard section may be performed using AI, for example, or without AI. For example, the whiteboard section can input spoken content into a generative AI and have the generative AI perform the visual organization.

[0096] The analysis unit can analyze the content of speeches during a meeting, estimate the speaker's intent, and highlight important points based on the estimated intent. For example, the analysis unit can use a generative AI to analyze the content of speeches, estimate the speaker's intent, and highlight important points. The analysis unit can have the generative AI analyze the content of speeches, automatically extract points that the speaker wants to emphasize, and reflect them in the meeting summary. The analysis unit can also have the generative AI estimate the speaker's intent and display important discussion points in real time. The analysis unit can also have the generative AI analyze the content of speeches and automatically present relevant materials and data based on the speaker's intent. This clarifies the main points of the meeting by highlighting important points based on the speaker's intent. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of speeches into a generative AI and have the generative AI perform the estimation of the speaker's intent and the highlighting of important points.

[0097] The analysis unit can analyze the content of statements made during a meeting and identify new discussion points by comparing them with past meeting content. For example, the analysis unit can use a generative AI to analyze the content of statements and identify new discussion points by comparing them with past meeting content. The analysis unit can have the generative AI retrieve past meeting content from a database and identify new discussion points by comparing them with the current meeting content. The analysis unit can also have the generative AI extract unresolved discussion points from past meetings and suggest that they be discussed again in the current meeting. The analysis unit can also have the generative AI analyze past meeting content and highlight new discussion points that have emerged in the current meeting. This allows for the identification of new discussion points by comparing them with past meeting content. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past meeting content into the generative AI and have the generative AI identify new discussion points.

[0098] The analysis unit can analyze the content of statements made during a meeting, estimate the speaker's level of expertise, and adjust the analysis results based on the estimated level of expertise. For example, the analysis unit can use a generative AI to analyze the content of statements, estimate the speaker's level of expertise, and adjust the analysis results. The analysis unit can use a generative AI to analyze the content of statements and estimate the level of expertise from the frequency of the speaker's use of technical terms. The analysis unit can also use a generative AI to refer to the speaker's past statement history, estimate the level of expertise, and adjust the analysis results. The analysis unit can also use a generative AI to display the analysis results in an easy-to-understand manner based on the speaker's level of expertise. This makes the analysis results more appropriate by adjusting them based on the speaker's level of expertise. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of statements into a generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the analysis results.

[0099] The analysis unit can analyze the content of statements made during a meeting, estimate the speaker's emotions, and adjust the analysis results based on the estimated emotions. For example, the analysis unit can use a generative AI to analyze the content of statements, estimate the speaker's emotions, and adjust the analysis results. The analysis unit can have a generative AI analyze the content of statements, estimate the speaker's emotions, and adjust the analysis results according to those emotions. The analysis unit can also have a generative AI estimate the speaker's emotions and highlight important points based on those emotions. The analysis unit can also have a generative AI estimate the speaker's emotions and provide feedback according to those emotions. This allows for more appropriate analysis results by adjusting the analysis results based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of statements into a generative AI and have the generative AI perform emotion estimation and adjustment of the analysis results.

[0100] The analysis unit can analyze the content of statements made during a meeting and adjust the analysis results considering the geographical background of the speaker. For example, the analysis unit can use a generative AI to analyze the content of statements and adjust the analysis results considering the geographical background of the speaker. The analysis unit can have the generative AI consider the geographical background of the speaker and reflect region-specific information in the analysis results. The analysis unit can also have the generative AI consider the geographical background of the speaker and automatically present region-related data. The analysis unit can also have the generative AI consider the geographical background of the speaker and display the analysis results in a format appropriate for the region. In this way, by considering the geographical background of the speaker, analysis results that reflect region-specific information can be obtained. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the content of statements into the generative AI and have the generative AI perform the consideration of geographical background and the adjustment of analysis results.

[0101] The analysis unit can analyze the content of statements made during a meeting and supplement the analysis results by referring to the speaker's social media activity. For example, the analysis unit can use a generative AI to analyze the content of statements and supplement the analysis results by referring to the speaker's social media activity. The analysis unit can have the generative AI refer to the speaker's social media activity and supplement information related to the content of the statements. The analysis unit can also have the generative AI analyze the speaker's social media activity and present topics related to the content of the statements. The analysis unit can also have the generative AI refer to the speaker's social media activity and automatically display data related to the content of the statements. This allows information related to the content of the statements to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the content of statements into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of analysis results.

[0102] The extraction unit can estimate the speaker's intent when extracting important points and action items, and adjust the extraction results based on the estimated intent. For example, the extraction unit can use a generative AI to estimate the speaker's intent and extract important points and action items. The extraction unit can use a generative AI to estimate the speaker's intent, extract important points, and list them. The extraction unit can also use a generative AI to estimate the speaker's intent, extract action items, and reflect them in the meeting summary. The extraction unit can also use a generative AI to estimate the speaker's intent and adjust the extraction results based on that intent. By adjusting the extraction results based on the speaker's intent, more appropriate points and action items are extracted. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into a generative AI and have the generative AI perform intent estimation and adjustment of the extraction results.

[0103] The extraction unit can identify new action items by comparing them with past meeting content when extracting important points and action items. For example, the extraction unit can use a generative AI to analyze the content of statements and identify new action items by comparing them with past meeting content. The extraction unit can have the generative AI retrieve past meeting content from a database and identify new action items by comparing them with the current meeting content. The extraction unit can also have the generative AI extract unresolved action items from past meetings and suggest that they be discussed again in the current meeting. The extraction unit can also have the generative AI analyze past meeting content and highlight action items that have newly emerged in the current meeting. This allows for the identification of new action items by comparing them with past meeting content. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input past meeting content into the generative AI and have the generative AI identify new action items.

[0104] The extraction unit can estimate the speaker's level of expertise when extracting important points and action items, and adjust the extraction results based on the estimated level of expertise. For example, the extraction unit can use a generative AI to analyze the content of the speech, estimate the speaker's level of expertise, and adjust the extraction results. The extraction unit can use the generative AI to estimate the speaker's level of expertise, extract important points, and list them. The extraction unit can also use the generative AI to estimate the speaker's level of expertise, extract action items, and reflect them in the meeting summary. The extraction unit can also use the generative AI to estimate the speaker's level of expertise and adjust the extraction results based on that level of expertise. By adjusting the extraction results based on the speaker's level of expertise, more appropriate points and action items are extracted. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into the generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the extraction results.

[0105] The extraction unit can estimate the speaker's emotions when extracting important points and action items, and adjust the extraction results based on the estimated emotions. For example, the extraction unit can analyze the content of a statement using a generative AI, estimate the speaker's emotions, and adjust the extraction results. The extraction unit can use the generative AI to estimate the speaker's emotions and extract important points based on those emotions. The extraction unit can also use the generative AI to estimate the speaker's emotions and extract action items based on those emotions. The extraction unit can also use the generative AI to estimate the speaker's emotions and adjust the extraction results based on those emotions. By adjusting the extraction results based on the speaker's emotions, more appropriate points and action items are extracted. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into the generating AI, which can then perform emotion estimation and adjustment of the extraction results.

[0106] The extraction unit can adjust the extraction results by considering the speaker's geographical background when extracting important points and action items. For example, the extraction unit can analyze the content of the speech using a generation AI and adjust the extraction results by considering the speaker's geographical background. The extraction unit can have the generation AI consider the speaker's geographical background and reflect region-specific information in the extraction results. The extraction unit can also have the generation AI consider the speaker's geographical background and automatically present region-related data. The extraction unit can also have the generation AI consider the speaker's geographical background and display the extraction results in a format appropriate for the region. As a result, by considering the speaker's geographical background, extraction results that reflect region-specific information can be obtained. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of the speech into the generation AI and have the generation AI perform the consideration of geographical background and adjustment of the extraction results.

[0107] The extraction unit can supplement its extraction results by referring to the speaker's social media activity when extracting important points and action items. For example, the extraction unit can analyze the content of a statement using a generative AI and supplement the extraction results by referring to the speaker's social media activity. The extraction unit can use the generative AI to refer to the speaker's social media activity and supplement information related to the content of the statement. The extraction unit can also use the generative AI to analyze the speaker's social media activity and present topics related to the content of the statement. The extraction unit can also use the generative AI to refer to the speaker's social media activity and automatically display data related to the content of the statement. This allows for supplementation of information related to the content of the statement by referring to the speaker's social media activity. Some or all of the above processing in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the content of a statement into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of the extraction results.

[0108] The monitoring unit can monitor the frequency of each member's speech and their emotions, estimate the speaker's intent, and adjust the monitoring results based on the estimated intent. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor each member's emotions, estimate the speaker's intent, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's intent. By adjusting the monitoring results based on the speaker's intent, more appropriate monitoring becomes possible. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform intent estimation and adjustment of the monitoring results.

[0109] The monitoring unit can monitor each member's frequency of speaking and emotions, and identify new speaking patterns by comparing them with their past speaking history. For example, the monitoring unit can use a generative AI to monitor each member's frequency of speaking and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can use a generative AI to monitor each member's frequency of speaking and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can also use a generative AI to monitor each member's emotions and identify new speaking patterns by comparing them with their past speaking history. The monitoring unit can also use a generative AI to monitor each member's frequency of speaking and emotions and identify new speaking patterns by comparing them with their past speaking history. This allows for the identification of new speaking patterns by comparing them with past speaking history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speaking data into a generative AI and have the generative AI perform the identification of speaking patterns.

[0110] The monitoring unit can monitor the frequency of each member's speech and their emotions, estimate the speaker's level of expertise, and adjust the monitoring results based on the estimated level of expertise. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can use a generative AI to monitor the frequency of each member's speech, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor each member's emotions, estimate the speaker's level of expertise, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's level of expertise. This allows for more appropriate monitoring by adjusting the monitoring results based on the speaker's level of expertise. Some or all of the above-described processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform the estimation of expertise levels and the adjustment of monitoring results.

[0111] The monitoring unit can monitor the frequency of speech and emotions of each member, estimate the emotions of the speakers, and adjust the monitoring results based on the estimated emotions. For example, the monitoring unit can use a generative AI to monitor the frequency of speech of each member, estimate the emotions of the speakers, and adjust the monitoring results. The monitoring unit can use a generative AI to monitor the frequency of speech of each member, estimate the emotions of the speakers, and adjust the monitoring results. The monitoring unit can also use a generative AI to monitor the emotions of each member and adjust the monitoring results based on the emotions of the speakers. The monitoring unit can also use a generative AI to monitor the frequency of speech and emotions of each member and adjust the monitoring results based on the emotions of the speakers. By adjusting the monitoring results based on the emotions of the speakers, more appropriate monitoring becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input each member's statement data into a generating AI, which can then perform emotion estimation and adjust the monitoring results.

[0112] The monitoring unit can monitor the frequency of each member's speech and their emotions, and adjust the monitoring results considering the speaker's geographical background. For example, the monitoring unit can use a generative AI to monitor the frequency of each member's speech and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can use a generative AI to monitor the frequency of each member's speech and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can also use a generative AI to monitor each member's emotions and adjust the monitoring results considering the speaker's geographical background. The monitoring unit can also use a generative AI to monitor the frequency of each member's speech and their emotions, and adjust the monitoring results based on the speaker's geographical background. By considering the speaker's geographical background, monitoring results that reflect region-specific information can be obtained. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's speech data into a generative AI and have the generative AI perform the consideration of geographical background and the adjustment of monitoring results.

[0113] The monitoring unit can monitor each member's frequency of speaking and their emotions, and supplement the monitoring results by referring to the speaker's social media activity. For example, the monitoring unit can use a generative AI to monitor each member's frequency of speaking and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can have the generative AI monitor each member's frequency of speaking and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can also have the generative AI monitor each member's emotions and supplement the monitoring results by referring to the speaker's social media activity. The monitoring unit can have the generative AI monitor each member's frequency of speaking and their emotions and supplement the monitoring results based on the speaker's social media activity. This allows information related to the content of the statements to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input each member's statement data into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of monitoring results.

[0114] The facilitator can estimate the speaker's intent and adjust the facilitation method based on the estimated intent when promoting a balanced discussion. For example, the facilitator can use generative AI to estimate the speaker's intent and adjust the order of statements to promote a balanced discussion. The facilitator can use generative AI to estimate the speaker's intent and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's intent and prompt statements at the appropriate time to ensure a smooth discussion. The facilitator can also use generative AI to estimate the speaker's intent and adjust the content of statements to balance the discussion. This allows for more effective discussion facilitation by adjusting the facilitation method based on the speaker's intent. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into generative AI and have the generative AI perform intent estimation and adjustment of the facilitation method.

[0115] The facilitator can identify new discussion points by comparing them with past discussion history when promoting a balanced discussion. For example, the facilitator can use generative AI to retrieve past discussion history from a database and identify new discussion points by comparing them with the current discussion content. The facilitator can also have the generative AI extract unresolved discussion points from past discussions and suggest that they be discussed again in the current discussion. The facilitator can also have the generative AI analyze past discussion history and highlight new discussion points that have emerged in the current discussion. This allows for the identification of new discussion points by comparing them with past discussion history. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input past discussion history into the generative AI and have the generative AI identify new discussion points.

[0116] The facilitator can estimate the speaker's level of expertise and adjust the facilitation method based on the estimated level of expertise when promoting a balanced discussion. For example, the facilitator can use generative AI to estimate the speaker's level of expertise and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and adjust the order of statements to promote a balanced discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and prompt statements at appropriate times to ensure a smooth discussion. The facilitator can also use generative AI to estimate the speaker's level of expertise and adjust the content of statements to balance the discussion. This allows for more appropriate discussion facilitation by adjusting the facilitation method based on the speaker's level of expertise. Some or all of the above processes in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into generative AI and have the generative AI perform the estimation of expertise levels and adjustment of facilitation methods.

[0117] The facilitator can estimate the speaker's emotions and adjust its facilitation methods based on the estimated emotions when facilitating a balanced discussion. For example, the facilitator can use generative AI to estimate the speaker's emotions and adjust the order of statements to facilitate a balanced discussion. The facilitator can also use generative AI to estimate the speaker's emotions and prompt statements at appropriate times to smooth the discussion based on those emotions. The facilitator can also use generative AI to estimate the speaker's emotions and adjust the content of statements to balance the discussion based on those emotions. This allows for more appropriate discussion facilitation by adjusting the facilitation methods based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the facilitator may be performed using AI, for example, or without AI. For example, the promotion unit can input the content of the speech into the generation AI, which can then perform emotion estimation and adjust the promotion method.

[0118] The facilitator can adjust its facilitation methods by considering the geographical background of the speakers when promoting a balanced discussion. For example, the facilitator can use generative AI to consider the geographical background of the speakers and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and reflect region-specific information in the discussion. The facilitator can also have the generative AI consider the geographical background of the speakers and automatically present region-related data. This makes it possible to promote a discussion that reflects region-specific information by considering the geographical background of the speakers. Some or all of the above processing in the facilitator may be performed using AI, for example, or not using AI. For example, the facilitator can input the content of the statements into the generative AI and have the generative AI perform the consideration of geographical background and adjustment of the facilitation method.

[0119] The facilitator can supplement its facilitation methods by referencing the speakers' social media activity when promoting a balanced discussion. For example, the facilitator can use generative AI to reference the speakers' social media activity and adjust the order of statements to promote a balanced discussion. The facilitator can have the generative AI reference the speakers' social media activity and adjust the order of statements to promote a balanced discussion. The facilitator can also have the generative AI reference the speakers' social media activity and reflect information related to the content of the statements in the discussion. The facilitator can also have the generative AI reference the speakers' social media activity and automatically present data related to the content of the statements. This allows for supplementation of information related to the content of the statements by referencing the speakers' social media activity. Some or all of the above processing in the facilitator may be performed using AI, for example, or without AI. For example, the facilitator can input the content of statements into the generative AI and have the generative AI perform the referencing of social media activity and supplementation of facilitation methods.

[0120] The whiteboard unit can reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method based on the estimated intent. For example, the whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method. The whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's intent, and adjust the visualization method. The whiteboard unit can also use a generative AI to estimate the speaker's intent and visually organize the spoken content based on that intent. The whiteboard unit can also use a generative AI to estimate the speaker's intent and display relevant materials and data on the whiteboard based on that intent. This allows for more appropriate visualization by adjusting the visualization method based on the speaker's intent. Some or all of the above-described processes in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generative AI and have the generative AI perform intent estimation and visualization method adjustment.

[0121] The whiteboard unit can reflect spoken content on the whiteboard in real time and identify new visualization methods by comparing it with past whiteboard content. For example, the whiteboard unit can use a generation AI to retrieve past whiteboard content from a database and identify new visualization methods by comparing it with the current spoken content. The whiteboard unit can also have the generation AI retrieve past whiteboard content from a database and identify new visualization methods by comparing it with the current spoken content. The whiteboard unit can also have the generation AI analyze past whiteboard content and propose new visualization methods based on the current spoken content. The whiteboard unit can also have the generation AI refer to past whiteboard content and present visualization methods related to the current spoken content. This allows for the identification of new visualization methods by comparing them with past whiteboard content. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input past whiteboard content into the generation AI and have the generation AI identify new visualization methods.

[0122] The whiteboard unit can reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method based on the estimated level of expertise. For example, the whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method. The whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's level of expertise, and adjust the visualization method. The whiteboard unit can also use a generative AI to estimate the speaker's level of expertise and visually organize the spoken content based on that level of expertise. The whiteboard unit can also use a generative AI to estimate the speaker's level of expertise and display relevant materials and data on the whiteboard based on that level of expertise. This allows for more appropriate visualization by adjusting the visualization method based on the speaker's level of expertise. Some or all of the above-described processes in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generative AI and have the generative AI perform the estimation of the level of expertise and the adjustment of the visualization method.

[0123] The whiteboard unit can reflect spoken content on the whiteboard in real time, estimate the speaker's emotions, and adjust the visualization method based on the estimated emotions. For example, the whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's emotions, and adjust the visualization method. The whiteboard unit can use a generative AI to reflect spoken content on the whiteboard in real time, estimate the speaker's emotions, and adjust the visualization method. The whiteboard unit can also use a generative AI to estimate the speaker's emotions and visually organize the spoken content based on those emotions. The whiteboard unit can also use a generative AI to estimate the speaker's emotions and display relevant materials and data on the whiteboard based on those emotions. This allows for more appropriate visualization by adjusting the visualization method based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the whiteboard unit may be performed using AI, or not. For example, the whiteboard section can input the content of the spoken words into a generating AI, which can then perform emotion estimation and adjust the visualization method.

[0124] The whiteboard unit can reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. For example, the whiteboard unit can use a generation AI to reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. The whiteboard unit can use a generation AI to reflect spoken content on the whiteboard in real time and adjust the visualization method considering the speaker's geographical background. The whiteboard unit can also use a generation AI to consider the speaker's geographical background and display region-specific information on the whiteboard. The whiteboard unit can also use a generation AI to consider the speaker's geographical background and display region-related data on the whiteboard. This makes it possible to visualize region-specific information by considering the speaker's geographical background. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input spoken content into a generation AI and have the generation AI consider geographical background and adjust the visualization method.

[0125] The whiteboard unit can reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. For example, the whiteboard unit can use a generative AI to reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. The whiteboard unit can have a generative AI reflect the content of a statement on the whiteboard in real time and supplement the visualization method by referring to the speaker's social media activity. The whiteboard unit can also have a generative AI refer to the speaker's social media activity and display information related to the content of the statement on the whiteboard. The whiteboard unit can also have a generative AI refer to the speaker's social media activity and display data related to the content of the statement on the whiteboard. This allows information related to the content of the statement to be supplemented by referring to the speaker's social media activity. Some or all of the above processing in the whiteboard unit may be performed using AI, for example, or without AI. For example, the whiteboard unit can input the content of a statement into a generative AI and have the generative AI perform the referencing of social media activity and the supplementation of the visualization method.

[0126] The encryption unit can estimate the speaker's intent when encrypting meeting content and adjust the encryption method based on the estimated intent. For example, the encryption unit can use a generative AI to estimate the speaker's intent and encrypt the meeting content. The encryption unit can use a generative AI to estimate the speaker's intent and encrypt the meeting content based on that intent. The encryption unit can also use a generative AI to estimate the speaker's intent and adjust the encryption strength based on that intent. The encryption unit can also use a generative AI to estimate the speaker's intent and set the encryption range based on that intent. This allows for more appropriate encryption by adjusting the encryption method based on the speaker's intent. Some or all of the above-described processes in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input the meeting content into a generative AI and have the generative AI perform intent estimation and encryption method adjustment.

[0127] The encryption unit can identify a new encryption method by comparing it with past encryption history when encrypting meeting content. For example, the encryption unit can use a generative AI to retrieve past encryption history from a database and identify a new encryption method by comparing it with the current meeting content. The encryption unit can also have the generative AI analyze past encryption history and propose the optimal encryption method based on the current meeting content. The encryption unit can also have the generative AI refer to past encryption history and present encryption methods relevant to the current meeting content. This allows for the identification of a new encryption method by comparing it with past encryption history. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input past encryption history into the generative AI and have the generative AI identify a new encryption method.

[0128] The encryption unit can estimate the speaker's emotions when encrypting meeting content and adjust the encryption method based on the estimated emotions. For example, the encryption unit can use a generative AI to estimate the speaker's emotions and then encrypt the meeting content. The encryption unit can use a generative AI to estimate the speaker's emotions and then encrypt the meeting content based on those emotions. The encryption unit can also use a generative AI to estimate the speaker's emotions and then adjust the encryption strength based on those emotions. The encryption unit can also use a generative AI to estimate the speaker's emotions and then set the encryption range based on those emotions. This allows for more appropriate encryption by adjusting the encryption method based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the encryption unit may be performed using AI, or not. For example, the encryption unit can input the meeting content into a generative AI and have the generative AI perform emotion estimation and adjust the encryption method.

[0129] The encryption unit can adjust the encryption method when encrypting meeting content, taking into account the geographical background of the speakers. For example, the encryption unit can use a generation AI to consider the geographical background of the speakers and encrypt the meeting content. The encryption unit can use a generation AI to consider the geographical background of the speakers and reflect region-specific information in the encryption. The encryption unit can also use a generation AI to consider the geographical background of the speakers and encrypt region-related data. The encryption unit can also use a generation AI to consider the geographical background of the speakers and set an encryption method appropriate for the region. This makes it possible to encrypt data that reflects region-specific information by considering the geographical background of the speakers. Some or all of the above processing in the encryption unit may be performed using AI, for example, or without AI. For example, the encryption unit can input the meeting content into a generation AI and have the generation AI perform the consideration of geographical background and adjustment of the encryption method.

[0130] The adjustment unit can estimate the speaker's intent and adjust the intervention level based on the estimated intent when adjusting the AI ​​intervention level. For example, the adjustment unit can use a generative AI to estimate the speaker's intent and adjust the AI ​​intervention level. The adjustment unit can have the generative AI estimate the speaker's intent and adjust the AI ​​intervention level based on that intent. The adjustment unit can also have the generative AI estimate the speaker's intent and set the frequency of intervention based on that intent. The adjustment unit can also have the generative AI estimate the speaker's intent and adjust the level of detail of the intervention based on that intent. By adjusting the intervention level based on the speaker's intent, more appropriate intervention becomes possible. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the utterance into the generative AI and have the generative AI perform intent estimation and intervention level adjustment.

[0131] The adjustment unit can identify a new intervention level by comparing it with past intervention history when adjusting the AI's intervention level. For example, the adjustment unit can use a generating AI to retrieve past intervention history from a database and identify a new intervention level by comparing it with the current meeting content. The adjustment unit can have the generating AI retrieve past intervention history from a database and identify a new intervention level by comparing it with the current meeting content. The adjustment unit can also have the generating AI analyze past intervention history and propose an optimal intervention level based on the current meeting content. The adjustment unit can also have the generating AI refer to past intervention history and present an intervention level relevant to the current meeting content. This allows for the identification of a new intervention level by comparing it with past intervention history. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input past intervention history into the generating AI and have the generating AI perform the identification of a new intervention level.

[0132] The adjustment unit can estimate the speaker's emotions and adjust the intervention level based on the estimated emotions when adjusting the AI ​​intervention level. For example, the adjustment unit can use a generative AI to estimate the speaker's emotions and adjust the AI ​​intervention level. The adjustment unit can have a generative AI estimate the speaker's emotions and adjust the AI ​​intervention level based on those emotions. The adjustment unit can also have a generative AI estimate the speaker's emotions and set the frequency of intervention based on those emotions. The adjustment unit can also have a generative AI estimate the speaker's emotions and adjust the level of detail of intervention based on those emotions. This allows for more appropriate intervention by adjusting the intervention level based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the adjustment unit may be performed using an AI, for example, or not using an AI. For example, the adjustment unit can input the utterance into a generative AI and have the generative AI perform emotion estimation and intervention level adjustment.

[0133] The adjustment unit can adjust the AI ​​intervention level by considering the speaker's geographical background when adjusting the AI ​​intervention level. For example, the adjustment unit can use a generative AI to consider the speaker's geographical background and adjust the AI ​​intervention level. The adjustment unit can have the generative AI consider the speaker's geographical background and reflect region-specific information in the intervention level. The adjustment unit can also have the generative AI consider the speaker's geographical background and reflect region-related data in the intervention level. The adjustment unit can also have the generative AI consider the speaker's geographical background and set an intervention level appropriate for the region. This makes it possible to implement interventions that reflect region-specific information by considering the speaker's geographical background. Some or all of the above processing in the adjustment unit may be performed using AI, for example, or without using AI. For example, the adjustment unit can input the utterance into the generative AI and have the generative AI perform the consideration of geographical background and the adjustment of the intervention level.

[0134] The interface unit can estimate the speaker's intent and adjust the display method based on the estimated intent when adjusting the interface display method. For example, the interface unit can use a generative AI to estimate the speaker's intent and adjust the interface display method. The interface unit can use a generative AI to estimate the speaker's intent and adjust the interface display method based on that intent. The interface unit can also use a generative AI to estimate the speaker's intent and set the display layout based on that intent. The interface unit can also use a generative AI to estimate the speaker's intent and adjust the level of detail of the display based on that intent. This makes it possible to display more appropriately by adjusting the display method based on the speaker's intent. Some or all of the above processing in the interface unit may be performed using AI, for example, or without using AI. For example, the interface unit can input the utterance content into a generative AI and have the generative AI perform intent estimation and display method adjustment.

[0135] The interface unit can identify new display methods by comparing them with past display history when adjusting the interface display method. For example, the interface unit can use a generation AI to retrieve past display history from a database and identify new display methods by comparing them with the current meeting content. The interface unit can have the generation AI retrieve past display history from a database and identify new display methods by comparing them with the current meeting content. The interface unit can also have the generation AI analyze past display history and propose the optimal display method based on the current meeting content. The interface unit can also have the generation AI refer to past display history and present display methods related to the current meeting content. This allows for the identification of new display methods by comparing them with past display history. Some or all of the above processing in the interface unit may be performed using AI, for example, or without AI. For example, the interface unit can input past display history into the generation AI and have the generation AI perform the identification of new display methods.

[0136] The interface unit can estimate the speaker's emotions when adjusting the interface display method and adjust the display method based on the estimated emotions. For example, the interface unit can use a generative AI to estimate the speaker's emotions and adjust the interface display method. The interface unit can use a generative AI to estimate the speaker's emotions and adjust the interface display method based on those emotions. The interface unit can also use a generative AI to estimate the speaker's emotions and set the display layout based on those emotions. The interface unit can also use a generative AI to estimate the speaker's emotions and adjust the level of detail of the display based on those emotions. This allows for a more appropriate display by adjusting the display method based on the speaker's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the interface unit may be performed using AI, for example, or without AI. For example, the interface unit can input the utterance content into a generative AI and have the generative AI perform emotion estimation and display method adjustment.

[0137] The interface unit can adjust the display method of the interface by taking into account the speaker's geographical background when adjusting the display method. For example, the interface unit can use a generation AI to take into account the speaker's geographical background and adjust the display method of the interface. The interface unit can have the generation AI take into account the speaker's geographical background and reflect region-specific information in the display method. The interface unit can also have the generation AI take into account the speaker's geographical background and reflect region-related data in the display method. The interface unit can also have the generation AI take into account the speaker's geographical background and set a display method appropriate for the region. This makes it possible to display information that reflects region-specific information by taking into account the speaker's geographical background. Some or all of the above processing in the interface unit may be performed using AI, for example, or without using AI. For example, the interface unit can input the content of the speech into the generation AI and have the generation AI perform the consideration of geographical background and adjustment of the display method.

[0138] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0139] Hybrid facilitators can have features that automatically adjust participants' schedules before a meeting starts to make the meeting run more smoothly. For example, a generative AI can analyze each participant's calendar and suggest the optimal meeting time. Furthermore, the generative AI can refer to participants' past meeting history to identify the most efficient meeting times. It can also adjust meeting times considering participants' workloads. This ensures that all participants can participate in the meeting as efficiently as possible.

[0140] Hybrid facilitators can be equipped with features to automatically transcribe and translate meeting content in real time, enabling more effective recording of meeting proceedings. For example, a generative AI can analyze the content of the speech and transcribe it in real time. Furthermore, the generative AI can translate the content into multiple languages ​​and provide it to participants. It can also summarize the content of the speech and distribute it to participants after the meeting. This enables effective communication across language barriers.

[0141] Hybrid facilitators can incorporate features that allow participants to conduct real-time polls and surveys, making meetings more interactive. For example, a generative AI can automatically create polls and surveys during the meeting and distribute them to participants. Furthermore, the generative AI can compile the poll results in real time and display them during the meeting. It can also analyze the survey results and incorporate them into the meeting's progress. This allows all participants to actively engage in the meeting.

[0142] Hybrid facilitators can be equipped with the ability to automatically collect and analyze participant feedback to improve the quality of meetings. For example, a generative AI can send feedback questionnaires to participants after the meeting and collect responses. Furthermore, the generative AI can analyze the feedback to identify areas for improvement in the meeting. It can also adjust the plan for the next meeting based on the feedback. This allows for continuous improvement in the quality of meetings.

[0143] Hybrid facilitators can be equipped with features to automate document sharing during meetings, further enhancing meeting efficiency. For example, a generative AI can automatically collect and distribute documents used during the meeting. Furthermore, the generative AI can analyze the document content and highlight key points. It can also reflect document updates in real time and notify participants. This ensures smooth document sharing and improves meeting efficiency.

[0144] A hybrid facilitator can be equipped with the ability to estimate participants' emotions and reflect them in the flow of the meeting. For example, a generative AI can analyze each participant's statements and facial expressions to estimate their emotions. Furthermore, the generative AI can adjust the flow of the meeting based on the emotions it has estimated. It can also provide feedback to participants based on their emotions. This makes it possible to conduct meetings that are considerate of the participants' emotions.

[0145] A hybrid facilitator can be equipped with the ability to estimate participants' emotions and stimulate discussion in meetings. For example, a generative AI can analyze each participant's statements and facial expressions to estimate their emotions. Furthermore, based on the emotions estimated by the generative AI, it can encourage less talkative participants to speak up. The generative AI can also adjust the direction of the discussion based on emotions. This allows all participants to actively engage in the discussion.

[0146] A hybrid facilitator can be equipped with the ability to estimate participants' emotions and reduce meeting stress. For example, a generative AI can analyze each participant's statements and facial expressions to estimate their emotions. Furthermore, the generative AI can adjust the flow of the meeting based on the emotions it estimates. It can also make suggestions to create a relaxed atmosphere based on the emotions. This reduces participant stress and allows the meeting to proceed smoothly.

[0147] A hybrid facilitator can have the ability to estimate participants' emotions and improve meeting engagement. For example, a generative AI can analyze each participant's statements and facial expressions to estimate their emotions. Furthermore, based on the emotions estimated by the generative AI, it can provide feedback to the participants. It can also suggest actions to increase engagement based on those emotions. This allows all participants to actively engage in the meeting.

[0148] A hybrid facilitator can be equipped with the ability to estimate participants' emotions and maximize meeting outcomes. For example, a generative AI can analyze each participant's statements and facial expressions to estimate their emotions. Furthermore, the generative AI can adjust the meeting's progress based on the estimated emotions. It can also make suggestions to increase participants' motivation based on their emotions. This maximizes the meeting's results.

[0149] The following briefly describes the processing flow for example form 2.

[0150] Step 1: The analysis unit analyzes the meeting content in real time. The analysis unit uses generative AI to analyze the content spoken during the meeting and extract important information. The analysis unit can use the generative AI to analyze the content spoken and automatically list important discussion points. It can also estimate the speaker's intent and highlight important points based on that estimated intent. Furthermore, it can identify new discussion points by comparing them with past meeting content. Step 2: The extraction unit extracts key points and action items based on the analysis performed by the analysis unit. The extraction unit uses generative AI to extract and list key points and action items. It can estimate the speaker's intent and extract and list key points. It can also identify new action items by comparing them with past meeting content. Furthermore, it can estimate the speaker's level of expertise and adjust the extraction results based on the estimated level of expertise. Step 3: The monitoring unit monitors the frequency of each member's contributions and their emotions. The monitoring unit uses generative AI to analyze the frequency of each member's contributions and their emotions, promoting balanced discussions. By analyzing the number of contributions and emotions, it can encourage members who are not contributing much to speak up. It can also estimate the speaker's intentions and adjust the monitoring results based on those estimations. Furthermore, it can identify new conversational patterns by comparing them with past conversational history. Step 4: The Facilitation Unit promotes a balanced discussion based on the information monitored by the Monitoring Unit. The Facilitation Unit uses Generative AI to estimate the speaker's intent and promotes the discussion based on the estimated intent. It can adjust the order of statements and prompt for statements at the appropriate time to ensure the smooth progress of the discussion. It can also adjust the content of statements to balance the discussion. Step 5: The whiteboard section visualizes ideas using a virtual whiteboard. The whiteboard section uses generative AI to reflect spoken content on the whiteboard in real time, visually organizing ideas. It can estimate the speaker's intent and adjust the visualization method based on that estimation. It can also identify new visualization methods by comparing them with past whiteboard content. Furthermore, it can estimate the speaker's level of expertise and adjust the visualization method based on that estimation.

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0153] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements described above, including the analysis unit, extraction unit, monitoring unit, acceleration unit, whiteboard unit, encryption unit, adjustment unit, and interface unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The extraction unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The monitoring unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The acceleration unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The whiteboard unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The encryption unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The adjustment unit is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing unit 12. The interface is implemented by the processor 46 of the smart device 14 and the processor 28 of the data processing device 12. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0156] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0163] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] Each of the multiple elements described above, including the analysis unit, extraction unit, monitoring unit, acceleration unit, whiteboard unit, encryption unit, adjustment unit, and interface unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The extraction unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The monitoring unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The acceleration unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The whiteboard unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The encryption unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The adjustment unit is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The interface section is implemented by the processor 46 of the smart glasses 214 and the processor 28 of the data processing unit 12. The correspondence between each section and the device or control unit is not limited to the example described above and can be modified in various ways.

[0171] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0172] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0173] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0174] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0175] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0177] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0178] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0179] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0180] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0181] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0182] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0183] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0184] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0185] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0186] Each of the multiple elements described above, including the analysis unit, extraction unit, monitoring unit, acceleration unit, whiteboard unit, encryption unit, adjustment unit, and interface unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The extraction unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The monitoring unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The acceleration unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The whiteboard unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The encryption unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The adjustment unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The interface unit is implemented by the processor 46 of the headset terminal 314 and the processor 28 of the data processing unit 12. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0187] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0188] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0189] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0190] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0191] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0193] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0194] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0195] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0196] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0197] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0198] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0199] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0200] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0201] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0202] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0203] Each of the multiple elements described above, including the analysis unit, extraction unit, monitoring unit, acceleration unit, whiteboard unit, encryption unit, adjustment unit, and interface unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The extraction unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The monitoring unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The acceleration unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The whiteboard unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The encryption unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The adjustment unit is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing unit 12. The interface is implemented by the processor 46 of the robot 414 and the processor 28 of the data processing device 12. The correspondence between each part and the device or control unit is not limited to the example described above and can be modified in various ways.

[0204] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0205] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0206] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0207] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0208] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0209] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0210] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0211] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0212] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0213] 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.

[0214] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0215] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0216] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0217] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0218] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0219] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0220] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0221] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0222] (Note 1) The analysis department analyzes the meeting content in real time, An extraction unit extracts important points and action items based on the content analyzed by the aforementioned analysis unit, The monitoring department monitors the frequency of each member's statements and their emotions, A facilitation unit that promotes balanced discussion based on the information monitored by the aforementioned monitoring unit, It includes a whiteboard section that utilizes a virtual whiteboard to visualize ideas. A system characterized by the following features. (Note 2) It offers privacy protection options and includes an encryption section to ensure data security. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features an adjustment unit that adjusts the level of AI intervention according to the user's needs. The system described in Appendix 1, characterized by the features described herein. (Note 4) It features an interface that provides a user-friendly interface and reduces user stress. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit, The system analyzes what is said during a meeting and automatically lists important discussion points. The system described in Appendix 1, characterized by the features described herein. (Note 6) The monitoring unit, The system analyzes the frequency of each member's contributions and their emotions, and encourages members who are not speaking up to participate. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned whiteboard section is The content of the comments is reflected on the whiteboard in real time, allowing for visual organization of ideas. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, This system analyzes the content of speeches during meetings, estimates the speaker's intent, and highlights key points based on that estimated intent. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, By analyzing the content of discussions during meetings and comparing it with past meeting content, we can identify new points for discussion. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, The system analyzes the content of statements made during meetings, estimates the speaker's level of expertise, and adjusts the analysis results based on the estimated level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, The system analyzes the content of statements made during meetings, estimates the speaker's emotions, and adjusts the analysis results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, The content of statements made during the meeting is analyzed, and the analysis results are adjusted considering the geographical background of the speakers. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system analyzes the content of statements made during meetings and supplements the analysis results by referring to the speakers' social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 14) The extraction unit is When extracting key points and action items, the speaker's intent is estimated, and the extraction results are adjusted based on that estimated intent. The system described in Appendix 1, characterized by the features described herein. (Note 15) The extraction unit is When extracting key points and action items, compare them with past meeting content to identify new action items. The system described in Appendix 1, characterized by the features described herein. (Note 16) The extraction unit is When extracting key points and action items, the speaker's level of expertise is estimated, and the extraction results are adjusted based on the estimated level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 17) The extraction unit is When extracting key points and action items, the system estimates the speaker's emotions and adjusts the extraction results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The extraction unit is When extracting key points and action items, the extraction results are adjusted to take into account the speaker's geographical background. The system described in Appendix 1, characterized by the features described herein. (Note 19) The extraction unit is When extracting key points and action items, refer to the speaker's social media activity to supplement the extraction results. The system described in Appendix 1, characterized by the features described herein. (Note 20) The monitoring unit, The system monitors the frequency and emotions of each member's statements, estimates the speaker's intent, and adjusts the monitoring results based on the estimated intent. The system described in Appendix 1, characterized by the features described herein. (Note 21) The monitoring unit, We monitor each member's frequency of speaking and emotions, and identify new speaking patterns by comparing them with their past speaking history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The monitoring unit, The system monitors the frequency and emotional tone of each member's statements, estimates their level of expertise, and adjusts the monitoring results based on the estimated level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 23) The monitoring unit, The system monitors the frequency and emotions of each member's statements, estimates the speaker's emotions, and adjusts the monitoring results based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The monitoring unit, The frequency of each member's contributions and their emotions are monitored, and the monitoring results are adjusted considering the geographical background of the speaker. The system described in Appendix 1, characterized by the features described herein. (Note 25) The monitoring unit, The frequency and emotional state of each member's statements are monitored, and the monitoring results are supplemented by referring to the speaker's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned promotion unit is When facilitating a balanced discussion, we estimate the speaker's intentions and adjust the facilitation method based on those estimated intentions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned promotion unit is To facilitate balanced discussion, identify new points of discussion by comparing them with past discussion history. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned promotion unit is To facilitate balanced discussion, estimate the level of expertise of the speakers and adjust the facilitation method based on the estimated level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned promotion unit is To facilitate a balanced discussion, we estimate the speaker's emotions and adjust the facilitation method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned promotion unit is When promoting balanced discussion, adjust the facilitation methods to take into account the geographical background of the speakers. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned promotion unit is When promoting balanced discussion, referencing the speakers' social media activity can complement the facilitation methods. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned whiteboard section is The system reflects the spoken content on a whiteboard in real time, estimates the speaker's intent, and adjusts the visualization method based on the estimated intent. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned whiteboard section is The content of the comments is reflected on the whiteboard in real time, and new visualization methods are identified by comparing it with past whiteboard content. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned whiteboard section is The system reflects the spoken content on a whiteboard in real time, estimates the speaker's level of expertise, and adjusts the visualization method based on the estimated level of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned whiteboard section is The system reflects the spoken content on a whiteboard in real time, estimates the speaker's emotions, and adjusts the visualization method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned whiteboard section is The content of the speech is reflected on the whiteboard in real time, and the visualization method is adjusted to take into account the speaker's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned whiteboard section is The content of the speech is reflected on the whiteboard in real time, and the visualization method is supplemented by referencing the speaker's social media activity. The system described in Appendix 1, characterized by the features described herein. (Note 38) The encryption unit is When encrypting meeting content, the speaker's intent is estimated, and the encryption method is adjusted based on that estimated intent. The system described in Appendix 2, characterized by the features described herein. (Note 39) The encryption unit is When encrypting meeting content, we identify new encryption methods by comparing them with past encryption history. The system described in Appendix 2, characterized by the features described herein. (Note 40) The encryption unit is When encrypting meeting content, the speaker's emotions are estimated, and the encryption method is adjusted based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 41) The encryption unit is When encrypting meeting content, the encryption method is adjusted to take into account the geographical location of the speakers. The system described in Appendix 2, characterized by the features described herein. (Note 42) The adjustment unit is, When adjusting the level of AI intervention, it estimates the speaker's intent and adjusts the intervention level based on that estimated intent. The system described in Appendix 3, characterized by the features described herein. (Note 43) The adjustment unit is, When adjusting the AI ​​intervention level, it identifies new intervention levels by comparing them with past intervention history. The system described in Appendix 3, characterized by the features described herein. (Note 44) The adjustment unit is, When adjusting the level of AI intervention, it estimates the speaker's emotions and adjusts the intervention level based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Supplementary Note 45) When adjusting the intervention level of the adjustment unit, the intervention level is adjusted considering the geographical background of the speaker. When adjusting the intervention level of the adjustment unit, the intervention level is adjusted considering the geographical background of the speaker. The system according to Supplementary Note 3, characterized in that. (Supplementary Note 46) When adjusting the display method of the interface unit, the intention of the speaker is estimated, and the display method is adjusted based on the estimated intention. When adjusting the display method of the interface unit, the intention of the speaker is estimated, and the display method is adjusted based on the estimated intention. The system according to Supplementary Note 4, characterized in that. (Supplementary Note 47) When adjusting the display method of the interface unit, a new display method is specified by comparing it with the past display history. When adjusting the display method of the interface unit, a new display method is specified by comparing it with the past display history. The system according to Supplementary Note 4, characterized in that. (Supplementary Note 48) When adjusting the display method of the interface unit, the emotion of the speaker is estimated, and the display method is adjusted based on the estimated emotion. When adjusting the display method of the interface unit, the emotion of the speaker is estimated, and the display method is adjusted based on the estimated emotion. The system according to Supplementary Note 4, characterized in that. (Supplementary Note 49) When adjusting the display method of the interface unit, the display method is adjusted considering the geographical background of the speaker. When adjusting the display method of the interface unit, the display method is adjusted considering the geographical background of the speaker. The system according to Supplementary Note 4, characterized in that.

Explanation of Reference Signs

[0223] 10, 210, 310, 410 Data Processing System 12 Data Processing Device 14 Smart Device 214 Smart Glasses 314 Headset-Type Terminal 414 Robot

Claims

1. The analysis department analyzes the meeting content in real time, An extraction unit extracts important points and action items based on the content analyzed by the aforementioned analysis unit, The monitoring department monitors the frequency of each member's statements and their emotions, A facilitation unit that promotes balanced discussion based on the information monitored by the aforementioned monitoring unit, It includes a whiteboard section that utilizes a virtual whiteboard to visualize ideas. A system characterized by the following features.

2. It offers privacy protection options and includes an encryption section to ensure data security. The system according to feature 1.

3. It includes an adjustment unit that adjusts the level of AI intervention according to the user's needs. The system according to feature 1.

4. It features an interface that provides a user-friendly interface and reduces user stress. The system according to feature 1.

5. The aforementioned analysis unit, The system analyzes what is said during a meeting and automatically lists important discussion points. The system according to feature 1.

6. The monitoring unit, The system analyzes the frequency of each member's contributions and their emotions, and encourages members who are not speaking up to participate. The system according to feature 1.

7. The aforementioned whiteboard section is The content of the comments is reflected on the whiteboard in real time, allowing for visual organization of ideas. The system according to feature 1.

8. The aforementioned analysis unit, This system analyzes the content of speeches during meetings, estimates the speaker's intent, and highlights key points based on that estimated intent. The system according to feature 1.

9. The aforementioned analysis unit, By analyzing the content of discussions during meetings and comparing it with past meeting content, we can identify new points for discussion. The system according to feature 1.

10. The aforementioned analysis unit, The system analyzes the content of statements made during meetings, estimates the speaker's level of expertise, and adjusts the analysis results based on the estimated level of expertise. The system according to feature 1.

Images