system

Abstract

The system according to this embodiment aims to automate meeting speeches and summaries, discussion facilitation, and document creation. [Solution] The system according to the embodiment comprises a speaking unit, a summarizing unit, a generation unit, a discussion unit, and a creation unit. The speaking unit automatically performs speech during the meeting. The summarizing unit summarizes the meeting content. The generation unit generates camera footage. The discussion unit sets the agenda and conducts the discussion. The creation unit creates the materials.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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, processes such as conversation, summary, progress of discussion, and document creation in a meeting are performed manually, so there is a problem of low efficiency and long time consumption.

[0005] The system according to the embodiment aims to automate conversation, summary, progress of discussion, and document creation in a meeting.

Means for Solving the Problems

[0006] The system according to the embodiment includes a speaking unit, a summarizing unit, a generating unit, a discussion unit, and a creating unit. The speaking unit automatically conducts conversations in a meeting. The summarizing unit summarizes the meeting content. The generating unit generates camera images. The discussion unit sets topics and advances the discussion. The creating unit creates documents.

Effects of the Invention

[0007] The system according to this embodiment can automate meeting speeches and summaries, discussion facilitation, and document creation. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The meeting support system according to an embodiment of the present invention is a system in which an agent automatically performs speaking and summarizing during a meeting. In this meeting support system, the agent stores materials, communication tools, emails, and conversation history that it owns as a database (DB). During the meeting, the agent follows the flow of conversation in real time, and when it needs to speak, it refers to the DB, synthesizes its own voice, and speaks automatically. After the meeting, it summarizes the meeting content, making it possible to understand the meeting content in 5 minutes even if the person did not attend the meeting. Furthermore, if camera footage is needed, a video generation AI generates camera footage in real time that makes it appear as if the agent is speaking. In addition, it is possible to give an agenda and have the MTG optimizer AIs discuss it and reach a conclusion. The agent also automatically creates materials based on past materials and conversation logs. For example, the agent stores materials, communication tools, emails, and conversation history that it owns as a DB. This DB includes records of past meetings and related materials. For example, presentation materials, minutes, and email exchanges used in past meetings are stored in the DB. Next, during the meeting, the agent follows the flow of conversation in real time. The agent analyzes conversations using speech recognition AI and speaks as needed. For example, if a question is raised during a meeting, the agent consults a database and synthesizes its own voice based on relevant information to provide an answer. After the meeting, the agent summarizes the meeting content. The agent uses natural language processing technology to extract the key points of the meeting and create a summary. This allows even those who were not present to understand the meeting content in 5 minutes. Furthermore, if camera footage is required, the agent uses video generation AI to generate camera footage in real time that makes it appear as if the agent is speaking. For example, when the agent speaks during a remote meeting, the agent's video is displayed, providing a more natural meeting experience. It is also possible to give an agenda and have the MTG optimizer AIs discuss it and reach a conclusion. The agent can even automatically create documents based on past materials and conversation logs. For example, when creating a proposal for a new project, the agent refers to past project materials and conversation logs and automatically creates the proposal.This system significantly improves meeting efficiency, allowing participants to focus on their work without being bogged down by meetings. It also reduces the effort required for document creation, further increasing work efficiency. As a result, the meeting support system can automate meeting speeches, summaries, video generation, discussions, and document creation.

[0029] The meeting support system according to this embodiment comprises a speaking unit, a summarizing unit, a generation unit, a discussion unit, and a creation unit. The speaking unit automatically performs speech during the meeting. The speaking unit performs speech using, for example, speech synthesis technology. The speaking unit can also optimize the timing of speech according to the progress of the meeting. Furthermore, the speaking unit can customize the content of speech according to the level of expertise of the meeting participants. For example, the speaking unit provides detailed technical explanations to participants with high expertise and concise and easy-to-understand explanations to participants with low expertise. The summarizing unit summarizes the meeting content. The summarizing unit extracts the key points of the meeting and creates a summary using, for example, natural language processing technology. The summarizing unit can also adjust the level of detail in the summary based on the importance of the meeting. Furthermore, the summarizing unit can apply different summarization algorithms depending on the category of the meeting. For example, the summarizing unit emphasizes technical points in the case of a technical meeting and business points in the case of a business meeting. The generation unit generates camera footage. The generation unit generates camera footage using, for example, video generation AI. Furthermore, the generation unit can optimize the video content according to the progress of the meeting. In addition, the generation unit can customize the video content according to the expertise level of the meeting participants. For example, the generation unit can generate videos with detailed technical explanations for participants with high expertise, and videos that are concise and easy to understand for participants with low expertise. The discussion unit sets the agenda and conducts the discussion. The discussion unit, for example, conducts discussions amongst itself using MTG optimizer AI to reach conclusions. The discussion unit can also optimize the timing of discussions according to the progress of the meeting. Furthermore, the discussion unit can customize the content of discussions according to the expertise level of the meeting participants. For example, the discussion unit conducts detailed technical discussions for participants with high expertise, and discussions that are concise and easy to understand for participants with low expertise. The creation unit creates the materials. The creation unit, for example, creates new materials by referring to past materials and conversation logs. Furthermore, the creation unit can optimize the content of the materials according to the progress of the meeting. Furthermore, the creation unit can customize the content of the materials according to the expertise level of the meeting participants.For example, the creation unit can create materials containing detailed technical explanations for participants with high expertise, and concise and easy-to-understand materials for participants with low expertise. As a result, the meeting support system according to this embodiment can automatically perform meeting speeches, summaries, video generation, discussions, and material creation.

[0030] The speaking unit automatically handles speech during meetings. For example, it uses speech synthesis technology. Specifically, it employs a Text-to-Speech (TTS) engine, which converts text into speech. This engine can generate natural-sounding speech based on pre-recorded audio data. The speaking unit can also optimize the timing of its speech according to the progress of the meeting. For example, it supports smooth meeting progress by speaking at appropriate times when the meeting agenda changes or when participants ask questions. Furthermore, the speaking unit can customize the content of its speech according to the expertise level of the meeting participants. For example, based on participant profile information, it can provide detailed technical explanations to participants with high expertise and concise, easy-to-understand explanations to participants with low expertise. This customization is achieved by dynamically generating speech content using natural language processing technology. This allows the speaking unit to facilitate smooth meeting progress and provide information in a format that is easily understood by all participants.

[0031] The summarization function summarizes the meeting content. For example, it uses natural language processing techniques to extract key points and create a summary. Specifically, it converts the meeting's audio data into text and uses key phrase extraction algorithms and topic modeling techniques to extract important information from that text data. This allows for a concise summary of the meeting's main agenda and conclusions. The summarization function can also adjust the level of detail in the summary based on the importance of the meeting. For example, it can create a detailed summary for important meetings and a concise summary for routine meetings. Furthermore, the summarization function can apply different summarization algorithms depending on the meeting category. For example, it can emphasize technical points in technical meetings and business points in business meetings. In this way, the summarization function can efficiently summarize the meeting content and provide it in a format that is easy for participants to refer to later.

[0032] The generation unit generates camera footage. For example, it uses video generation AI to generate camera footage. Specifically, the generation unit can optimize the video content according to the progress of the meeting. For example, it can generate graphs and charts related to the meeting agenda in real time, providing participants with visual information. Furthermore, the generation unit can customize the video content according to the expertise level of the meeting participants. For example, it can generate videos with detailed technical explanations for participants with high expertise, and concise and easy-to-understand videos for participants with low expertise. This customization is achieved by the generation AI generating optimal video content based on participant profile information and past meeting data. In addition, the generation unit can dynamically change the video layout and display content in accordance with the progress of the meeting. This allows the generation unit to visually complement the meeting content and deepen participants' understanding.

[0033] The discussion unit sets the agenda and conducts the discussion. For example, the discussion unit can have MTG optimizer AIs discuss amongst themselves and reach a conclusion. Specifically, the discussion unit can optimize the timing of discussions according to the progress of the meeting. For example, if the discussion stalls or an important topic arises, it will facilitate the discussion at the appropriate time. The discussion unit can also customize the content of the discussion according to the level of expertise of the meeting participants. For example, it can conduct detailed technical discussions for participants with high expertise and concise and easy-to-understand discussions for participants with low expertise. This customization is achieved by the discussion AI generating optimal discussion content based on participant profile information and past discussion data. Furthermore, the discussion unit can monitor the progress of the discussion in real time and adjust the direction of the discussion as needed. This allows the discussion unit to conduct discussions efficiently and effectively and reach a conclusion in the meeting.

[0034] The creation team creates the materials. For example, the creation team can create new materials by referring to past materials and conversation logs. Specifically, the creation team can optimize the content of the materials according to the progress of the meeting. For example, it can collect information related to the meeting agenda in real time and reflect it in the materials. The creation team can also customize the content of the materials according to the level of expertise of the meeting participants. For example, it can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise. This customization is achieved by the creation AI generating optimal material content based on participant profile information and past material data. Furthermore, the creation team can dynamically change the layout and design of the materials. This allows the creation team to quickly create and provide materials that effectively convey the content of the meeting to participants.

[0035] The speech unit can retrieve information from a database and make speech based on that information. For example, the speech unit can retrieve information from the database using SQL queries. It can also retrieve information from the database using an API. Furthermore, the speech unit can make speech using speech synthesis technology based on the information retrieved from the database. For example, the speech unit can make speech using speech synthesis technology based on the information retrieved from the database. This allows for the provision of accurate information by making speech based on the information retrieved from the database. Some or all of the above processing in the speech unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the speech unit can input information retrieved from the database into a generative AI, and the generative AI can make speech using speech synthesis technology.

[0036] The summarization unit can analyze meeting content and create a summary. For example, the summarization unit can analyze meeting content using natural language processing technology. It can also analyze meeting content using analysis algorithms. Furthermore, the summarization unit can analyze meeting content and create a summary. For example, the summarization unit can analyze meeting content using natural language processing technology and create a summary. This makes it easier to grasp the key points of the meeting by analyzing the meeting content and creating a summary. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting content into a generative AI, which can then create a summary using natural language processing technology.

[0037] The generation unit can generate camera footage using a video generation AI. For example, the generation unit can generate camera footage using a GAN. Furthermore, the generation unit can generate camera footage using an RNN. In addition, the generation unit can generate camera footage using a video generation AI. For example, the generation unit can generate camera footage using a GAN. This allows for real-time generation of camera footage using a video generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without a generation AI. For example, the generation unit can have a generation AI perform the generation of camera footage.

[0038] The discussion unit can conduct discussions among MTG optimizer AIs and reach conclusions. The discussion unit can conduct discussions using, for example, deep learning models. Furthermore, the discussion unit can conduct discussions using reinforcement learning. In addition, the discussion unit can conduct discussions among MTG optimizer AIs and reach conclusions. For example, the discussion unit can conduct discussions using deep learning models and reach conclusions. This allows for efficient conclusion reckoning through discussions among MTG optimizer AIs. Some or all of the above-described processes in the discussion unit may be performed using, for example, generative AI, or without generative AI. For example, the discussion unit can have a generative AI execute the discussion process.

[0039] The creation unit can create new documents by referring to past documents and conversation logs. For example, the creation unit can refer to past documents and conversation logs by specifying the type of database. The creation unit can also refer to past documents and conversation logs using a search algorithm. Furthermore, the creation unit can create new documents by referring to past documents and conversation logs. For example, the creation unit can refer to past documents and conversation logs by specifying the type of database and create new documents. This allows for the efficient creation of new documents by referring to past documents and conversation logs. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can have a generative AI perform the creation of documents.

[0040] The utterance unit can optimize the timing of its utterances according to the progress of the meeting. For example, if the meeting agenda is ongoing, the utterance unit will insert its comments at the appropriate time. Furthermore, if the meeting is stalled, the utterance unit can make comments to stimulate discussion. In addition, the utterance unit can make comments to emphasize important points near the end of the meeting. For example, the utterance unit optimizes the timing of its utterances according to the progress of the meeting. This optimization of timing according to the meeting's progress enables more effective communication. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the utterance unit can input meeting progress data into a generative AI, which can then optimize the timing of its utterances.

[0041] The utterance unit can customize its utterance content according to the expertise level of the meeting participants. For example, it can provide detailed technical explanations to participants with high expertise, and concise and easy-to-understand explanations to participants with low expertise. Furthermore, if there are participants with different expertise levels, the utterance unit can provide a balanced explanation. For example, it can provide detailed technical explanations to participants with high expertise and concise and easy-to-understand explanations to participants with low expertise. This allows for easily understandable speech by customizing the utterance content according to the expertise level of the meeting participants. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or not. For example, the utterance unit can input participant expertise level data into a generative AI, which can then customize the utterance content.

[0042] The utterance unit can adjust its utterance content to take into account the geographical background of the conference participants. For example, it can explain things to participants from different regions by incorporating region-specific examples. In the case of an international conference, the utterance unit can also make utterances that take cultural backgrounds into account. Furthermore, the utterance unit can explain things using specific examples that are appropriate to the characteristics of the region. For example, it can explain things to participants from different regions by incorporating region-specific examples. By adjusting the utterance content to take into account the geographical background of the conference participants, more appropriate remarks become possible. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the utterance unit can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the utterance content.

[0043] The utterance unit can provide relevant information by referring to the past speaking history of meeting participants when it speaks. For example, the utterance unit can make statements based on ideas previously proposed by participants. The utterance unit can also advance the discussion by quoting past statements by participants. Furthermore, the utterance unit can provide relevant information based on the past speaking history of participants. For example, the utterance unit can make statements based on ideas previously proposed by participants. This allows for more effective discussion by providing relevant information by referring to the past speaking history of meeting participants. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the utterance unit can input data on the participants' past speaking history into a generative AI, and the generative AI can provide relevant information.

[0044] The summarization unit can adjust the level of detail in the summary based on the importance of the meeting. For example, the summarization unit provides a detailed summary for important meetings. It can also provide a concise summary for general meetings. Furthermore, it can provide a summary that highlights the key points for urgent meetings. For example, the summarization unit provides a detailed summary for important meetings. This ensures that an appropriate summary is provided by adjusting the level of detail in the summary based on the importance of the meeting. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting importance data into a generative AI, which can then adjust the level of detail in the summary.

[0045] The summarization unit can apply different summarization algorithms depending on the meeting category during the summarization process. For example, in the case of a technical meeting, the summarization unit can provide a summary that emphasizes the technical points. It can also provide a summary that emphasizes the business points in the case of a business meeting. Furthermore, in the case of an internal company meeting, the summarization unit can provide a summary that takes internal information into account. For example, in the case of a technical meeting, the summarization unit can provide a summary that emphasizes the technical points. This ensures that appropriate summaries are provided by applying different summarization algorithms depending on the meeting category. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting category data into a generative AI, which can then apply different summarization algorithms.

[0046] The summarization unit can determine the priority of summaries based on the timing of the meetings. For example, the summarization unit can prioritize summaries of the most recent meetings. Furthermore, for regular meetings, the summarization unit can provide summaries based on past meeting content. In addition, for urgent meetings, the summarization unit can provide summaries with the highest priority. For example, the summarization unit prioritizes summaries of the most recent meetings. This ensures that appropriate summaries are provided by determining the priority of summaries based on the timing of the meetings. Some or all of the above processing in the summarization unit may be performed using, for example, a generating AI, or without a generating AI. For example, the summarization unit can input meeting timing data into a generating AI, which can then determine the priority of the summaries.

[0047] The summarization unit can adjust the order of summaries based on the relevance of the meeting. For example, the summarization unit may summarize important topics first. It can also prioritize summarizing highly relevant topics. Furthermore, it can postpone summarizing less relevant topics. For example, the summarization unit may summarize important topics first. This ensures that an appropriate summary is provided by adjusting the order of summaries based on the relevance of the meeting. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the summarization unit can input meeting relevance data into a generative AI, which can then adjust the order of summaries.

[0048] The generation unit can optimize the video content according to the progress of the meeting during video generation. For example, if the meeting agenda is ongoing, the video will emphasize content related to the agenda. Furthermore, if the meeting is stalled, the video can provide content to stimulate discussion. Additionally, the generation unit can generate a video that highlights important points near the end of the meeting. For example, the generation unit optimizes the video content according to the progress of the meeting. This optimization of video content according to the meeting's progress provides a more effective video. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input meeting progress data into the generation AI, which can then optimize the video content.

[0049] The generation unit can customize the video content according to the expertise level of the meeting participants during video generation. For example, the generation unit can generate a video with detailed technical explanations for participants with high expertise. It can also generate a concise and easy-to-understand video for participants with low expertise. Furthermore, if there are participants with different expertise levels, the generation unit can generate a balanced video. For example, it can generate a video with detailed technical explanations for participants with high expertise and a concise and easy-to-understand video for participants with low expertise. This ensures that the video content is easy to understand by customizing it according to the expertise level of the meeting participants. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input participant expertise level data into the generation AI, which can then customize the video content.

[0050] The generation unit can adjust the video content when generating the video, taking into account the geographical background of the conference participants. For example, the generation unit can generate videos that include region-specific examples for participants from different regions. In the case of an international conference, the generation unit can also generate videos that take cultural backgrounds into account. Furthermore, the generation unit can generate videos that use specific examples that are appropriate to the characteristics of the region. For example, the generation unit can generate videos that include region-specific examples for participants from different regions. By adjusting the video content to take into account the geographical background of the conference participants, more appropriate videos are provided. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the geographical background data of the participants into the generation AI, and the generation AI can adjust the video content.

[0051] The generation unit can provide relevant videos by referencing the past speaking history of meeting participants when generating videos. For example, the generation unit can generate videos based on ideas previously proposed by participants. The generation unit can also generate videos that advance the discussion by quoting past statements by participants. Furthermore, the generation unit can generate videos that include relevant information based on the past speaking history of participants. For example, the generation unit can generate videos based on ideas previously proposed by participants. This allows for more effective discussions by providing relevant videos by referencing the past speaking history of meeting participants. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the participants' past speaking history into a generation AI, and the generation AI can provide relevant videos.

[0052] The discussion unit can optimize the timing of discussions according to the progress of the meeting. For example, if the meeting agenda is ongoing, the discussion unit will insert discussions at appropriate times. The discussion unit can also speak up to stimulate discussion if the meeting is stalled. Furthermore, the discussion unit can discuss important points to emphasize near the end of the meeting. For example, the discussion unit optimizes the timing of discussions according to the progress of the meeting. This optimization of discussion timing according to the progress of the meeting enables effective discussions. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input meeting progress data into a generative AI, which can then optimize the timing of discussions.

[0053] The discussion unit can customize the content of discussions according to the expertise level of the meeting participants. For example, the discussion unit can provide detailed technical discussions to participants with high expertise, and concise and easy-to-understand discussions to participants with low expertise. Furthermore, the discussion unit can conduct balanced discussions when there are participants with different expertise levels. For example, the discussion unit can provide detailed technical discussions to participants with high expertise and concise and easy-to-understand discussions to participants with low expertise. This makes it possible to conduct discussions that are easy to understand by customizing the content according to the expertise level of the meeting participants. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input participant expertise level data into a generative AI, and the generative AI can customize the discussion content.

[0054] The discussion unit can adjust the content of discussions to take into account the geographical backgrounds of the conference participants. For example, the discussion unit can incorporate region-specific examples into discussions for participants from different regions. In the case of international conferences, the discussion unit can also consider cultural backgrounds. Furthermore, the discussion unit can use specific examples that are appropriate to the characteristics of each region. For example, the discussion unit can incorporate region-specific examples into discussions for participants from different regions. By adjusting the content of discussions to take into account the geographical backgrounds of the conference participants, more appropriate discussions become possible. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the content of the discussion.

[0055] The discussion unit can provide relevant information during a discussion by referring to the past statements of the meeting participants. For example, the discussion unit can conduct the discussion based on ideas previously proposed by the participants. The discussion unit can also advance the discussion by quoting the participants' past statements. Furthermore, the discussion unit can provide relevant information based on the participants' past statements. For example, the discussion unit can conduct the discussion based on ideas previously proposed by the participants. This allows for a more effective discussion by providing relevant information by referring to the past statements of the meeting participants. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input data on the participants' past statements into a generative AI, and the generative AI can provide relevant information.

[0056] The creation unit can optimize the content of the materials according to the progress of the meeting. For example, if the meeting agenda is ongoing, the materials will emphasize content related to the agenda. Also, if the meeting is stalled, the materials can provide content to stimulate discussion. Furthermore, the creation unit can create materials that highlight important points near the end of the meeting. For example, the creation unit optimizes the content of the materials according to the progress of the meeting. This optimizes the content of the materials according to the progress of the meeting, thereby providing more effective materials. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input meeting progress data into a generative AI, and the generative AI can optimize the content of the materials.

[0057] The creation unit can customize the content of the materials according to the expertise level of the meeting participants. For example, it can create materials with detailed technical explanations for participants with high expertise, or create concise and easy-to-understand materials for participants with low expertise. Furthermore, if there are participants with different expertise levels, the creation unit can create balanced materials. For example, it can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise. This ensures that the materials are easy to understand by customizing the content according to the expertise level of the meeting participants. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not. For example, the creation unit can input participant expertise level data into a generative AI, which can then customize the content of the materials.

[0058] The document creation department can adjust the content of the materials when creating them, taking into account the geographical backgrounds of the conference participants. For example, the department can create materials that include region-specific examples for participants from different regions. In the case of international conferences, the department can also create materials that take cultural backgrounds into account. Furthermore, the department can create materials that use specific examples that are appropriate to the characteristics of each region. For example, the department can create materials that include region-specific examples for participants from different regions. By adjusting the content of the materials to take into account the geographical backgrounds of the conference participants, more appropriate materials can be provided. Some or all of the above processing in the document creation department may be performed using, for example, a generative AI, or not using a generative AI. For example, the document creation department can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the content of the materials.

[0059] The creation unit can provide relevant information by referring to the past statements of meeting participants when creating materials. For example, the creation unit can create materials based on ideas previously proposed by participants. The creation unit can also create materials that advance the discussion by quoting past statements of participants. Furthermore, the creation unit can create materials that include relevant information based on the past statements of participants. For example, the creation unit can create materials based on ideas previously proposed by participants. This allows for the provision of more effective materials by referring to the past statements of meeting participants and providing relevant information. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input data on the participants' past statements into a generative AI, and the generative AI can provide relevant information.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The meeting support system can also include a translation function. This function can translate what is said during the meeting in real time and provide it in the appropriate language to participants who speak different languages. For example, it can translate what is said in English into Japanese and provide it to Japanese-speaking participants. Furthermore, the translation function can create meeting summaries in multiple languages ​​and provide these summaries to participants who speak different languages. In addition, the translation function can translate meeting materials into multiple languages ​​and provide these materials to participants who speak different languages. This allows participants who speak different languages ​​to participate in the same meeting and communicate effectively.

[0062] The meeting support system can also include a feedback function. This function collects feedback from participants after the meeting and analyzes areas for improvement. For example, it can conduct surveys to gather opinions on the meeting's progress and content. The feedback function can also make suggestions for improving the meeting's methods and content based on the collected feedback. Furthermore, it can evaluate the meeting based on participant feedback and incorporate the findings into future meetings. This improves the quality of meetings and increases participant satisfaction.

[0063] The meeting support system can also include a scheduling unit. This unit can automatically adjust participants' schedules and suggest the optimal meeting date and time. For example, it can refer to participants' calendars and automatically select a date and time when everyone can attend. The scheduling unit can also prioritize scheduling based on the importance and urgency of the meeting. Furthermore, it can respond to changes in participants' schedules and readjust accordingly. This ensures that all participants can efficiently attend the meeting.

[0064] The meeting support system can also include a reminder function. This function can send reminders to participants before a meeting to encourage preparation. For example, it can send a reminder the day before the meeting, notifying participants of the date, time, location, and agenda. It can also send another reminder immediately before the meeting to ensure participants are on time. Furthermore, the reminder function can include meeting materials and preparation items in the reminders. This allows participants to prepare thoroughly for the meeting, ensuring it runs smoothly.

[0065] The meeting support system can also include an archiving section. This section can store meeting records for extended periods, allowing for later reference. For example, it can archive meeting audio, video, and materials, and play them back as needed. The archiving section can also store meeting summaries and minutes for later review. Furthermore, the archiving section can provide a meeting search function, making it easy to find specific meetings or agenda items. This allows for easy reference of past meeting content and quick retrieval of necessary information.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The utterance unit automatically handles the meeting's speech. The utterance unit uses speech synthesis technology to produce speech and can optimize the timing of speech according to the progress of the meeting. The utterance unit can also customize the content of speech according to the expertise level of the meeting participants. For example, it can provide detailed technical explanations to participants with high expertise and concise, easy-to-understand explanations to participants with low expertise. Step 2: The summarization unit summarizes the meeting content. The summarization unit uses natural language processing techniques to extract the key points of the meeting and create a summary. The summarization unit can also adjust the level of detail in the summary based on the importance of the meeting. Furthermore, the summarization unit can apply different summarization algorithms depending on the category of the meeting. For example, it can emphasize technical points in a technical meeting and business points in a business meeting. Step 3: The generation unit generates camera footage. The generation unit generates camera footage using video generation AI and can optimize the video content according to the progress of the meeting. The generation unit can also customize the video content according to the expertise level of the meeting participants. For example, it can generate videos with detailed technical explanations for participants with high expertise and videos that are concise and easy to understand for participants with low expertise. Step 4: The discussion team sets the agenda and proceeds with the discussion. The discussion team conducts discussions amongst themselves using MTG optimizer AI and reaches a conclusion. The discussion team can also optimize the timing of discussions according to the progress of the meeting. Furthermore, the discussion team can customize the content of the discussion according to the level of expertise of the meeting participants. For example, it can conduct detailed technical discussions for participants with high expertise and concise and easy-to-understand discussions for participants with low expertise. Step 5: The drafting team creates the materials. The drafting team creates new materials by referring to past materials and conversation logs. They can also optimize the content of the materials according to the progress of the meeting. Furthermore, the drafting team can customize the content of the materials according to the level of expertise of the meeting participants. For example, they can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise.

[0068] (Example of form 2) The meeting support system according to an embodiment of the present invention is a system in which an agent automatically performs speaking and summarizing during a meeting. In this meeting support system, the agent stores materials, communication tools, emails, and conversation history that it owns as a database (DB). During the meeting, the agent follows the flow of conversation in real time, and when it needs to speak, it refers to the DB, synthesizes its own voice, and speaks automatically. After the meeting, it summarizes the meeting content, making it possible to understand the meeting content in 5 minutes even if the person did not attend the meeting. Furthermore, if camera footage is needed, a video generation AI generates camera footage in real time that makes it appear as if the agent is speaking. In addition, it is possible to give an agenda and have the MTG optimizer AIs discuss it and reach a conclusion. The agent also automatically creates materials based on past materials and conversation logs. For example, the agent stores materials, communication tools, emails, and conversation history that it owns as a DB. This DB includes records of past meetings and related materials. For example, presentation materials, minutes, and email exchanges used in past meetings are stored in the DB. Next, during the meeting, the agent follows the flow of conversation in real time. The agent analyzes conversations using speech recognition AI and speaks as needed. For example, if a question is raised during a meeting, the agent consults a database and synthesizes its own voice based on relevant information to provide an answer. After the meeting, the agent summarizes the meeting content. The agent uses natural language processing technology to extract the key points of the meeting and create a summary. This allows even those who were not present to understand the meeting content in 5 minutes. Furthermore, if camera footage is required, the agent uses video generation AI to generate camera footage in real time that makes it appear as if the agent is speaking. For example, when the agent speaks during a remote meeting, the agent's video is displayed, providing a more natural meeting experience. It is also possible to give an agenda and have the MTG optimizer AIs discuss it and reach a conclusion. The agent can even automatically create documents based on past materials and conversation logs. For example, when creating a proposal for a new project, the agent refers to past project materials and conversation logs and automatically creates the proposal.This system significantly improves meeting efficiency, allowing participants to focus on their work without being bogged down by meetings. It also reduces the effort required for document creation, further increasing work efficiency. As a result, the meeting support system can automate meeting speeches, summaries, video generation, discussions, and document creation.

[0069] The meeting support system according to this embodiment comprises a speaking unit, a summarizing unit, a generation unit, a discussion unit, and a creation unit. The speaking unit automatically performs speech during the meeting. The speaking unit performs speech using, for example, speech synthesis technology. The speaking unit can also optimize the timing of speech according to the progress of the meeting. Furthermore, the speaking unit can customize the content of speech according to the level of expertise of the meeting participants. For example, the speaking unit provides detailed technical explanations to participants with high expertise and concise and easy-to-understand explanations to participants with low expertise. The summarizing unit summarizes the meeting content. The summarizing unit extracts the key points of the meeting and creates a summary using, for example, natural language processing technology. The summarizing unit can also adjust the level of detail in the summary based on the importance of the meeting. Furthermore, the summarizing unit can apply different summarization algorithms depending on the category of the meeting. For example, the summarizing unit emphasizes technical points in the case of a technical meeting and business points in the case of a business meeting. The generation unit generates camera footage. The generation unit generates camera footage using, for example, video generation AI. Furthermore, the generation unit can optimize the video content according to the progress of the meeting. In addition, the generation unit can customize the video content according to the expertise level of the meeting participants. For example, the generation unit can generate videos with detailed technical explanations for participants with high expertise, and videos that are concise and easy to understand for participants with low expertise. The discussion unit sets the agenda and conducts the discussion. The discussion unit, for example, conducts discussions amongst itself using MTG optimizer AI to reach conclusions. The discussion unit can also optimize the timing of discussions according to the progress of the meeting. Furthermore, the discussion unit can customize the content of discussions according to the expertise level of the meeting participants. For example, the discussion unit conducts detailed technical discussions for participants with high expertise, and discussions that are concise and easy to understand for participants with low expertise. The creation unit creates the materials. The creation unit, for example, creates new materials by referring to past materials and conversation logs. Furthermore, the creation unit can optimize the content of the materials according to the progress of the meeting. Furthermore, the creation unit can customize the content of the materials according to the expertise level of the meeting participants.For example, the creation unit can create materials containing detailed technical explanations for participants with high expertise, and concise and easy-to-understand materials for participants with low expertise. As a result, the meeting support system according to this embodiment can automatically perform meeting speeches, summaries, video generation, discussions, and material creation.

[0070] The speaking unit automatically handles speech during meetings. For example, it uses speech synthesis technology. Specifically, it employs a Text-to-Speech (TTS) engine, which converts text into speech. This engine can generate natural-sounding speech based on pre-recorded audio data. The speaking unit can also optimize the timing of its speech according to the progress of the meeting. For example, it supports smooth meeting progress by speaking at appropriate times when the meeting agenda changes or when participants ask questions. Furthermore, the speaking unit can customize the content of its speech according to the expertise level of the meeting participants. For example, based on participant profile information, it can provide detailed technical explanations to participants with high expertise and concise, easy-to-understand explanations to participants with low expertise. This customization is achieved by dynamically generating speech content using natural language processing technology. This allows the speaking unit to facilitate smooth meeting progress and provide information in a format that is easily understood by all participants.

[0071] The summarization function summarizes the meeting content. For example, it uses natural language processing techniques to extract key points and create a summary. Specifically, it converts the meeting's audio data into text and uses key phrase extraction algorithms and topic modeling techniques to extract important information from that text data. This allows for a concise summary of the meeting's main agenda and conclusions. The summarization function can also adjust the level of detail in the summary based on the importance of the meeting. For example, it can create a detailed summary for important meetings and a concise summary for routine meetings. Furthermore, the summarization function can apply different summarization algorithms depending on the meeting category. For example, it can emphasize technical points in technical meetings and business points in business meetings. In this way, the summarization function can efficiently summarize the meeting content and provide it in a format that is easy for participants to refer to later.

[0072] The generation unit generates camera footage. For example, it uses video generation AI to generate camera footage. Specifically, the generation unit can optimize the video content according to the progress of the meeting. For example, it can generate graphs and charts related to the meeting agenda in real time, providing participants with visual information. Furthermore, the generation unit can customize the video content according to the expertise level of the meeting participants. For example, it can generate videos with detailed technical explanations for participants with high expertise, and concise and easy-to-understand videos for participants with low expertise. This customization is achieved by the generation AI generating optimal video content based on participant profile information and past meeting data. In addition, the generation unit can dynamically change the video layout and display content in accordance with the progress of the meeting. This allows the generation unit to visually complement the meeting content and deepen participants' understanding.

[0073] The discussion unit sets the agenda and conducts the discussion. For example, the discussion unit can have MTG optimizer AIs discuss amongst themselves and reach a conclusion. Specifically, the discussion unit can optimize the timing of discussions according to the progress of the meeting. For example, if the discussion stalls or an important topic arises, it will facilitate the discussion at the appropriate time. The discussion unit can also customize the content of the discussion according to the level of expertise of the meeting participants. For example, it can conduct detailed technical discussions for participants with high expertise and concise and easy-to-understand discussions for participants with low expertise. This customization is achieved by the discussion AI generating optimal discussion content based on participant profile information and past discussion data. Furthermore, the discussion unit can monitor the progress of the discussion in real time and adjust the direction of the discussion as needed. This allows the discussion unit to conduct discussions efficiently and effectively and reach a conclusion in the meeting.

[0074] The creation team creates the materials. For example, the creation team can create new materials by referring to past materials and conversation logs. Specifically, the creation team can optimize the content of the materials according to the progress of the meeting. For example, it can collect information related to the meeting agenda in real time and reflect it in the materials. The creation team can also customize the content of the materials according to the level of expertise of the meeting participants. For example, it can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise. This customization is achieved by the creation AI generating optimal material content based on participant profile information and past material data. Furthermore, the creation team can dynamically change the layout and design of the materials. This allows the creation team to quickly create and provide materials that effectively convey the content of the meeting to participants.

[0075] The speech unit can retrieve information from a database and make speech based on that information. For example, the speech unit can retrieve information from the database using SQL queries. It can also retrieve information from the database using an API. Furthermore, the speech unit can make speech using speech synthesis technology based on the information retrieved from the database. For example, the speech unit can make speech using speech synthesis technology based on the information retrieved from the database. This allows for the provision of accurate information by making speech based on the information retrieved from the database. Some or all of the above processing in the speech unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the speech unit can input information retrieved from the database into a generative AI, and the generative AI can make speech using speech synthesis technology.

[0076] The summarization unit can analyze meeting content and create a summary. For example, the summarization unit can analyze meeting content using natural language processing technology. It can also analyze meeting content using analysis algorithms. Furthermore, the summarization unit can analyze meeting content and create a summary. For example, the summarization unit can analyze meeting content using natural language processing technology and create a summary. This makes it easier to grasp the key points of the meeting by analyzing the meeting content and creating a summary. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting content into a generative AI, which can then create a summary using natural language processing technology.

[0077] The generation unit can generate camera footage using a video generation AI. For example, the generation unit can generate camera footage using a GAN. Furthermore, the generation unit can generate camera footage using an RNN. In addition, the generation unit can generate camera footage using a video generation AI. For example, the generation unit can generate camera footage using a GAN. This allows for real-time generation of camera footage using a video generation AI. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or without a generation AI. For example, the generation unit can have a generation AI perform the generation of camera footage.

[0078] The discussion unit can conduct discussions among MTG optimizer AIs and reach conclusions. The discussion unit can conduct discussions using, for example, deep learning models. Furthermore, the discussion unit can conduct discussions using reinforcement learning. In addition, the discussion unit can conduct discussions among MTG optimizer AIs and reach conclusions. For example, the discussion unit can conduct discussions using deep learning models and reach conclusions. This allows for efficient conclusion reckoning through discussions among MTG optimizer AIs. Some or all of the above-described processes in the discussion unit may be performed using, for example, generative AI, or without generative AI. For example, the discussion unit can have a generative AI execute the discussion process.

[0079] The creation unit can create new documents by referring to past documents and conversation logs. For example, the creation unit can refer to past documents and conversation logs by specifying the type of database. The creation unit can also refer to past documents and conversation logs using a search algorithm. Furthermore, the creation unit can create new documents by referring to past documents and conversation logs. For example, the creation unit can refer to past documents and conversation logs by specifying the type of database and create new documents. This allows for the efficient creation of new documents by referring to past documents and conversation logs. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can have a generative AI perform the creation of documents.

[0080] The speech unit can estimate the user's emotions and adjust its speech content based on the estimated emotions. For example, the speech unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the speech unit can adjust its speech content based on the estimated emotions. For example, if the user is tense, the speech unit can speak in a calm tone to help them relax. If the user is excited, the speech unit can balance this by speaking calmly. Furthermore, if the user is tired, the speech unit can speak concisely and clearly. This allows for more appropriate speech by adjusting the speech content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech unit may be performed using, for example, generative AI, or without generative AI. For example, the speech unit can input user emotion data into a generating AI, which can then adjust the content of the speech.

[0081] The utterance unit can optimize the timing of its utterances according to the progress of the meeting. For example, if the meeting agenda is ongoing, the utterance unit will insert its comments at the appropriate time. Furthermore, if the meeting is stalled, the utterance unit can make comments to stimulate discussion. In addition, the utterance unit can make comments to emphasize important points near the end of the meeting. For example, the utterance unit optimizes the timing of its utterances according to the progress of the meeting. This optimization of timing according to the meeting's progress enables more effective communication. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the utterance unit can input meeting progress data into a generative AI, which can then optimize the timing of its utterances.

[0082] The utterance unit can customize its utterance content according to the expertise level of the meeting participants. For example, it can provide detailed technical explanations to participants with high expertise, and concise and easy-to-understand explanations to participants with low expertise. Furthermore, if there are participants with different expertise levels, the utterance unit can provide a balanced explanation. For example, it can provide detailed technical explanations to participants with high expertise and concise and easy-to-understand explanations to participants with low expertise. This allows for easily understandable speech by customizing the utterance content according to the expertise level of the meeting participants. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or not. For example, the utterance unit can input participant expertise level data into a generative AI, which can then customize the utterance content.

[0083] The speech unit can estimate the user's emotions and adjust the tone and speed of speech based on the estimated emotions. For example, the speech unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the speech unit can adjust the tone and speed of speech based on the estimated emotions. For example, if the user is relaxed, the speech unit will speak in a relaxed tone. If the user is in a hurry, the speech unit can speak quickly and concisely. Furthermore, if the user is excited, the speech unit can speak in a calm and composed tone. This allows for more appropriate speech by adjusting the tone and speed of speech according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech unit may be performed using, for example, generative AI, or without generative AI. For example, the speech unit can input user emotion data into a generating AI, which can then adjust the tone and speed of the speech.

[0084] The utterance unit can adjust its utterance content to take into account the geographical background of the conference participants. For example, it can explain things to participants from different regions by incorporating region-specific examples. In the case of an international conference, the utterance unit can also make utterances that take cultural backgrounds into account. Furthermore, the utterance unit can explain things using specific examples that are appropriate to the characteristics of the region. For example, it can explain things to participants from different regions by incorporating region-specific examples. By adjusting the utterance content to take into account the geographical background of the conference participants, more appropriate remarks become possible. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the utterance unit can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the utterance content.

[0085] The utterance unit can provide relevant information by referring to the past speaking history of meeting participants when it speaks. For example, the utterance unit can make statements based on ideas previously proposed by participants. The utterance unit can also advance the discussion by quoting past statements by participants. Furthermore, the utterance unit can provide relevant information based on the past speaking history of participants. For example, the utterance unit can make statements based on ideas previously proposed by participants. This allows for more effective discussion by providing relevant information by referring to the past speaking history of meeting participants. Some or all of the above processing in the utterance unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the utterance unit can input data on the participants' past speaking history into a generative AI, and the generative AI can provide relevant information.

[0086] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, the summarization unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the summarization unit can adjust the way the summary is presented based on the estimated emotions. For example, if the user is relaxed, the summarization unit can provide a detailed summary. If the user is in a hurry, it can provide a concise summary. Furthermore, if the user is excited, it can provide a summary that emphasizes the key points. This allows for the provision of a more appropriate summary by adjusting the way the summary is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input user sentiment data into a generating AI, which can then adjust how the summary is expressed.

[0087] The summarization unit can adjust the level of detail in the summary based on the importance of the meeting. For example, the summarization unit provides a detailed summary for important meetings. It can also provide a concise summary for general meetings. Furthermore, it can provide a summary that highlights the key points for urgent meetings. For example, the summarization unit provides a detailed summary for important meetings. This ensures that an appropriate summary is provided by adjusting the level of detail in the summary based on the importance of the meeting. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting importance data into a generative AI, which can then adjust the level of detail in the summary.

[0088] The summarization unit can apply different summarization algorithms depending on the meeting category during the summarization process. For example, in the case of a technical meeting, the summarization unit can provide a summary that emphasizes the technical points. It can also provide a summary that emphasizes the business points in the case of a business meeting. Furthermore, in the case of an internal company meeting, the summarization unit can provide a summary that takes internal information into account. For example, in the case of a technical meeting, the summarization unit can provide a summary that emphasizes the technical points. This ensures that appropriate summaries are provided by applying different summarization algorithms depending on the meeting category. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting category data into a generative AI, which can then apply different summarization algorithms.

[0089] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, the summarization unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the summarization unit can adjust the length of the summary based on the estimated emotions. For example, if the user is in a hurry, the summarization unit can provide a short, concise summary. If the user is relaxed, it can provide a longer summary with more detailed explanations. Furthermore, if the user is excited, it can provide a summary with visually stimulating effects. This allows for the provision of more appropriate summaries by adjusting the length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input user sentiment data into a generating AI, which can then adjust the length of the summary.

[0090] The summarization unit can determine the priority of summaries based on the timing of the meetings. For example, the summarization unit can prioritize summaries of the most recent meetings. Furthermore, for regular meetings, the summarization unit can provide summaries based on past meeting content. In addition, for urgent meetings, the summarization unit can provide summaries with the highest priority. For example, the summarization unit prioritizes summaries of the most recent meetings. This ensures that appropriate summaries are provided by determining the priority of summaries based on the timing of the meetings. Some or all of the above processing in the summarization unit may be performed using, for example, a generating AI, or without a generating AI. For example, the summarization unit can input meeting timing data into a generating AI, which can then determine the priority of the summaries.

[0091] The summarization unit can adjust the order of summaries based on the relevance of the meeting. For example, the summarization unit may summarize important topics first. It can also prioritize summarizing highly relevant topics. Furthermore, it can postpone summarizing less relevant topics. For example, the summarization unit may summarize important topics first. This ensures that an appropriate summary is provided by adjusting the order of summaries based on the relevance of the meeting. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the summarization unit can input meeting relevance data into a generative AI, which can then adjust the order of summaries.

[0092] The generation unit can estimate the user's emotions and adjust the way the generated video is presented based on the estimated emotions. For example, the generation unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using voice analysis technology. Furthermore, the generation unit can adjust the way the generated video is presented based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a video that progresses at a leisurely pace. If the user is in a hurry, the generation unit can also generate a video that emphasizes the shortest route. Furthermore, if the user is excited, the generation unit can generate a video with visually stimulating effects. In this way, by adjusting the way the video is presented according to the user's emotions, a more appropriate video is provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input user emotion data into the generation AI, which can then adjust the way the video is expressed.

[0093] The generation unit can optimize the video content according to the progress of the meeting during video generation. For example, if the meeting agenda is ongoing, the video will emphasize content related to the agenda. Furthermore, if the meeting is stalled, the video can provide content to stimulate discussion. Additionally, the generation unit can generate a video that highlights important points near the end of the meeting. For example, the generation unit optimizes the video content according to the progress of the meeting. This optimization of video content according to the meeting's progress provides a more effective video. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input meeting progress data into the generation AI, which can then optimize the video content.

[0094] The generation unit can customize the video content according to the expertise level of the meeting participants during video generation. For example, the generation unit can generate a video with detailed technical explanations for participants with high expertise. It can also generate a concise and easy-to-understand video for participants with low expertise. Furthermore, if there are participants with different expertise levels, the generation unit can generate a balanced video. For example, it can generate a video with detailed technical explanations for participants with high expertise and a concise and easy-to-understand video for participants with low expertise. This ensures that the video content is easy to understand by customizing it according to the expertise level of the meeting participants. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not. For example, the generation unit can input participant expertise level data into the generation AI, which can then customize the video content.

[0095] The generation unit can estimate the user's emotions and adjust the tone and speed of the generated video based on the estimated emotions. For example, the generation unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using voice analysis technology. Furthermore, the generation unit can adjust the tone and speed of the generated video based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate a video with a relaxed tone. If the user is in a hurry, the generation unit can generate a fast-paced and concise video. Furthermore, if the user is excited, the generation unit can generate a video with visually stimulating effects. This allows for the provision of more appropriate video by adjusting the tone and speed of the video according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or without a generation AI. For example, the generation unit can input user emotion data into the generation AI, which can then adjust the tone and speed of the video.

[0096] The generation unit can adjust the video content when generating the video, taking into account the geographical background of the conference participants. For example, the generation unit can generate videos that include region-specific examples for participants from different regions. In the case of an international conference, the generation unit can also generate videos that take cultural backgrounds into account. Furthermore, the generation unit can generate videos that use specific examples that are appropriate to the characteristics of the region. For example, the generation unit can generate videos that include region-specific examples for participants from different regions. By adjusting the video content to take into account the geographical background of the conference participants, more appropriate videos are provided. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the geographical background data of the participants into the generation AI, and the generation AI can adjust the video content.

[0097] The generation unit can provide relevant videos by referencing the past speaking history of meeting participants when generating videos. For example, the generation unit can generate videos based on ideas previously proposed by participants. The generation unit can also generate videos that advance the discussion by quoting past statements by participants. Furthermore, the generation unit can generate videos that include relevant information based on the past speaking history of participants. For example, the generation unit can generate videos based on ideas previously proposed by participants. This allows for more effective discussions by providing relevant videos by referencing the past speaking history of meeting participants. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input data on the participants' past speaking history into a generation AI, and the generation AI can provide relevant videos.

[0098] The discussion unit can estimate the user's emotions and adjust the discussion process based on the estimated emotions. For example, the discussion unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the discussion unit can adjust the discussion process based on the estimated emotions. For example, if the user is tense, the discussion unit can conduct the discussion calmly to help them relax. If the user is excited, the discussion unit can balance this by conducting the discussion calmly. Furthermore, if the user is tired, the discussion unit can conduct the discussion concisely and clearly. This allows for more appropriate discussions by adjusting the discussion process according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, 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 discussion unit may be performed using, for example, generative AI, or without generative AI. For example, the discussion unit can input user emotion data into a generating AI, which can then adjust how the discussion progresses.

[0099] The discussion unit can optimize the timing of discussions according to the progress of the meeting. For example, if the meeting agenda is ongoing, the discussion unit will insert discussions at appropriate times. The discussion unit can also speak up to stimulate discussion if the meeting is stalled. Furthermore, the discussion unit can discuss important points to emphasize near the end of the meeting. For example, the discussion unit optimizes the timing of discussions according to the progress of the meeting. This optimization of discussion timing according to the progress of the meeting enables effective discussions. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input meeting progress data into a generative AI, which can then optimize the timing of discussions.

[0100] The discussion unit can customize the content of discussions according to the expertise level of the meeting participants. For example, the discussion unit can provide detailed technical discussions to participants with high expertise, and concise and easy-to-understand discussions to participants with low expertise. Furthermore, the discussion unit can conduct balanced discussions when there are participants with different expertise levels. For example, the discussion unit can provide detailed technical discussions to participants with high expertise and concise and easy-to-understand discussions to participants with low expertise. This makes it possible to conduct discussions that are easy to understand by customizing the content according to the expertise level of the meeting participants. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input participant expertise level data into a generative AI, and the generative AI can customize the discussion content.

[0101] The discussion unit can estimate the user's emotions and adjust the tone and pace of the discussion based on the estimated emotions. For example, the discussion unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the discussion unit can adjust the tone and pace of the discussion based on the estimated emotions. For example, if the user is relaxed, the discussion unit will proceed in a relaxed tone. If the user is in a hurry, the discussion unit can conduct a quick and concise discussion. Furthermore, if the user is excited, the discussion unit can proceed in a calm and composed tone. This allows for a more appropriate discussion by adjusting the tone and pace of the discussion according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the discussion unit may be performed using, for example, generative AI, or without generative AI. For example, the discussion section can input user emotion data into a generating AI, which can then adjust the tone and pace of the discussion.

[0102] The discussion unit can adjust the content of discussions to take into account the geographical backgrounds of the conference participants. For example, the discussion unit can incorporate region-specific examples into discussions for participants from different regions. In the case of international conferences, the discussion unit can also consider cultural backgrounds. Furthermore, the discussion unit can use specific examples that are appropriate to the characteristics of each region. For example, the discussion unit can incorporate region-specific examples into discussions for participants from different regions. By adjusting the content of discussions to take into account the geographical backgrounds of the conference participants, more appropriate discussions become possible. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the content of the discussion.

[0103] The discussion unit can provide relevant information during a discussion by referring to the past statements of the meeting participants. For example, the discussion unit can conduct the discussion based on ideas previously proposed by the participants. The discussion unit can also advance the discussion by quoting the participants' past statements. Furthermore, the discussion unit can provide relevant information based on the participants' past statements. For example, the discussion unit can conduct the discussion based on ideas previously proposed by the participants. This allows for a more effective discussion by providing relevant information by referring to the past statements of the meeting participants. Some or all of the above processing in the discussion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the discussion unit can input data on the participants' past statements into a generative AI, and the generative AI can provide relevant information.

[0104] The creation unit can estimate the user's emotions and adjust the presentation of the materials based on the estimated emotions. For example, the creation unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using voice analysis technology. Furthermore, the creation unit can adjust the presentation of the materials based on the estimated emotions. For example, if the user is relaxed, the creation unit can provide detailed materials. If the user is in a hurry, it can provide concise materials. Furthermore, if the user is excited, it can provide materials with visually stimulating effects. In this way, by adjusting the presentation of the materials according to the user's emotions, more appropriate materials are provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the creation unit may be performed using, for example, generative AI, or without generative AI. For example, the creation unit can input user emotion data into the generating AI, which can then adjust the way the document is presented.

[0105] The creation unit can optimize the content of the materials according to the progress of the meeting. For example, if the meeting agenda is ongoing, the materials will emphasize content related to the agenda. Also, if the meeting is stalled, the materials can provide content to stimulate discussion. Furthermore, the creation unit can create materials that highlight important points near the end of the meeting. For example, the creation unit optimizes the content of the materials according to the progress of the meeting. This optimizes the content of the materials according to the progress of the meeting, thereby providing more effective materials. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input meeting progress data into a generative AI, and the generative AI can optimize the content of the materials.

[0106] The creation unit can customize the content of the materials according to the expertise level of the meeting participants. For example, it can create materials with detailed technical explanations for participants with high expertise, or create concise and easy-to-understand materials for participants with low expertise. Furthermore, if there are participants with different expertise levels, the creation unit can create balanced materials. For example, it can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise. This ensures that the materials are easy to understand by customizing the content according to the expertise level of the meeting participants. Some or all of the above processes in the creation unit may be performed using, for example, a generative AI, or not. For example, the creation unit can input participant expertise level data into a generative AI, which can then customize the content of the materials.

[0107] The creation unit can estimate the user's emotions and adjust the tone and speed of the material based on the estimated emotions. For example, the creation unit can estimate the user's emotions using facial recognition technology. It can also estimate the user's emotions using speech analysis technology. Furthermore, the creation unit can adjust the tone and speed of the material based on the estimated emotions. For example, if the user is relaxed, the creation unit can create material that proceeds in a relaxed tone. If the user is in a hurry, the creation unit can create material that is quick and concise. Furthermore, if the user is excited, the creation unit can create material with visually stimulating effects. This allows for the provision of more appropriate material by adjusting the tone and speed of the material according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, 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 creation unit may be performed using, for example, generative AI, or without generative AI. For example, the creation unit can input user emotion data into a generating AI, which can then adjust the tone and pace of the document.

[0108] The document creation department can adjust the content of the materials when creating them, taking into account the geographical backgrounds of the conference participants. For example, the department can create materials that include region-specific examples for participants from different regions. In the case of international conferences, the department can also create materials that take cultural backgrounds into account. Furthermore, the department can create materials that use specific examples that are appropriate to the characteristics of each region. For example, the department can create materials that include region-specific examples for participants from different regions. By adjusting the content of the materials to take into account the geographical backgrounds of the conference participants, more appropriate materials can be provided. Some or all of the above processing in the document creation department may be performed using, for example, a generative AI, or not using a generative AI. For example, the document creation department can input the geographical background data of the participants into a generative AI, and the generative AI can adjust the content of the materials.

[0109] The creation unit can provide relevant information by referring to the past statements of meeting participants when creating materials. For example, the creation unit can create materials based on ideas previously proposed by participants. The creation unit can also create materials that advance the discussion by quoting past statements of participants. Furthermore, the creation unit can create materials that include relevant information based on the past statements of participants. For example, the creation unit can create materials based on ideas previously proposed by participants. This allows for the provision of more effective materials by referring to the past statements of meeting participants and providing relevant information. Some or all of the above processing in the creation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the creation unit can input data on the participants' past statements into a generative AI, and the generative AI can provide relevant information.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The meeting support system can also include a translation function. This function can translate what is said during the meeting in real time and provide it in the appropriate language to participants who speak different languages. For example, it can translate what is said in English into Japanese and provide it to Japanese-speaking participants. Furthermore, the translation function can create meeting summaries in multiple languages ​​and provide these summaries to participants who speak different languages. In addition, the translation function can translate meeting materials into multiple languages ​​and provide these materials to participants who speak different languages. This allows participants who speak different languages ​​to participate in the same meeting and communicate effectively.

[0112] The meeting support system can also include a feedback function. This function collects feedback from participants after the meeting and analyzes areas for improvement. For example, it can conduct surveys to gather opinions on the meeting's progress and content. The feedback function can also make suggestions for improving the meeting's methods and content based on the collected feedback. Furthermore, it can evaluate the meeting based on participant feedback and incorporate the findings into future meetings. This improves the quality of meetings and increases participant satisfaction.

[0113] The meeting support system can also include a scheduling unit. This unit can automatically adjust participants' schedules and suggest the optimal meeting date and time. For example, it can refer to participants' calendars and automatically select a date and time when everyone can attend. The scheduling unit can also prioritize scheduling based on the importance and urgency of the meeting. Furthermore, it can respond to changes in participants' schedules and readjust accordingly. This ensures that all participants can efficiently attend the meeting.

[0114] The meeting support system can also include a reminder function. This function can send reminders to participants before a meeting to encourage preparation. For example, it can send a reminder the day before the meeting, notifying participants of the date, time, location, and agenda. It can also send another reminder immediately before the meeting to ensure participants are on time. Furthermore, the reminder function can include meeting materials and preparation items in the reminders. This allows participants to prepare thoroughly for the meeting, ensuring it runs smoothly.

[0115] The meeting support system can also include an archiving section. This section can store meeting records for extended periods, allowing for later reference. For example, it can archive meeting audio, video, and materials, and play them back as needed. The archiving section can also store meeting summaries and minutes for later review. Furthermore, the archiving section can provide a meeting search function, making it easy to find specific meetings or agenda items. This allows for easy reference of past meeting content and quick retrieval of necessary information.

[0116] The meeting support system can also be equipped with an emotion analysis unit. This unit can analyze participants' emotions in real time during a meeting and reflect this in the meeting's progress. For example, it can use facial recognition technology to estimate participants' emotions and respond appropriately according to the meeting's progress. Furthermore, the emotion analysis unit can use voice analysis technology to estimate participants' emotions and adjust the tone and content of their speech. In addition, the emotion analysis unit can analyze participants' emotional data after the meeting and suggest areas for improvement. This enables meeting management that takes participants' emotions into consideration, providing a better meeting experience.

[0117] The meeting support system can also include a stress management unit. This unit can monitor participants' stress levels during meetings and take appropriate measures. For example, it can measure heart rate and skin electrical activity to estimate participants' stress levels. The stress management unit can also provide relaxation advice if stress levels are high. Furthermore, it can analyze stress level data after the meeting and offer suggestions for reducing stress. This reduces participant stress and provides a more comfortable meeting environment.

[0118] The meeting support system can also include a motivation enhancement unit. This unit can provide functions to increase participant motivation during meetings. For example, it can evaluate participants' contributions and speeches, awarding points or badges. Furthermore, the unit can provide feedback to participants according to the meeting's progress to maintain motivation. It can also analyze participant motivation data after the meeting and offer suggestions to further enhance motivation. This can increase participant motivation and encourage more active participation in meetings.

[0119] The meeting support system can also include a conflict management unit. This unit can manage disagreements and clashes of opinion among participants during a meeting, facilitating smooth discussion. For example, it can mediate neutrally when a conflict arises. Furthermore, the conflict management unit can analyze the causes of conflicts and propose solutions. It can also analyze conflict data after the meeting and make suggestions to prevent future conflicts. This effectively manages conflicts among participants and promotes constructive discussion.

[0120] The meeting support system can also be equipped with an engagement enhancement unit. This unit can provide functions to increase participant engagement during meetings. For example, it can analyze the number of times and the content of participants' contributions and evaluate highly engaged participants. The engagement enhancement unit can also solicit questions and opinions from participants as the meeting progresses. Furthermore, it can analyze participant engagement data after the meeting and provide suggestions for improving engagement. This can increase participant engagement and lead to more active meetings.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The utterance unit automatically handles the meeting's speech. The utterance unit uses speech synthesis technology to produce speech and can optimize the timing of speech according to the progress of the meeting. The utterance unit can also customize the content of speech according to the expertise level of the meeting participants. For example, it can provide detailed technical explanations to participants with high expertise and concise, easy-to-understand explanations to participants with low expertise. Step 2: The summarization unit summarizes the meeting content. The summarization unit uses natural language processing techniques to extract the key points of the meeting and create a summary. The summarization unit can also adjust the level of detail in the summary based on the importance of the meeting. Furthermore, the summarization unit can apply different summarization algorithms depending on the category of the meeting. For example, it can emphasize technical points in a technical meeting and business points in a business meeting. Step 3: The generation unit generates camera footage. The generation unit generates camera footage using video generation AI and can optimize the video content according to the progress of the meeting. The generation unit can also customize the video content according to the expertise level of the meeting participants. For example, it can generate videos with detailed technical explanations for participants with high expertise and videos that are concise and easy to understand for participants with low expertise. Step 4: The discussion team sets the agenda and proceeds with the discussion. The discussion team conducts discussions amongst themselves using MTG optimizer AI and reaches a conclusion. The discussion team can also optimize the timing of discussions according to the progress of the meeting. Furthermore, the discussion team can customize the content of the discussion according to the level of expertise of the meeting participants. For example, it can conduct detailed technical discussions for participants with high expertise and concise and easy-to-understand discussions for participants with low expertise. Step 5: The drafting team creates the materials. The drafting team creates new materials by referring to past materials and conversation logs. They can also optimize the content of the materials according to the progress of the meeting. Furthermore, the drafting team can customize the content of the materials according to the level of expertise of the meeting participants. For example, they can create materials with detailed technical explanations for participants with high expertise and concise and easy-to-understand materials for participants with low expertise.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the speaking unit, summarizing unit, generation unit, discussion unit, and creation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the speaking unit is implemented by the processor 46 of the smart device 14 and performs speech using speech synthesis technology. The summarizing unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts the key points of a meeting and creates a summary using natural language processing technology. The generation unit is implemented by the processor 46 of the smart device 14 and generates camera footage using video generation AI. The discussion unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts discussions among the MTG optimizer AIs to reach a conclusion. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates new materials by referring to past materials and conversation logs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the speech unit, summarization unit, generation unit, discussion unit, and creation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the speech unit is implemented by the processor 46 of the smart glasses 214 and performs speech using speech synthesis technology. The summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts the key points of a meeting and creates a summary using natural language processing technology. The generation unit is implemented by the processor 46 of the smart glasses 214 and generates camera footage using video generation AI. The discussion unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts discussions among the MTG optimizer AIs to reach a conclusion. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates new materials by referring to past materials and conversation logs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the speech unit, summarization unit, generation unit, discussion unit, and creation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the speech unit is implemented by the processor 46 of the headset terminal 314 and performs speech using speech synthesis technology. The summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts the key points of a meeting and creates a summary using natural language processing technology. The generation unit is implemented by the processor 46 of the headset terminal 314 and generates camera footage using video generation AI. The discussion unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts discussions among the MTG optimizer AIs to reach a conclusion. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates new materials by referring to past materials and conversation logs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the speaking unit, summarizing unit, generation unit, discussion unit, and creation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the speaking unit is implemented by the processor 46 of the robot 414 and performs speech using speech synthesis technology. The summarizing unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts the main points of a meeting and creates a summary using natural language processing technology. The generation unit is implemented by the processor 46 of the robot 414 and generates camera footage using video generation AI. The discussion unit is implemented by the specific processing unit 290 of the data processing unit 12 and conducts discussions among the MTG optimizer AIs to reach a conclusion. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates new materials by referring to past materials and conversation logs. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) A speech unit that automatically performs speeches during meetings, A summary section that summarizes the meeting content, A generation unit that generates camera images, The discussion group sets the agenda and proceeds with the discussion, A document creation unit, A system characterized by the following features. (Note 2) The aforementioned speech unit, The system retrieves information from a database and uses that information to produce speech. The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Analyze the meeting content and create a summary. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate camera footage using video generation AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned discussion section is, MTG optimizer AIs engage in discussions and reach conclusions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned creation unit, Create new documents by referring to past documents and conversation logs. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned speech unit, It estimates the user's emotions and adjusts the content of the speech based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned speech unit, When speaking, optimize the timing of your utterances according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned speech unit, When speaking, the content of the speech is customized according to the expertise level of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned speech unit, It estimates the user's emotions and adjusts the tone and speed of speech based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned speech unit, When speaking, adjust your speech to take into account the geographical background of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned speech unit, When someone speaks, the system provides relevant information by referring to the past speaking history of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The summary section above is, When summarizing, adjust the level of detail in the summary based on the importance of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, When summarizing, different summarization algorithms are applied depending on the meeting category. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The summary section above is, When summarizing, prioritize summaries based on when the meetings took place. The system described in Appendix 1, characterized by the features described herein. (Note 18) The summary section above is, When summarizing, adjust the order of summaries based on their relevance to the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the way the generated video is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating video, the video content is optimized according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating the video, customize the video content according to the expertise level of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts the tone and speed of the generated video based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating the video, the video content is adjusted to take into account the geographical background of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating video, the system references the past statements of meeting participants to provide relevant footage. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned discussion section is, It estimates the user's emotions and adjusts the discussion process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned discussion section is, During discussions, optimize the timing of discussions according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned discussion section is, During discussions, customize the content of the discussion according to the level of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned discussion section is, It estimates the user's emotions and adjusts the tone and pace of the discussion based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned discussion section is, During discussions, we adjust the content of the discussion to take into account the geographical background of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned discussion section is, During discussions, refer to the past statements of meeting participants to provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned creation unit, It estimates the user's emotions and adjusts the way the material is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned creation unit, When creating documents, optimize the content of the documents according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned creation unit, When creating materials, customize the content according to the expertise level of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned creation unit, It estimates the user's emotions and adjusts the tone and pace of the material based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned creation unit, When preparing materials, adjust the content to take into account the geographical background of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned creation unit, When creating materials, refer to the past statements of meeting participants to provide relevant information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A speech unit that automatically performs speeches during meetings, A summary section that summarizes the meeting content, A generation unit that generates camera images, The discussion group sets the agenda and proceeds with the discussion, A document creation unit, A system characterized by the following features.

2. The aforementioned speech unit, The system retrieves information from a database and uses that information to produce speech. The system according to feature 1.

3. The summary section above is, Analyze the meeting content and create a summary. The system according to feature 1.

4. The generating unit is Generate camera footage using video generation AI. The system according to feature 1.

5. The aforementioned discussion section is, MTG optimizer: AIs engage in discussions and reach conclusions. The system according to feature 1.

6. The aforementioned creation unit, Create new documents by referring to past documents and conversation logs. The system according to feature 1.

7. The aforementioned speech unit, It estimates the user's emotions and adjusts the content of the speech based on the estimated emotions. The system according to feature 1.

8. The aforementioned speech unit, When speaking, optimize the timing of your utterances according to the progress of the meeting. The system according to feature 1.

9. The aforementioned speech unit, When speaking, the content of the speech is customized according to the expertise level of the meeting participants. The system according to feature 1.

10. The aforementioned speech unit, It estimates the user's emotions and adjusts the tone and speed of speech based on those estimated emotions. The system according to feature 1.

Images