system

Abstract

The system according to this embodiment aims to provide advice and suggestions for improving the progress of meetings and the quality of discussions. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, and a proposal unit. The collection unit collects the content of the meeting. The analysis unit analyzes the content of the meeting collected by the collection unit. The proposal unit provides advice and suggestions based on the content analyzed by the analysis unit.

Description

Technical Field

[0006] , , , ,

[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 performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that advice and proposals for improving the progress of a meeting and the quality of discussions do not immediately come to mind.

[0005] The system according to the embodiment aims to provide advice and proposals for improving the progress of a meeting and the quality of discussions.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a proposal unit. The collection unit collects the speech content of a meeting. The analysis unit analyzes the speech content collected by the collection unit. The proposal unit gives advice and proposals based on the content analyzed by the analysis unit.

Effects of the Invention

[0007] The system according to this embodiment can provide advice and suggestions to improve the progress of meetings and the quality of discussions. [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 that provides advice and suggestions to employees, especially junior employees, participating in difficult meetings led by their superiors, in order to improve the progress of the meeting and the quality of the discussion. This system integrates single-channel speaker automatic speech recognition, natural language processing AI, and a task management tool. This system improves the quality and effectiveness of meetings by having the generation AI perform the following two main functions. First, it analyzes the progress of the meeting and the content of the statements. The generation AI analyzes statements made during the meeting in real time and grasps important points and the flow of the discussion. For example, it automatically transcribes what is said during the meeting and extracts the main points of the discussion. This information is used as basic data to make the meeting progress smoothly. Next, it provides advice and suggestions. Based on the progress of the meeting and the content of the statements, the generation AI provides appropriate advice and suggestions. For example, if the discussion is stalled, it presents new perspectives and questions to revitalize the discussion. Also, if a particular topic requires further exploration, it provides relevant information and materials. As a result, the quality of the meeting improves and all participants can effectively express their opinions. Furthermore, this system enables more effective meeting management by collaborating with human moderators. Because the generative AI can process large amounts of information, it can provide advice from a broader perspective than humans. For example, by learning from past meeting data and relevant literature and creating meeting playbooks, it enables participants to quickly catch up on past meetings. This system is particularly useful for employees working from home or those who need to quickly adapt to new tasks. For instance, if an employee is working from home and doesn't have a senior colleague nearby to easily ask questions, or if they are suddenly assigned to facilitate a meeting, the generative AI can provide real-time support, ensuring smoother meeting progress and more equal participation. Thus, a meeting support system utilizing generative AI not only improves the quality and effectiveness of meetings but also serves as an important tool for creating a workplace environment where all employees can work comfortably and with peace of mind. In this way, the meeting support system can support employee participation in meetings and improve their quality and effectiveness.

[0029] The meeting support system according to this embodiment comprises a collection unit, an analysis unit, and a proposal unit. The collection unit collects the content of speeches during a meeting. The collection unit can, for example, collect speeches during a meeting in real time. The collection unit can collect speech content using speech recognition technology. The collection unit can also collect speech content using manual input or sensors. For example, the collection unit collects speeches during a meeting using a microphone and saves them as audio data. The collection unit can use speech recognition technology to convert the audio data into text data. The collection unit can collect speeches during a meeting in real time, enabling immediate analysis and proposals. The analysis unit analyzes the speech content collected by the collection unit. The analysis unit can, for example, automatically transcribe the collected speech content and extract the main points of the discussion. The analysis unit can analyze the speech content using natural language processing technology. The analysis unit can also analyze the speech content using sentiment analysis or keyword extraction. For example, the analysis unit automatically transcribes the collected speech content and extracts the main points of the discussion. The analysis unit transcribes the content of the discussion and extracts the key points, thereby facilitating the smooth progress of the meeting. The proposal unit provides advice and suggestions based on the content analyzed by the analysis unit. For example, the proposal unit can offer new perspectives or questions when the discussion is stalled. The proposal unit can provide relevant information and materials when a particular topic needs to be explored in more depth. The proposal unit can also learn from past meeting data and relevant literature to create a meeting playbook. For example, the proposal unit can offer new perspectives or questions when the discussion is stalled. The proposal unit can provide relevant information and materials when a particular topic needs to be explored in more depth. The proposal unit can learn from past meeting data and relevant literature to create a meeting playbook. As a result, the meeting support system according to this embodiment can improve the quality and effectiveness of meetings by collecting and analyzing the content of the discussion and providing advice and suggestions.

[0030] The data collection unit collects the content of meetings. For example, the unit can collect meeting speeches in real time. The unit can use speech recognition technology to collect speech content. It can also collect speech content using manual input or sensors. For example, the unit can collect meeting speeches using a microphone and save them as audio data. The unit can use speech recognition technology to convert the audio data into text data. The unit collects meeting speeches in real time, enabling immediate analysis and proposals. Specifically, the unit uses a high-sensitivity microphone to collect all speeches in the meeting room without omission. This ensures that all speeches are accurately recorded, regardless of the speaker's volume or location. Furthermore, the unit incorporates noise cancellation technology to remove background noise and other sounds, allowing for clear collection of speech content. The collected audio data is transmitted to the speech recognition engine in real time and immediately converted into text data. The speech recognition engine utilizes the latest deep learning technology, enabling highly accurate transcription of speech content. Furthermore, the data collection unit can identify speakers and clearly record who made each statement. This allows for accurate understanding of each speaker's opinions and the flow of their statements during subsequent analysis and proposals. The data collection unit can also collect nonverbal information during meetings using manual input or sensors. For example, it can capture participants' facial expressions and gestures with a camera and utilize this information for analysis. This allows for the collection of comprehensive data that includes not only the content of statements but also participants' emotions and reactions.

[0031] The analysis unit analyzes the content of speeches collected by the collection unit. For example, the analysis unit can automatically transcribe the collected speeches and extract the key points of the discussion. The analysis unit can analyze speeches using natural language processing techniques. Furthermore, the analysis unit can analyze speeches using sentiment analysis and keyword extraction. For example, the analysis unit automatically transcribes the collected speeches and extracts the key points of the discussion. By transcribing speeches and extracting key points, the analysis unit facilitates the smooth progress of meetings. Specifically, the analysis unit analyzes the collected text data using natural language processing (NLP) techniques to understand the intent and content of the speeches. NLP techniques include topic modeling, keyword extraction, and contextual analysis, which are combined to analyze speeches from multiple perspectives. For example, topic modeling is used to automatically identify the main agenda items and themes of the meeting, and keyword extraction is used to extract important terms and phrases. Furthermore, contextual analysis is used to understand the context and relationships of speeches and grasp the flow of the discussion. The analysis unit utilizes sentiment analysis technology to analyze the emotions and attitudes of speakers. This enables a comprehensive analysis that includes not only the content of what is said, but also the speaker's emotions and intentions. For example, it can identify points that speakers want to emphasize or concerns they want to address, which can be used to guide the discussion. Based on these analysis results, the analysis unit automatically extracts key points and important statements from the discussion, supporting the progress of the meeting. Furthermore, by referring to past meeting data and relevant literature and comparing them with the current discussion, the analysis unit can provide insights into the discussion's progress and offer new perspectives. In this way, the analysis unit can improve the quality of meetings and promote efficient discussion.

[0032] The proposal department provides advice and suggestions based on the analysis conducted by the analysis department. For example, the proposal department can offer new perspectives or questions when a discussion is stalled. The proposal department can provide relevant information and materials when a particular topic requires further exploration. The proposal department can also learn from past meeting data and relevant literature to create meeting playbooks. Specifically, the proposal department automatically searches for relevant information and materials based on the key points and keywords of the discussion provided by the analysis department and provides them to meeting participants. For example, it can deepen the discussion by presenting the latest research findings, industry trends, and discussion content from past meetings on a particular topic. The proposal department uses AI to monitor the progress of the discussion and the content of participants' statements in real time and provides advice and suggestions at the appropriate time. For example, if a discussion is stalled, it can offer new perspectives or questions to stimulate the discussion. Furthermore, if a specific topic requires further exploration, relevant information and materials will be provided to support the discussion. In addition, the proposal team will study past meeting data and relevant literature to create a meeting playbook. This playbook will include successful and unsuccessful examples from past meetings, as well as effective discussion strategies, which can be used to support the progress of meetings. Based on this information, the proposal team can improve the quality of meetings and promote efficient discussions. Moreover, the proposal team can collect participant feedback to continuously improve the accuracy and effectiveness of proposals. This allows the proposal team to always provide the latest information and optimal proposals, maximizing the effectiveness of meetings.

[0033] The data collection unit can collect speeches during a meeting in real time. For example, the data collection unit can collect speeches during a meeting using a microphone and save them as audio data. The data collection unit can use speech recognition technology to convert the audio data into text data. Furthermore, the data collection unit can collect speeches during a meeting in real time, enabling immediate analysis and suggestions. For example, the data collection unit collects speeches during a meeting using a microphone and saves them as audio data. The data collection unit can use speech recognition technology to convert the audio data into text data. The data collection unit can collect speeches during a meeting in real time, enabling immediate analysis and suggestions. This allows for immediate analysis and suggestions by collecting speeches during a meeting in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit collects speeches during a meeting using a microphone and saves them as audio data. The data collection unit can use generative AI to convert the audio data into text data.

[0034] The analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. The analysis unit can analyze the statements using natural language processing technology. The analysis unit can also analyze the statements using sentiment analysis and keyword extraction. For example, the analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. By transcribing the statements and extracting the main points of the discussion, the analysis unit can facilitate the smooth progress of the meeting. By transcribing the statements and extracting the main points of the discussion, the meeting can be made to proceed smoothly. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected statements into a generating AI and have the generating AI perform transcription and extraction of the main points of the discussion.

[0035] The proposal unit can introduce new perspectives or questions when the discussion is stalled. For example, the proposal unit can introduce new perspectives or questions when the discussion is stalled. The proposal unit can revitalize the discussion by introducing new perspectives or questions when the discussion is stalled. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input new perspectives or questions into a generating AI when the discussion is stalled and have the generating AI execute them.

[0036] The proposal department can provide relevant information and materials when it is necessary to delve deeper into a particular topic. For example, the proposal department can provide relevant information and materials when it is necessary to delve deeper into a particular topic. The proposal department can improve the quality of the discussion by providing relevant information and materials when it is necessary to delve deeper into a particular topic. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input relevant information and materials when it is necessary to delve deeper into a particular topic into a generating AI and have the generating AI execute it.

[0037] The proposal unit can learn from past meeting data and related literature and create a meeting playbook. For example, the proposal unit can learn from past meeting data and related literature and create a meeting playbook. By learning from past meeting data and related literature and creating a meeting playbook, the proposal unit enables participants to quickly catch up on past meetings. This allows participants to quickly catch up on past meetings by learning from past meeting data and related literature and creating a meeting playbook. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input past meeting data and related literature into a generating AI and have the generating AI create a meeting playbook.

[0038] The collection unit can prioritize collecting the statements of specific speakers according to the progress of the meeting. For example, if the meeting is behind schedule, the AI ​​will prioritize collecting the statements of speakers relevant to the agenda. If the meeting is progressing smoothly, the AI ​​can collect the statements of all participants equally. Furthermore, if the meeting is stalled, the AI ​​can prioritize collecting the statements of speakers who offer new perspectives. This allows the meeting to proceed smoothly by prioritizing the collection of statements from specific speakers according to the progress of the meeting. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the progress of the meeting into a generating AI and have the generating AI perform the process of prioritizing the collection of statements from specific speakers.

[0039] The collection unit can automatically classify and collect statements based on the meeting's theme and topics. For example, if there are multiple meeting themes, the AI ​​can classify and collect statements for each theme. If the meeting's topic changes, the AI ​​can prioritize collecting statements related to the new topic. Furthermore, if a new topic is added during the meeting, the AI ​​can automatically classify and collect statements related to that topic. This makes it easier to organize the discussion by classifying statements based on the meeting's theme and topics. Some or all of the above processing in the collection unit may be performed using AI, or not. For example, the collection unit can input the meeting's theme and topics into a generating AI, and have the generating AI perform the classification and collection of statements.

[0040] The data collection unit can adjust how it collects spoken content based on the meeting location and time. For example, if the meeting is held online, the AI ​​can prioritize collecting audio data. If the meeting is held offline, the AI ​​can prioritize collecting video data. Furthermore, if the meeting is held at night, the AI ​​can summarize and collect spoken content concisely. This allows for efficient data collection by adjusting the method of collecting spoken content based on the meeting location and time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the meeting location and time into a generating AI and have the generating AI adjust the method of collecting spoken content.

[0041] The data collection unit can filter and collect the content of a meeting based on the participants' positions and areas of expertise. For example, if a participant is a senior manager, the AI ​​will prioritize collecting their statements. If a participant specializes in a particular field, the AI ​​will prioritize collecting statements related to that field. Furthermore, if a participant is a newcomer, the AI ​​can filter and collect their statements and extract key points. This allows for the priority collection of important statements by filtering the content of the meeting based on the participants' positions and areas of expertise. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input the participants' positions and areas of expertise into a generating AI and have the generating AI perform the filtering of the content of the statements.

[0042] The analysis unit can improve the accuracy of its analysis by referring to the speaker's past speech history when analyzing the content of a speech. For example, the analysis unit can improve accuracy by having the AI ​​analyze the current speech content based on the speaker's past speech history. The analysis unit can refer to the speaker's past speech history, and the AI ​​can emphasize specific keywords or phrases during the analysis. The analysis unit can also analyze the speaker's past speech history, and the AI ​​can grasp speech patterns to improve the accuracy of the analysis. In this way, the accuracy of the analysis is improved by referring to the speaker's past speech history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the speaker's past speech history into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0043] The analysis unit can dynamically change its analysis algorithm according to the progress of the meeting when analyzing the content of the statements. For example, if the meeting is behind schedule, the AI ​​will change the analysis algorithm to prioritize the analysis of important points. If the meeting is progressing smoothly, the AI ​​can use the normal analysis algorithm to analyze the content of the statements. The analysis unit can also change the analysis algorithm if the meeting is stalled, so that the AI ​​can provide a new perspective. This allows for prioritizing the analysis of important points by changing the analysis algorithm according to the progress of the meeting. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the progress of the meeting into a generating AI and have the generating AI perform the dynamic changes to the analysis algorithm.

[0044] The analysis unit can adjust its analysis method based on the meeting's theme and topics when analyzing the content of the statements. For example, if the meeting's theme is technical, the AI ​​can prioritize the analysis of technical terms. If the meeting's topic is business strategy, the AI ​​can prioritize the analysis of strategic points. Furthermore, if the meeting's theme is human resources, the AI ​​can prioritize the analysis of statements related to human resources. By adjusting the analysis method based on the meeting's theme and topics, efficient analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the meeting's theme and topics into a generating AI and have the generating AI perform the adjustment of the analysis method.

[0045] The analysis unit can customize the analysis results based on the expertise and job titles of the meeting participants when analyzing the content of their speeches. For example, if a meeting participant is an engineer, the AI ​​can emphasize technical points in the analysis. If a meeting participant is a manager, the AI ​​can emphasize management-related points in the analysis. Furthermore, if a meeting participant is a newcomer, the AI ​​can emphasize basic points in the analysis. This allows for the emphasis of important points by customizing the analysis results based on the expertise and job titles of the meeting participants. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the expertise and job titles of the meeting participants into a generating AI and have the generating AI perform the customization of the analysis results.

[0046] The proposal department can select the most suitable proposal by referring to past meeting data when providing advice or suggestions. For example, the proposal department can use AI to select the most suitable proposal based on past meeting data. The proposal department can refer to past meeting data, and the AI ​​can provide suggestions based on similar discussions. The proposal department can also analyze past meeting data, and the AI ​​can select the most effective proposal. In this way, the best proposal can be selected by referring to past meeting data. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input past meeting data into a generating AI and have the generating AI perform the selection of the best proposal.

[0047] The proposal department can adjust the timing of its suggestions and advice according to the progress of the meeting. For example, if the meeting is behind schedule, the AI ​​can provide a quick suggestion. If the meeting is progressing smoothly, the AI ​​can provide suggestions at the normal time. The proposal department can also adjust the timing of suggestions if the meeting is stalled, allowing the AI ​​to offer a new perspective. By adjusting the timing of suggestions according to the progress of the meeting, effective suggestions become possible. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input the progress of the meeting into a generating AI and have the generating AI adjust the timing of suggestions.

[0048] The proposal department can customize its suggestions based on the meeting's theme and topics when providing advice and proposals. For example, if the meeting's theme is technical, the AI ​​can provide technical suggestions. If the meeting's topic is business strategy, the AI ​​can provide strategic suggestions. Furthermore, if the meeting's theme is human resources, the AI ​​can provide human resources-related suggestions. This allows for more effective suggestions by customizing them based on the meeting's theme and topics. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department can input the meeting's theme and topics into a generating AI and have the generating AI customize the suggestions.

[0049] The proposal department can adjust its suggestions based on the expertise and roles of the meeting participants when providing advice or suggestions. For example, if the meeting participants are engineers, the AI ​​can provide technical suggestions. If the meeting participants are managers, the AI ​​can provide management-related suggestions. Furthermore, if the meeting participants are new employees, the AI ​​can provide basic suggestions. This allows for the emphasis of key points by adjusting the suggestions based on the expertise and roles of the meeting participants. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department can input the expertise and roles of the meeting participants into a generating AI and have the generating AI adjust the suggestions.

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

[0051] The meeting support system can also include a feedback function. This function provides feedback to participants after the meeting. For example, it can analyze the content of discussions and the progress of the debate during the meeting, and point out areas for improvement and successes to participants. It can also evaluate the frequency and quality of participants' contributions and provide advice for future meetings. Furthermore, the feedback function can provide tools for participants to review their own contributions based on meeting recordings and transcripts. This allows participants to objectively evaluate their own contributions and the progress of the discussion, enabling them to improve for future meetings.

[0052] The meeting support system can also include a translation function. This function translates meeting content in real time, facilitating communication between participants who speak different languages. For example, it can translate statements made in English into Japanese and vice versa. Furthermore, it can include a dictionary function to appropriately translate specialized terminology and industry-specific vocabulary. Additionally, it can prioritize the translation of important statements and key points of discussion as the meeting progresses. This improves communication among participants who speak different languages, enhancing the quality and effectiveness of the meeting.

[0053] The meeting support system can also include a scheduling unit. This unit automatically adjusts meeting schedules and suggests times that are convenient for all participants. For example, it can collect participants' calendar information and suggest the optimal meeting time. It can also prioritize schedules based on their importance and urgency. Furthermore, it can automatically send meeting reminders to ensure participants don't forget. This ensures efficient meeting scheduling and smooth participation for all attendees.

[0054] The meeting support system can also include a remote participation section. This section shares the meeting progress and discussion content in real time for employees participating remotely. For example, the remote participation section can transcribe meeting discussions in real time and provide this to remote participants. It can also video stream the meeting, allowing remote participants to visually understand what is happening. Furthermore, the remote participation section can include a function to adjust the timing of participation to make it easier for remote participants to speak. This allows employees participating remotely to actively participate in meetings, improving the quality and effectiveness of the meetings.

[0055] The meeting support system can also include a document sharing section. This section allows for the real-time sharing of materials and documents used during the meeting, ensuring all participants have access to the same information. For example, the document sharing section can share presentation materials during the meeting, allowing participants to discuss while viewing the materials. It can also instantly share any newly added materials or documents during the meeting. Furthermore, the document sharing section can include a function to organize materials after the meeting and save them for later reference. This streamlines information sharing during meetings, improving the quality and effectiveness of discussions.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The collection unit collects the content of the meeting. The collection unit can, for example, collect the content of the meeting in real time. The collection unit can collect the content of the meeting using speech recognition technology. The collection unit can also collect the content of the meeting using manual input or sensors. For example, the collection unit can collect the content of the meeting using a microphone and save it as audio data. The collection unit can use speech recognition technology to convert the audio data into text data. The collection unit can collect the content of the meeting in real time, enabling immediate analysis and suggestions. Step 2: The analysis unit analyzes the content of the statements collected by the collection unit. The analysis unit can, for example, automatically transcribe the collected statements and extract the main points of the discussion. The analysis unit can analyze the content of the statements using natural language processing technology. The analysis unit can also analyze the content of the statements using sentiment analysis and keyword extraction. For example, the analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. By transcribing the statements and extracting the main points of the discussion, the analysis unit facilitates the smooth progress of the meeting. Step 3: The proposal team provides advice and suggestions based on the analysis conducted by the analysis team. For example, the proposal team can offer new perspectives or questions when a discussion is stalled. The proposal team can provide relevant information and materials when a particular topic requires further exploration. The proposal team can also learn from past meeting data and relevant literature to create a meeting playbook. For example, the proposal team can offer new perspectives or questions when a discussion is stalled. The proposal team can provide relevant information and materials when a particular topic requires further exploration. The proposal team can learn from past meeting data and relevant literature to create a meeting playbook.

[0058] (Example of form 2) The meeting support system according to an embodiment of the present invention is a system that provides advice and suggestions to employees, especially junior employees, participating in difficult meetings led by their superiors, in order to improve the progress of the meeting and the quality of the discussion. This system integrates single-channel speaker automatic speech recognition, natural language processing AI, and a task management tool. This system improves the quality and effectiveness of meetings by having the generation AI perform the following two main functions. First, it analyzes the progress of the meeting and the content of the statements. The generation AI analyzes statements made during the meeting in real time and grasps important points and the flow of the discussion. For example, it automatically transcribes what is said during the meeting and extracts the main points of the discussion. This information is used as basic data to make the meeting progress smoothly. Next, it provides advice and suggestions. Based on the progress of the meeting and the content of the statements, the generation AI provides appropriate advice and suggestions. For example, if the discussion is stalled, it presents new perspectives and questions to revitalize the discussion. Also, if a particular topic requires further exploration, it provides relevant information and materials. As a result, the quality of the meeting improves and all participants can effectively express their opinions. Furthermore, this system enables more effective meeting management by collaborating with human moderators. Because the generative AI can process large amounts of information, it can provide advice from a broader perspective than humans. For example, by learning from past meeting data and relevant literature and creating meeting playbooks, it enables participants to quickly catch up on past meetings. This system is particularly useful for employees working from home or those who need to quickly adapt to new tasks. For instance, if an employee is working from home and doesn't have a senior colleague nearby to easily ask questions, or if they are suddenly assigned to facilitate a meeting, the generative AI can provide real-time support, ensuring smoother meeting progress and more equal participation. Thus, a meeting support system utilizing generative AI not only improves the quality and effectiveness of meetings but also serves as an important tool for creating a workplace environment where all employees can work comfortably and with peace of mind. In this way, the meeting support system can support employee participation in meetings and improve their quality and effectiveness.

[0059] The meeting support system according to this embodiment comprises a collection unit, an analysis unit, and a proposal unit. The collection unit collects the content of speeches during a meeting. The collection unit can, for example, collect speeches during a meeting in real time. The collection unit can collect speech content using speech recognition technology. The collection unit can also collect speech content using manual input or sensors. For example, the collection unit collects speeches during a meeting using a microphone and saves them as audio data. The collection unit can use speech recognition technology to convert the audio data into text data. The collection unit can collect speeches during a meeting in real time, enabling immediate analysis and proposals. The analysis unit analyzes the speech content collected by the collection unit. The analysis unit can, for example, automatically transcribe the collected speech content and extract the main points of the discussion. The analysis unit can analyze the speech content using natural language processing technology. The analysis unit can also analyze the speech content using sentiment analysis or keyword extraction. For example, the analysis unit automatically transcribes the collected speech content and extracts the main points of the discussion. The analysis unit transcribes the content of the discussion and extracts the key points, thereby facilitating the smooth progress of the meeting. The proposal unit provides advice and suggestions based on the content analyzed by the analysis unit. For example, the proposal unit can offer new perspectives or questions when the discussion is stalled. The proposal unit can provide relevant information and materials when a particular topic needs to be explored in more depth. The proposal unit can also learn from past meeting data and relevant literature to create a meeting playbook. For example, the proposal unit can offer new perspectives or questions when the discussion is stalled. The proposal unit can provide relevant information and materials when a particular topic needs to be explored in more depth. The proposal unit can learn from past meeting data and relevant literature to create a meeting playbook. As a result, the meeting support system according to this embodiment can improve the quality and effectiveness of meetings by collecting and analyzing the content of the discussion and providing advice and suggestions.

[0060] The data collection unit collects the content of meetings. For example, the unit can collect meeting speeches in real time. The unit can use speech recognition technology to collect speech content. It can also collect speech content using manual input or sensors. For example, the unit can collect meeting speeches using a microphone and save them as audio data. The unit can use speech recognition technology to convert the audio data into text data. The unit collects meeting speeches in real time, enabling immediate analysis and proposals. Specifically, the unit uses a high-sensitivity microphone to collect all speeches in the meeting room without omission. This ensures that all speeches are accurately recorded, regardless of the speaker's volume or location. Furthermore, the unit incorporates noise cancellation technology to remove background noise and other sounds, allowing for clear collection of speech content. The collected audio data is transmitted to the speech recognition engine in real time and immediately converted into text data. The speech recognition engine utilizes the latest deep learning technology, enabling highly accurate transcription of speech content. Furthermore, the data collection unit can identify speakers and clearly record who made each statement. This allows for accurate understanding of each speaker's opinions and the flow of their statements during subsequent analysis and proposals. The data collection unit can also collect nonverbal information during meetings using manual input or sensors. For example, it can capture participants' facial expressions and gestures with a camera and utilize this information for analysis. This allows for the collection of comprehensive data that includes not only the content of statements but also participants' emotions and reactions.

[0061] The analysis unit analyzes the content of speeches collected by the collection unit. For example, the analysis unit can automatically transcribe the collected speeches and extract the key points of the discussion. The analysis unit can analyze speeches using natural language processing techniques. Furthermore, the analysis unit can analyze speeches using sentiment analysis and keyword extraction. For example, the analysis unit automatically transcribes the collected speeches and extracts the key points of the discussion. By transcribing speeches and extracting key points, the analysis unit facilitates the smooth progress of meetings. Specifically, the analysis unit analyzes the collected text data using natural language processing (NLP) techniques to understand the intent and content of the speeches. NLP techniques include topic modeling, keyword extraction, and contextual analysis, which are combined to analyze speeches from multiple perspectives. For example, topic modeling is used to automatically identify the main agenda items and themes of the meeting, and keyword extraction is used to extract important terms and phrases. Furthermore, contextual analysis is used to understand the context and relationships of speeches and grasp the flow of the discussion. The analysis unit utilizes sentiment analysis technology to analyze the emotions and attitudes of speakers. This enables a comprehensive analysis that includes not only the content of what is said, but also the speaker's emotions and intentions. For example, it can identify points that speakers want to emphasize or concerns they want to address, which can be used to guide the discussion. Based on these analysis results, the analysis unit automatically extracts key points and important statements from the discussion, supporting the progress of the meeting. Furthermore, by referring to past meeting data and relevant literature and comparing them with the current discussion, the analysis unit can provide insights into the discussion's progress and offer new perspectives. In this way, the analysis unit can improve the quality of meetings and promote efficient discussion.

[0062] The proposal department provides advice and suggestions based on the analysis conducted by the analysis department. For example, the proposal department can offer new perspectives or questions when a discussion is stalled. The proposal department can provide relevant information and materials when a particular topic requires further exploration. The proposal department can also learn from past meeting data and relevant literature to create meeting playbooks. Specifically, the proposal department automatically searches for relevant information and materials based on the key points and keywords of the discussion provided by the analysis department and provides them to meeting participants. For example, it can deepen the discussion by presenting the latest research findings, industry trends, and discussion content from past meetings on a particular topic. The proposal department uses AI to monitor the progress of the discussion and the content of participants' statements in real time and provides advice and suggestions at the appropriate time. For example, if a discussion is stalled, it can offer new perspectives or questions to stimulate the discussion. Furthermore, if a specific topic requires further exploration, relevant information and materials will be provided to support the discussion. In addition, the proposal team will study past meeting data and relevant literature to create a meeting playbook. This playbook will include successful and unsuccessful examples from past meetings, as well as effective discussion strategies, which can be used to support the progress of meetings. Based on this information, the proposal team can improve the quality of meetings and promote efficient discussions. Moreover, the proposal team can collect participant feedback to continuously improve the accuracy and effectiveness of proposals. This allows the proposal team to always provide the latest information and optimal proposals, maximizing the effectiveness of meetings.

[0063] The data collection unit can collect speeches during a meeting in real time. For example, the data collection unit can collect speeches during a meeting using a microphone and save them as audio data. The data collection unit can use speech recognition technology to convert the audio data into text data. Furthermore, the data collection unit can collect speeches during a meeting in real time, enabling immediate analysis and suggestions. For example, the data collection unit collects speeches during a meeting using a microphone and saves them as audio data. The data collection unit can use speech recognition technology to convert the audio data into text data. The data collection unit can collect speeches during a meeting in real time, enabling immediate analysis and suggestions. This allows for immediate analysis and suggestions by collecting speeches during a meeting in real time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit collects speeches during a meeting using a microphone and saves them as audio data. The data collection unit can use generative AI to convert the audio data into text data.

[0064] The analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. The analysis unit can analyze the statements using natural language processing technology. The analysis unit can also analyze the statements using sentiment analysis and keyword extraction. For example, the analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. By transcribing the statements and extracting the main points of the discussion, the analysis unit can facilitate the smooth progress of the meeting. By transcribing the statements and extracting the main points of the discussion, the meeting can be made to proceed smoothly. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the collected statements into a generating AI and have the generating AI perform transcription and extraction of the main points of the discussion.

[0065] The proposal unit can introduce new perspectives or questions when the discussion is stalled. For example, the proposal unit can introduce new perspectives or questions when the discussion is stalled. The proposal unit can revitalize the discussion by introducing new perspectives or questions when the discussion is stalled. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input new perspectives or questions into a generating AI when the discussion is stalled and have the generating AI execute them.

[0066] The proposal department can provide relevant information and materials when it is necessary to delve deeper into a particular topic. For example, the proposal department can provide relevant information and materials when it is necessary to delve deeper into a particular topic. The proposal department can improve the quality of the discussion by providing relevant information and materials when it is necessary to delve deeper into a particular topic. Some or all of the above processing in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can input relevant information and materials when it is necessary to delve deeper into a particular topic into a generating AI and have the generating AI execute it.

[0067] The proposal unit can learn from past meeting data and related literature and create a meeting playbook. For example, the proposal unit can learn from past meeting data and related literature and create a meeting playbook. By learning from past meeting data and related literature and creating a meeting playbook, the proposal unit enables participants to quickly catch up on past meetings. This allows participants to quickly catch up on past meetings by learning from past meeting data and related literature and creating a meeting playbook. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can input past meeting data and related literature into a generating AI and have the generating AI create a meeting playbook.

[0068] The data collection unit can estimate the emotions of meeting participants and adjust the timing of collecting their statements based on the estimated emotions. For example, if a meeting participant is tense, the AI ​​can widen the intervals between their statements to allow them time to relax. If a meeting participant is excited, the AI ​​can narrow the intervals between their statements to maintain the momentum of the discussion. The data collection unit can also adjust the intervals between participants' statements and suggest breaks if they are tired. By adjusting the timing of collecting statements based on the participants' emotions, participants can speak in a relaxed manner. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input the emotional data of meeting participants into a generative AI and have the generative AI adjust the timing of collecting statements.

[0069] The collection unit can prioritize collecting the statements of specific speakers according to the progress of the meeting. For example, if the meeting is behind schedule, the AI ​​will prioritize collecting the statements of speakers relevant to the agenda. If the meeting is progressing smoothly, the AI ​​can collect the statements of all participants equally. Furthermore, if the meeting is stalled, the AI ​​can prioritize collecting the statements of speakers who offer new perspectives. This allows the meeting to proceed smoothly by prioritizing the collection of statements from specific speakers according to the progress of the meeting. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the progress of the meeting into a generating AI and have the generating AI perform the process of prioritizing the collection of statements from specific speakers.

[0070] The collection unit can automatically classify and collect statements based on the meeting's theme and topics. For example, if there are multiple meeting themes, the AI ​​can classify and collect statements for each theme. If the meeting's topic changes, the AI ​​can prioritize collecting statements related to the new topic. Furthermore, if a new topic is added during the meeting, the AI ​​can automatically classify and collect statements related to that topic. This makes it easier to organize the discussion by classifying statements based on the meeting's theme and topics. Some or all of the above processing in the collection unit may be performed using AI, or not. For example, the collection unit can input the meeting's theme and topics into a generating AI, and have the generating AI perform the classification and collection of statements.

[0071] The data collection unit can estimate the emotions of meeting participants and determine the priority of the statements to be collected based on the estimated emotions. For example, if a meeting participant is feeling anxious, the AI ​​in the data collection unit can prioritize collecting that participant's statements to provide reassurance. If a meeting participant is confident, the AI ​​in the data collection unit can postpone that participant's statements and prioritize the statements of other participants. Furthermore, if a meeting participant is excited, the AI ​​in the data collection unit can prioritize collecting that participant's statements to stimulate discussion. In this way, by determining the priority of statements based on the emotions of meeting participants, participants can speak with confidence. 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 data collection unit may be performed using AI, or not using AI. For example, the data collection unit can input the emotion data of meeting participants into a generative AI and have the generative AI perform the determination of the priority of statements.

[0072] The data collection unit can adjust how it collects spoken content based on the meeting location and time. For example, if the meeting is held online, the AI ​​can prioritize collecting audio data. If the meeting is held offline, the AI ​​can prioritize collecting video data. Furthermore, if the meeting is held at night, the AI ​​can summarize and collect spoken content concisely. This allows for efficient data collection by adjusting the method of collecting spoken content based on the meeting location and time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the meeting location and time into a generating AI and have the generating AI adjust the method of collecting spoken content.

[0073] The data collection unit can filter and collect the content of a meeting based on the participants' positions and areas of expertise. For example, if a participant is a senior manager, the AI ​​will prioritize collecting their statements. If a participant specializes in a particular field, the AI ​​will prioritize collecting statements related to that field. Furthermore, if a participant is a newcomer, the AI ​​can filter and collect their statements and extract key points. This allows for the priority collection of important statements by filtering the content of the meeting based on the participants' positions and areas of expertise. Some or all of the above processing in the data collection unit may be performed using AI, or not. For example, the data collection unit can input the participants' positions and areas of expertise into a generating AI and have the generating AI perform the filtering of the content of the statements.

[0074] The analysis unit can estimate the emotions of meeting participants and adjust the transcription accuracy based on the estimated emotions. For example, if a meeting participant is nervous, the AI ​​in the analysis unit can improve the transcription accuracy to accurately record what is said. If a meeting participant is relaxed, the AI ​​in the analysis unit can maintain normal transcription accuracy to record natural conversation. Furthermore, if a meeting participant is excited, the AI ​​in the analysis unit can adjust the transcription accuracy to highlight important points. This ensures that what is said is accurately recorded by adjusting the transcription accuracy based on the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input the emotion data of meeting participants into a generative AI and have the generative AI adjust the transcription accuracy.

[0075] The analysis unit can improve the accuracy of its analysis by referring to the speaker's past speech history when analyzing the content of a speech. For example, the analysis unit can improve accuracy by having the AI ​​analyze the current speech content based on the speaker's past speech history. The analysis unit can refer to the speaker's past speech history, and the AI ​​can emphasize specific keywords or phrases during the analysis. The analysis unit can also analyze the speaker's past speech history, and the AI ​​can grasp speech patterns to improve the accuracy of the analysis. In this way, the accuracy of the analysis is improved by referring to the speaker's past speech history. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the speaker's past speech history into a generating AI and have the generating AI perform the improvement of the analysis accuracy.

[0076] The analysis unit can dynamically change its analysis algorithm according to the progress of the meeting when analyzing the content of the statements. For example, if the meeting is behind schedule, the AI ​​will change the analysis algorithm to prioritize the analysis of important points. If the meeting is progressing smoothly, the AI ​​can use the normal analysis algorithm to analyze the content of the statements. The analysis unit can also change the analysis algorithm if the meeting is stalled, so that the AI ​​can provide a new perspective. This allows for prioritizing the analysis of important points by changing the analysis algorithm according to the progress of the meeting. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the progress of the meeting into a generating AI and have the generating AI perform the dynamic changes to the analysis algorithm.

[0077] The analysis unit can estimate the emotions of meeting participants and determine the priority of extracting key points from the discussion based on the estimated emotions. For example, if a meeting participant is feeling anxious, the AI ​​in the analysis unit can prioritize extracting the key points of their statements to provide reassurance. If a meeting participant is confident, the AI ​​in the analysis unit can postpone extracting the key points of their statements and prioritize the statements of other participants. Furthermore, if a meeting participant is excited, the AI ​​in the analysis unit can prioritize extracting the key points of their statements to stimulate the discussion. In this way, by determining the priority of extracting key points from the discussion based on the emotions of the meeting participants, participants can speak with confidence. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input emotional data of meeting participants into a generating AI, which can then perform the task of determining the priority of key points for extracting discussion points.

[0078] The analysis unit can adjust its analysis method based on the meeting's theme and topics when analyzing the content of the statements. For example, if the meeting's theme is technical, the AI ​​can prioritize the analysis of technical terms. If the meeting's topic is business strategy, the AI ​​can prioritize the analysis of strategic points. Furthermore, if the meeting's theme is human resources, the AI ​​can prioritize the analysis of statements related to human resources. By adjusting the analysis method based on the meeting's theme and topics, efficient analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the meeting's theme and topics into a generating AI and have the generating AI perform the adjustment of the analysis method.

[0079] The analysis unit can customize the analysis results based on the expertise and job titles of the meeting participants when analyzing the content of their speeches. For example, if a meeting participant is an engineer, the AI ​​can emphasize technical points in the analysis. If a meeting participant is a manager, the AI ​​can emphasize management-related points in the analysis. Furthermore, if a meeting participant is a newcomer, the AI ​​can emphasize basic points in the analysis. This allows for the emphasis of important points by customizing the analysis results based on the expertise and job titles of the meeting participants. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the expertise and job titles of the meeting participants into a generating AI and have the generating AI perform the customization of the analysis results.

[0080] The suggestion unit can estimate the emotions of meeting participants and adjust the content of advice and suggestions based on the estimated emotions. For example, if a meeting participant is tense, the suggestion unit can use AI to provide advice to help them relax. If a meeting participant is relaxed, the suggestion unit can use AI to provide positive suggestions. Furthermore, if a meeting participant is excited, the suggestion unit can use AI to provide advice to help them calm down. This allows participants to speak more freely and relaxed by adjusting the content of advice and suggestions based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the emotional data of meeting participants into a generative AI and have the generative AI adjust the content of advice and suggestions.

[0081] The proposal department can select the most suitable proposal by referring to past meeting data when providing advice or suggestions. For example, the proposal department can use AI to select the most suitable proposal based on past meeting data. The proposal department can refer to past meeting data, and the AI ​​can provide suggestions based on similar discussions. The proposal department can also analyze past meeting data, and the AI ​​can select the most effective proposal. In this way, the best proposal can be selected by referring to past meeting data. Some or all of the above processes in the proposal department may be performed using AI, for example, or without AI. For example, the proposal department can input past meeting data into a generating AI and have the generating AI perform the selection of the best proposal.

[0082] The proposal department can adjust the timing of its suggestions and advice according to the progress of the meeting. For example, if the meeting is behind schedule, the AI ​​can provide a quick suggestion. If the meeting is progressing smoothly, the AI ​​can provide suggestions at the normal time. The proposal department can also adjust the timing of suggestions if the meeting is stalled, allowing the AI ​​to offer a new perspective. By adjusting the timing of suggestions according to the progress of the meeting, effective suggestions become possible. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can input the progress of the meeting into a generating AI and have the generating AI adjust the timing of suggestions.

[0083] The suggestion unit can estimate the emotions of meeting participants and prioritize advice and suggestions based on those estimated emotions. For example, if a meeting participant is feeling anxious, the suggestion unit's AI can prioritize providing advice to that participant. If a meeting participant is confident, the suggestion unit can postpone providing advice to that participant. Furthermore, if a meeting participant is excited, the suggestion unit's AI can prioritize providing advice to that participant. This allows participants to speak with confidence by prioritizing advice and suggestions based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input meeting participant emotion data into a generative AI and have the generative AI determine the priority of advice and suggestions.

[0084] The proposal department can customize its suggestions based on the meeting's theme and topics when providing advice and proposals. For example, if the meeting's theme is technical, the AI ​​can provide technical suggestions. If the meeting's topic is business strategy, the AI ​​can provide strategic suggestions. Furthermore, if the meeting's theme is human resources, the AI ​​can provide human resources-related suggestions. This allows for more effective suggestions by customizing them based on the meeting's theme and topics. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department can input the meeting's theme and topics into a generating AI and have the generating AI customize the suggestions.

[0085] The proposal department can adjust its suggestions based on the expertise and roles of the meeting participants when providing advice or suggestions. For example, if the meeting participants are engineers, the AI ​​can provide technical suggestions. If the meeting participants are managers, the AI ​​can provide management-related suggestions. Furthermore, if the meeting participants are new employees, the AI ​​can provide basic suggestions. This allows for the emphasis of key points by adjusting the suggestions based on the expertise and roles of the meeting participants. Some or all of the above processes in the proposal department may be performed using AI, or not. For example, the proposal department can input the expertise and roles of the meeting participants into a generating AI and have the generating AI adjust the suggestions.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The meeting support system can also include a feedback function. This function provides feedback to participants after the meeting. For example, it can analyze the content of discussions and the progress of the debate during the meeting, and point out areas for improvement and successes to participants. It can also evaluate the frequency and quality of participants' contributions and provide advice for future meetings. Furthermore, the feedback function can provide tools for participants to review their own contributions based on meeting recordings and transcripts. This allows participants to objectively evaluate their own contributions and the progress of the discussion, enabling them to improve for future meetings.

[0088] The meeting support system can also include a translation function. This function translates meeting content in real time, facilitating communication between participants who speak different languages. For example, it can translate statements made in English into Japanese and vice versa. Furthermore, it can include a dictionary function to appropriately translate specialized terminology and industry-specific vocabulary. Additionally, it can prioritize the translation of important statements and key points of discussion as the meeting progresses. This improves communication among participants who speak different languages, enhancing the quality and effectiveness of the meeting.

[0089] The meeting support system can also include a scheduling unit. This unit automatically adjusts meeting schedules and suggests times that are convenient for all participants. For example, it can collect participants' calendar information and suggest the optimal meeting time. It can also prioritize schedules based on their importance and urgency. Furthermore, it can automatically send meeting reminders to ensure participants don't forget. This ensures efficient meeting scheduling and smooth participation for all attendees.

[0090] The meeting support system can also include a remote participation section. This section shares the meeting progress and discussion content in real time for employees participating remotely. For example, the remote participation section can transcribe meeting discussions in real time and provide this to remote participants. It can also video stream the meeting, allowing remote participants to visually understand what is happening. Furthermore, the remote participation section can include a function to adjust the timing of participation to make it easier for remote participants to speak. This allows employees participating remotely to actively participate in meetings, improving the quality and effectiveness of the meetings.

[0091] The meeting support system can also include a document sharing section. This section allows for the real-time sharing of materials and documents used during the meeting, ensuring all participants have access to the same information. For example, the document sharing section can share presentation materials during the meeting, allowing participants to discuss while viewing the materials. It can also instantly share any newly added materials or documents during the meeting. Furthermore, the document sharing section can include a function to organize materials after the meeting and save them for later reference. This streamlines information sharing during meetings, improving the quality and effectiveness of discussions.

[0092] The meeting support system can also be equipped with an emotional feedback unit. This unit provides real-time feedback on participants' emotions during the meeting and adjusts the meeting's progress accordingly. For example, if a participant is feeling tense, the emotional feedback unit can provide relaxing music or visuals. It can also offer advice to calm participants if they are feeling agitated. Furthermore, after the meeting, the emotional feedback unit can analyze participants' emotional data and suggest improvements for the next meeting. This allows the meeting to be conducted based on participants' emotions, creating an environment where everyone can relax and speak freely.

[0093] The meeting support system can also be equipped with an emotion monitoring unit. This unit monitors the emotions of participants in a meeting in real time and provides appropriate feedback according to the meeting's progress. For example, if a participant is feeling anxious, the emotion monitoring unit can offer reassuring advice. It can also offer positive suggestions if a participant is relaxed. Furthermore, if a participant is agitated, the emotion monitoring unit can offer advice to help them calm down. This allows the meeting to be managed based on participants' emotions, creating an environment where all participants can speak freely and comfortably.

[0094] The meeting support system can also be equipped with an emotion analysis unit. This unit analyzes participants' emotions based on their statements, facial expressions, and tone of voice during the meeting, and uses this information to improve the meeting's progress. For example, if a participant is tense, the emotion analysis unit can identify the cause and provide advice to help them relax. If a participant is excited, the unit can suggest ways to leverage that excitement to stimulate the discussion. Furthermore, after the meeting, the emotion analysis unit can analyze participants' emotional data and suggest improvements for the next meeting. This allows the meeting to be conducted based on participants' emotions, creating an environment where everyone can speak freely and comfortably.

[0095] The meeting support system can also be equipped with an emotion prediction unit. This unit predicts participants' emotions based on past meeting data and their speaking history, and uses this information to facilitate the meeting. For example, it can predict when participants are likely to become tense based on past data and provide advice to help them relax at those times. It can also predict topics that participants are likely to become excited about and offer suggestions to stimulate discussion on those topics. Furthermore, it can analyze participants' emotional data after the meeting and suggest improvements for the next meeting. This allows the meeting to be conducted based on participants' emotions, creating an environment where all participants can speak comfortably and relaxed.

[0096] The meeting support system can also be equipped with an emotion regulation unit. This unit adjusts participants' emotions in real time during a meeting, ensuring smooth proceedings. For example, if a participant is feeling tense, the unit can provide relaxing music or visuals. It can also offer advice to calm participants who are agitated. Furthermore, after the meeting, the unit can analyze participants' emotional data and suggest improvements for future meetings. This allows the meeting to be conducted based on participants' emotions, creating an environment where everyone can relax and speak freely.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The collection unit collects the content of the meeting. The collection unit can, for example, collect the content of the meeting in real time. The collection unit can collect the content of the meeting using speech recognition technology. The collection unit can also collect the content of the meeting using manual input or sensors. For example, the collection unit can collect the content of the meeting using a microphone and save it as audio data. The collection unit can use speech recognition technology to convert the audio data into text data. The collection unit can collect the content of the meeting in real time, enabling immediate analysis and suggestions. Step 2: The analysis unit analyzes the content of the statements collected by the collection unit. The analysis unit can, for example, automatically transcribe the collected statements and extract the main points of the discussion. The analysis unit can analyze the content of the statements using natural language processing technology. The analysis unit can also analyze the content of the statements using sentiment analysis and keyword extraction. For example, the analysis unit can automatically transcribe the collected statements and extract the main points of the discussion. By transcribing the statements and extracting the main points of the discussion, the analysis unit facilitates the smooth progress of the meeting. Step 3: The proposal team provides advice and suggestions based on the analysis conducted by the analysis team. For example, the proposal team can offer new perspectives or questions when a discussion is stalled. The proposal team can provide relevant information and materials when a particular topic requires further exploration. The proposal team can also learn from past meeting data and relevant literature to create a meeting playbook. For example, the proposal team can offer new perspectives or questions when a discussion is stalled. The proposal team can provide relevant information and materials when a particular topic requires further exploration. The proposal team can learn from past meeting data and relevant literature to create a meeting playbook.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] Each of the multiple elements described above, including the collection unit, analysis unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects speech during a meeting using the microphone 38B of the smart device 14 and converts the speech data into text data using the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech content using natural language processing technology and extracts the main points of the discussion. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12, which generates appropriate advice and suggestions based on the analysis results and provides them through the display 40A and speaker 40B of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the collection unit, analysis unit, and proposal unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit uses the microphone 238 of the smart glasses 214 to collect speech during a meeting and the control unit 46A converts the speech data into text data. The analysis unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech content using natural language processing technology and extracts the main points of the discussion. The proposal unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which generates appropriate advice and suggestions based on the analysis results and provides them through the speaker 240 of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is 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.

[0134] Each of the multiple elements described above, including the collection unit, analysis unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects speech during a meeting using the microphone 238 of the headset terminal 314 and converts the speech data into text data using the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech content using natural language processing technology and extracts the main points of the discussion. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12, which generates appropriate advice and suggestions based on the analysis results and provides them through the speaker 240 of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] Each of the multiple elements described above, including the collection unit, analysis unit, and proposal unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the collection unit uses the microphone 238 of the robot 414 to collect speech during a meeting and the control unit 46A converts the speech data into text data. The analysis unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which analyzes the collected speech content using natural language processing technology and extracts the main points of the discussion. The proposal unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which generates appropriate advice and suggestions based on the analysis results and provides them through the speaker 240 of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] (Note 1) The collection department is responsible for gathering the content of the meeting discussions, An analysis unit analyzes the content of speeches collected by the aforementioned collection unit, A proposal unit provides advice and suggestions based on the analysis performed by the aforementioned analysis unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect comments made during meetings in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The collected speeches are automatically transcribed, and the main points of the discussion are extracted. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, When discussions have stalled, introduce new perspectives or questions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned proposal section is, Provide relevant information and materials when you need to delve deeper into a specific topic. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned proposal section is, Learn from past meeting data and relevant literature to create a meeting playbook. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the emotions of meeting participants and adjusts the timing of collecting their comments based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Depending on the progress of the meeting, prioritize collecting the statements of specific speakers. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is The system automatically categorizes and collects the content of the discussions based on the meeting's theme and topics. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates the emotions of meeting participants and prioritizes the content of their statements to be collected based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is Adjust the method of collecting comments based on the location and time of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is The content of the discussions is filtered and collected based on the roles and areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, The system estimates the emotions of meeting participants and adjusts the accuracy of the transcription based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing the content of a statement, the accuracy of the analysis is improved by referring to the speaker's past statement history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, When analyzing the content of the speeches, the analysis algorithm is dynamically changed according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, The system estimates the emotions of meeting participants and prioritizes the extraction of key points from the discussion based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, When analyzing the content of the speeches, the analysis method is adjusted based on the meeting's theme and topics. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, When analyzing the content of the discussion, the analysis results are customized based on the expertise and job titles of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, The system estimates the emotions of meeting participants and adjusts the content of advice and suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, When providing advice or suggestions, we refer to past meeting data to select the most suitable proposal. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When offering advice or suggestions, adjust the timing of the suggestions according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, The system estimates the emotions of meeting participants and prioritizes advice and suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, When offering advice or suggestions, customize the content of the suggestions based on the meeting's theme or topic. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, When offering advice or suggestions, tailor the content of the suggestions based on the expertise and positions of the meeting participants. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0171] 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. The collection department is responsible for gathering the content of the meeting discussions, An analysis unit analyzes the content of speeches collected by the aforementioned collection unit, A proposal unit provides advice and suggestions based on the analysis performed by the aforementioned analysis unit, Equipped with A system characterized by the following features.

2. The aforementioned collection unit is Collect comments made during meetings in real time. The system according to feature 1.

3. The aforementioned analysis unit, The collected speeches are automatically transcribed, and the main points of the discussion are extracted. The system according to feature 1.

4. The aforementioned proposal section is, When discussions have stalled, introduce new perspectives or questions. The system according to feature 1.

5. The aforementioned proposal section is, Provide relevant information and materials when you need to delve deeper into a specific topic. The system according to feature 1.

6. The aforementioned proposal section is, Learn from past meeting data and relevant literature to create a meeting playbook. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the emotions of meeting participants and adjusts the timing of collecting their comments based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Depending on the progress of the meeting, prioritize collecting the statements of specific speakers. The system according to feature 1.

Images