System

Abstract

To provide a system for improving the quality of a meeting by automating progress and summarizing of a meeting.SOLUTION: A system includes a collection section, a progress section, and a summarization section. The collection section collects a participant's information. The progress section manages progress of a meeting on the basis of the collected information. The summarization section analyzes contents of the meeting managed by the progress section in real time and extracts important points.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, the progress and summary of a meeting depended on the ability of the facilitator, which led to issues with inconsistent quality of the meeting.

[0005] The system according to the embodiment aims to improve the quality of the conference by automating the progress and summary of the conference. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a proceeding unit, and a summarization unit. The collection unit collects participant information. The proceeding unit manages the progress of the conference based on the collected information. The summarization unit analyzes the contents of the conference managed by the proceeding unit in real time and extracts important points. Effect of the Invention

[0007] The system according to the embodiment can automate the progress and summary of a meeting, thereby improving the quality of the meeting. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

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

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

[0028] (Example 1) The conference support system according to the embodiment of the present invention is a system that improves the quality of a conference by entrusting the role of a facilitator to an AI. This conference support system collects participant information, manages the progress of the conference, and analyzes the contents of the conference in real time to create a summary. For example, the participant information of the conference and the purpose of the conference are input to the AI. The participant information includes names, positions, fields of expertise, etc. The purpose of the conference includes the agenda and goals. Next, the AI ​​is in charge of the progress of the conference. The AI ​​determines which participant to ask which remark based on the participant information and the purpose of the conference. For example, by asking participants with specialized knowledge about a specific topic to speak, the efficiency of the conference is improved. In addition, the AI ​​manages the order of remarks and time allocation to ensure that the conference proceeds smoothly. Furthermore, the AI ​​is in charge of summarizing the conference and creating the minutes. The remarks are analyzed in real time during the conference and the important points are summarized. After the conference ends, minutes are created based on the summary and provided to the participants. This makes it easy to accurately record the contents of the conference and refer to them later. This system improves the quality of the conference and enables efficient progress by entrusting the role of the facilitator to the AI. In addition, by automating the creation of summaries and minutes, participants can more easily grasp the content of the meeting. This allows the meeting support system to improve the quality of meetings and ensure efficient progress by entrusting the role of facilitator to AI.

[0029] The conference support system according to the embodiment includes a collection unit, a proceeding unit, and a summarizing unit. The collection unit collects participant information. The participant information includes, for example, names, job titles, fields of expertise, and past speech histories, but is not limited to such examples. The collection unit collects participant information using, for example, a questionnaire. The collection unit can also collect biometric information of participants using a sensor. Furthermore, the collection unit can grasp the interests and concerns of participants using social media analysis. For example, the collection unit collects names and job titles of participants through a questionnaire. The heart rate and body temperature of participants are measured using a sensor to grasp the degree of tension. Topics in which participants are interested are identified from contents posted in the past by the participants using social media analysis. The proceeding unit manages the progress of the conference based on the information collected by the collection unit. For example, the proceeding unit determines the order of speech and adjusts time allocation, but is not limited to such examples. The proceeding unit determines the order of speech based on the job titles and expertise of participants, for example. The proceeding unit can also change the proceeding method in real time according to the progress of the conference. For example, the proceeding unit determines the order of speech based on the roles of the participants, and requests participants with specialized knowledge to speak preferentially for important topics. If the meeting is behind schedule, the proceeding method is changed to a quick proceeding method. The summarizing unit analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. The summarizing unit analyzes the contents of the statements using, for example, natural language processing technology, but is not limited to such an example. The summarizing unit extracts important points based on, for example, frequent keywords of the statements and the importance of the statements. The summarizing unit can also apply different summarizing algorithms depending on the category of the statements. For example, the summarizing unit analyzes the contents of the statements using natural language processing technology and extracts frequent keywords. The level of detail of the summary is adjusted based on the importance of the statements, and a detailed summary is provided for important statements. Depending on the category of the statements, a detailed summarizing algorithm is applied to technical statements, and a concise summarizing algorithm is applied to statements for exchanging opinions. As a result, the meeting support system according to the embodiment can improve the quality of the meeting and achieve efficient progress by entrusting the role of the facilitator to AI.

[0030] The collection unit collects participant information. The participant information includes, for example, names, job titles, fields of expertise, and past speech histories, but is not limited to such examples. The collection unit collects participant information, for example, using a questionnaire. The collection unit can also collect biometric information of participants using sensors. Furthermore, the collection unit can grasp the interests and concerns of participants using social media analysis. For example, the collection unit collects the names and job titles of participants through a questionnaire. The sensor is used to measure the heart rate and body temperature of participants to grasp the level of tension. Social media analysis is used to identify topics in which participants are interested from content posted in the past. Specifically, the questionnaire is conducted through an online form or a prior email survey, and collects basic information of participants, expectations for the meeting, and matters of interest. The sensor monitors participants' biometric information in real time using a wearable device or an environmental sensor installed in the meeting room. This makes it possible to grasp the level of tension and concentration of participants and use this information to help progress the meeting. Social media analysis analyzes participants' public profiles and past postings to identify topics and areas of interest. This can be useful for setting meeting agendas and determining the order of speaking. Furthermore, the collection department can centrally manage this information and link it with other systems and departments as necessary. For example, the collected data can be stored on a cloud server and made accessible to the progress department and summary department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses can be made according to specific situations and conditions. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0031] The progress unit manages the progress of the meeting based on the information collected by the collection unit. For example, the progress unit determines the order of speaking and adjusts the time allocation, but is not limited to such examples. For example, the progress unit determines the order of speaking based on the titles and expertise of the participants. The progress unit can also change the progress method in real time according to the progress of the meeting. For example, the progress unit determines the order of speaking based on the titles of the participants, and asks participants with specialized knowledge to speak preferentially for important topics. If the meeting is running behind schedule, the progress method is changed to a quicker progress method. Specifically, the progress unit uses AI to analyze the titles and expertise of the participants and past speech history, and automatically determines the optimal speech order. This allows the meeting to proceed smoothly, and the opinions of participants with specialized knowledge can be heard at the appropriate time for important topics. The progress unit also monitors the progress of the meeting in real time and flexibly changes the progress method as necessary. For example, if the meeting is running behind schedule, the time to speak can be shortened or the priority of the topics can be changed to achieve efficient progress. Furthermore, the facilitator can use participants' biometric information to grasp their levels of concentration and tension and take appropriate measures such as taking breaks at appropriate times. This allows the facilitator to reduce the burden on participants and improve the quality of the meeting. Through these functions, the facilitator can efficiently and effectively manage the progress of the meeting and provide an environment in which all participants can actively participate.

[0032] The summarization unit analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. The summarization unit analyzes the contents of the remarks using, for example, natural language processing technology, but is not limited to such an example. The summarization unit extracts important points based on, for example, frequently occurring keywords in the remarks and the importance of the remarks. The summarization unit can also apply different summarization algorithms depending on the category of the remarks. For example, the summarization unit analyzes the contents of the remarks using natural language processing technology and extracts frequently occurring keywords. The level of detail of the summary is adjusted based on the importance of the remarks, and a detailed summary is provided for important remarks. Depending on the category of the remarks, a detailed summarization algorithm is applied for technical remarks, and a concise summarization algorithm is applied for remarks of exchange of opinions. Specifically, the summarization unit converts the audio data of the meeting into text using AI, and analyzes the text data using natural language processing technology. This makes it possible to understand the meaning of the remarks and extract important points. Furthermore, the summarization unit adjusts the level of detail of the summary based on frequently occurring keywords in the remarks and the importance of the remarks. For example, a detailed summary is provided for important topics, and a concise summary is provided for remarks of exchange of opinions. The summarization unit can also apply different summarization algorithms depending on the category of comments. For example, a detailed summarization algorithm is applied to technical comments, and a concise summarization algorithm is applied to comments that exchange opinions. This allows the summarization unit to efficiently summarize the contents of the meeting and quickly provide important information to participants. Furthermore, the summarization unit can update the summary results in real time and provide the latest information as the meeting progresses. This allows the summarization unit to efficiently summarize the contents of the meeting and quickly provide important information to participants.

[0033] The conference support system includes an order management unit that manages the order of speech. The order management unit manages the order of speech. The order management unit determines the order of speech based on, for example, the titles and expertise of the participants, but is not limited to such examples. The order management unit determines the order of speech based on, for example, the titles of the participants, and prioritizes participants with specialized knowledge to speak on important topics. The order management unit can also change the order of speech in real time according to the progress of the conference. For example, the order management unit determines the order of speech based on the titles of the participants, and prioritizes participants with specialized knowledge to speak on important topics. If the conference is running behind schedule, the method is changed to a quick progress method. In this way, the conference progresses smoothly by managing the order of speech. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can determine the order of speech using an AI model that inputs the titles and expertise of the participants and outputs the order of speech.

[0034] The conference support system includes a time management unit that manages the time allocation of remarks. The time management unit manages the time allocation of remarks. The time management unit determines the time allocation based on, for example, the importance of remarks and the titles of participants, but is not limited to such examples. The time management unit determines the time allocation based on, for example, the importance of remarks, and allocates a longer time to important remarks. The time management unit can also change the time allocation in real time according to the progress of the conference. For example, the time management unit determines the time allocation based on the importance of remarks, and allocates a longer time to important remarks. If the conference is behind schedule, the progress method is changed to a quick progress method. In this way, the efficiency of the conference is improved by managing the time allocation of remarks. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can determine the time allocation using an AI model that inputs the importance of remarks and the titles of participants and outputs the time allocation.

[0035] The conference support system includes an analysis unit that analyzes the contents of a speech. The analysis unit analyzes the contents of a speech. The analysis unit analyzes the contents of a speech. The analysis unit analyzes the contents of a speech using, for example, natural language processing technology, but is not limited to such an example. The analysis unit extracts important points based on, for example, frequently occurring keywords in the speech and the importance of the speech. The analysis unit can also apply different analysis algorithms depending on the category of the speech. For example, the analysis unit analyzes the contents of a speech using natural language processing technology and extracts frequently occurring keywords. The level of detail of the analysis is adjusted based on the importance of the speech, and a detailed analysis is performed on important speech. Depending on the category of the speech, a detailed analysis algorithm is applied to technical speech, and a simple analysis algorithm is applied to speech for exchanging opinions. In this way, the contents of the speech can be analyzed to accurately grasp the contents of the conference. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the contents of a speech using a generation AI model that inputs the contents of a speech and outputs important points.

[0036] The meeting support system includes a minutes-taking section that takes minutes based on a summary. The minutes-taking section takes minutes based on the summary. The minutes-taking section takes minutes based on, for example, the level of detail of the summary and the type of information to be recorded, but is not limited to such an example. The minutes-taking section adjusts the length of the minutes based on, for example, the level of detail of the summary, and takes detailed minutes for important remarks. The minutes-taking section can also apply different minutes-taking algorithms depending on the category of remarks. For example, the minutes-taking section adjusts the length of the minutes based on the level of detail of the summary, and takes detailed minutes for important remarks. Depending on the category of remarks, a detailed minutes-taking algorithm is applied to technical remarks, and a concise minutes-taking algorithm is applied to remarks for exchanging opinions. This allows the contents of the meeting to be accurately recorded by automatically taking minutes. Some or all of the above-mentioned processing in the minutes-taking section may be performed using, for example, AI, or may be performed without using AI. For example, the minutes-taking unit can take minutes using an AI model that takes a summary as input and outputs minutes.

[0037] The conference support system includes a speech promotion unit that encourages participants to speak. The speech promotion unit encourages participants to speak. For example, the speech promotion unit asks questions and adjusts the order of speech, but is not limited to such examples. The speech promotion unit determines the order in which speech is encouraged based on the participants' positions and expertise. The speech promotion unit can also change the method of encouraging speech in real time according to the progress of the conference. For example, the speech promotion unit determines the order in which speech is encouraged based on the participants' positions, and prioritizes participants with expertise in important topics. If the conference is running behind schedule, the method is changed to a quick progress method. This encourages speech and promotes lively discussion in the conference. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech promotion unit can determine the method of encouraging speech using an AI model that inputs the participants' positions and expertise and outputs the order in which speech is encouraged.

[0038] The collection unit can analyze the past speech history of the participants and select the optimal information collection method. For example, the collection unit preferentially collects information related to topics that the participants have frequently spoken about in the past. For example, the collection unit can also analyze the past speech patterns of the participants and select an effective information collection method. For example, the collection unit can also collect information related to topics that the participants have shown interest in in the past. This makes it possible to effectively collect information by analyzing the past speech history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can select the information collection method using an AI model that inputs the past speech history of the participants and outputs the optimal information collection method.

[0039] The collection unit can filter information based on the specialty and title of the participant at the time of collection. The collection unit, for example, preferentially collects information related to the specialty of the participant. The collection unit can also filter necessary information according to the role of the participant. The collection unit can also collect highly relevant information based on the expertise of the participant. This makes it possible to collect highly relevant information by filtering information based on the specialty and title. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can filter information using an AI model that uses the specialty and title of the participant as input and filters information.

[0040] The collection unit can collect highly relevant information preferentially based on the geographical location information of the participant at the time of collection. For example, when the participant is in a specific area, the collection unit preferentially collects information related to the area. The collection unit can also filter highly relevant information based on the geographical location information of the participant. For example, when the participant is moving, the collection unit can also collect necessary information based on the current location. In this way, highly relevant information can be collected preferentially by collecting information based on the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the geographical location information of the participant and outputs highly relevant information.

[0041] The collection unit can analyze the social media activities of the participants at the time of collection and collect related information. The collection unit can, for example, analyze the content of the participants' comments on social media and collect related information. The collection unit can also collect necessary information based on information shared by the participants on social media, for example. The collection unit can also collect information related to topics of interest from the participants' social media activities, for example. In this way, information based on the participants' interests can be collected by analyzing the social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the participants' social media activities and outputs related information.

[0042] During the proceedings, the proceeding unit can determine the order in which participants are asked to speak based on the expertise of the participants. For example, the proceeding unit preferentially asks participants who have expertise on a particular topic to speak. For example, the proceeding unit can also determine an effective order of speaking based on the expertise of the participants. For example, the proceeding unit can adjust the order of speaking based on the role or field of expertise of the participants. This enables effective discussion by determining the order of speaking based on expertise. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can determine the order of speaking using an AI model that inputs the expertise of participants and outputs the order of speaking.

[0043] The progress unit can apply different progress algorithms depending on the purpose of the meeting during the progress. For example, when the purpose of the meeting is decision-making, the progress unit applies a rapid progress algorithm. For example, when the purpose of the meeting is brainstorming, the progress unit can also apply a progress algorithm that encourages free speech. For example, when the purpose of the meeting is information sharing, the progress unit can also apply a progress algorithm that includes a detailed explanation. This makes it possible to progress according to the purpose by applying a progress algorithm according to the purpose of the meeting. Some or all of the above-mentioned processing in the progress unit may be performed using, for example, AI, or may be performed without using AI. For example, the progress unit can apply the progress algorithm using an AI model that inputs the purpose of the meeting and outputs a progress algorithm.

[0044] The facilitator can adjust the order of requests for speech based on the content of past speeches of the participants during the discussion. The facilitator determines an effective speech order based on, for example, the content of past speeches of the participants. The facilitator can also adjust the optimal speech order by, for example, analyzing the past speech patterns of the participants. The facilitator can also preferentially request speech related to topics in which the participants have shown interest in the past. This allows for effective discussion by adjusting the speech order based on the content of past speeches. A part or all of the above-mentioned processing in the facilitator may be performed using, for example, AI, or may be performed without using AI. For example, the facilitator can adjust the speech order using an AI model that inputs the content of past speeches of the participants and outputs the speech order.

[0045] The proceeding unit can change the proceeding method in real time according to the progress of the conference during the conference. For example, if the conference is running behind schedule, the proceeding unit changes to a quick proceeding method. For example, if the conference is running ahead of schedule, the proceeding unit can also change to a proceeding method that encourages detailed discussion. For example, the proceeding unit can adjust an appropriate proceeding method in real time according to the progress of the conference. This allows flexible conference progress by changing the proceeding method according to the progress. A part or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can change the proceeding method using an AI model that inputs the progress of the conference and outputs the proceeding method.

[0046] The summarization unit can adjust the level of detail of the summary based on the importance of the statement when summarizing. The summarization unit can provide a detailed summary for an important statement, for example. The summarization unit can also provide a concise summary for a statement with low importance, for example. The summarization unit can also adjust the level of detail of the summary according to the importance of the statement, for example. As a result, important information is appropriately summarized by adjusting the level of detail of the summary based on the importance of the statement. A part or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI, or can be performed without using AI. For example, the summarization unit can adjust the level of detail of the summary using an AI model that inputs the importance of the statement and outputs the level of detail of the summary.

[0047] The summarization unit can apply different summarization algorithms depending on the category of the utterance when summarizing. For example, the summarization unit applies a detailed summarization algorithm to technical utterances. For example, the summarization unit can also apply a concise summarization algorithm to utterances of an exchange of opinions. The summarization unit can also select an appropriate summarization algorithm depending on the category of the utterance. In this way, an appropriate summary is provided by applying a summarization algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can apply a summarization algorithm using an AI model that inputs the category of the utterance and outputs a summarization algorithm.

[0048] The summarization unit can determine the priority of summarization based on the timing of utterances when summarizing. The summarization unit, for example, prioritizes summarization of content uttered at the beginning of a meeting. The summarization unit can also prioritize summarization of content uttered at the end of a meeting. The summarization unit can also adjust the priority of summarization based on the timing of utterances. As a result, important information is appropriately summarized by determining the priority of summarization based on the timing of utterances. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can determine the priority of summarization using an AI model that inputs the timing of utterances and outputs the priority of summarization.

[0049] The summarization unit can adjust the order of summaries based on the relevance of the utterances when summarizing. The summarization unit, for example, prioritizes summarization of highly relevant utterances. The summarization unit can also summarize less relevant utterances later, for example. The summarization unit can also adjust the order of summaries based on the relevance of the utterances. As a result, important information is appropriately summarized by adjusting the order of summaries based on the relevance of the utterances. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can adjust the order of summaries using an AI model that inputs the relevance of the utterances and outputs the order of summaries.

[0050] The order management unit can determine the order based on the expertise of the participants when managing the speaking order. For example, the order management unit preferentially requests participants who have expertise on a specific topic to speak. The order management unit can also determine an effective speaking order based on the expertise of the participants. The order management unit can also adjust the order in which participants are asked to speak, for example, according to their positions and fields of expertise. This enables effective discussion by determining the speaking order based on expertise. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can determine the speaking order using an AI model that inputs the expertise of participants and outputs the speaking order.

[0051] The order management unit can adjust the order based on the past remarks of the participants when managing the remark order. The order management unit determines an effective remark order based on, for example, the contents of the remarks made by the participants in the past. The order management unit can also adjust the optimal remark order by analyzing, for example, the past remark patterns of the participants. The order management unit can also preferentially request remarks related to topics in which the participants have shown interest in the past. This enables effective discussion by adjusting the remark order based on the past remarks. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can adjust the remark order using an AI model that inputs the past remarks of the participants and outputs the remark order.

[0052] The time management unit can optimize time allocation according to the progress of the meeting during time management. For example, if the meeting is running behind schedule, the time management unit changes to a quick progress method. For example, if the meeting is running ahead of schedule, the time management unit can also change to a progress method that encourages detailed discussion. For example, the time management unit can adjust an appropriate progress method in real time according to the progress of the meeting. This allows flexible progress of the meeting by optimizing time allocation according to the progress. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can optimize time allocation using an AI model that inputs the progress of the meeting and outputs time allocation.

[0053] The time management unit can adjust the time allocation based on the past speech times of the participants during time management. For example, if the participant has spoken for a long time in the past, the time management unit shortens the next speech time. For example, if the participant has spoken for a short time in the past, the time management unit can also extend the next speech time. For example, the time management unit can analyze the past speech times of the participants and adjust the optimal time allocation. As a result, by adjusting the time allocation based on the past speech times, it is possible to effectively proceed with the conference. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can adjust the time allocation using an AI model that inputs the past speech times of the participants and outputs the time allocation.

[0054] The analysis unit can adjust the level of detail of the analysis based on the importance of the statement during analysis. The analysis unit, for example, performs a detailed analysis of an important statement. The analysis unit can also perform a concise analysis of a statement with low importance. The analysis unit can also adjust the level of detail of the analysis according to the importance of the statement. As a result, important information is appropriately analyzed by adjusting the level of detail of the analysis based on the importance of the statement. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that inputs the importance of the statement and outputs the level of detail of the analysis.

[0055] The analysis unit can apply different analysis algorithms depending on the category of the statement during analysis. For example, the analysis unit applies a detailed analysis algorithm to technical statements. For example, the analysis unit can also apply a simple analysis algorithm to statements of exchange of opinions. For example, the analysis unit can select an appropriate analysis algorithm depending on the category of the statement. This enables appropriate analysis by applying an analysis algorithm according to the category of the statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can apply the analysis algorithm using an AI model that inputs the category of the statement and outputs the analysis algorithm.

[0056] The analysis unit can determine the priority of the analysis based on the timing of the speech during the analysis. The analysis unit, for example, preferentially analyzes the content spoken at the beginning of the meeting. The analysis unit can also preferentially analyze the content spoken at the end of the meeting. The analysis unit can also adjust the priority of the analysis based on the timing of the speech. As a result, important information is appropriately analyzed by determining the priority of the analysis based on the timing of the speech. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority of the analysis using an AI model that inputs the timing of the speech and outputs the priority of the analysis.

[0057] The analysis unit can adjust the order of analysis based on the relevance of the statements during analysis. The analysis unit, for example, prioritizes analysis of highly relevant statements. The analysis unit can also analyze less relevant statements later, for example. The analysis unit can also adjust the order of analysis based on the relevance of the statements. As a result, important information is appropriately analyzed by adjusting the order of analysis based on the relevance of the statements. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the order of analysis using an AI model that inputs the relevance of the statements and outputs the order of analysis.

[0058] The minutes-taking section can adjust the level of detail of the minutes based on the importance of the remarks when taking the minutes. The minutes-taking section can take detailed minutes for important remarks, for example. The minutes-taking section can also take concise minutes for remarks with low importance, for example. The minutes-taking section can also adjust the level of detail of the minutes according to the importance of the remarks, for example. By adjusting the level of detail of the minutes based on the importance of the remarks, important information is appropriately recorded. Some or all of the above-mentioned processing in the minutes-taking section can be performed using, for example, AI, or can be performed without using AI. For example, the minutes-taking section can adjust the level of detail of the minutes using an AI model that inputs the importance of the remarks and outputs the level of detail of the minutes.

[0059] The minutes-taking section can determine the priority of the minutes based on the timing of remarks when taking minutes. The minutes-taking section, for example, preferentially records in the minutes the contents of remarks made at the beginning of the meeting. The minutes-taking section can also preferentially record in the minutes the contents of remarks made at the end of the meeting. The minutes-taking section can also adjust the priority of the minutes based on the timing of remarks. As a result, important information is appropriately recorded by determining the priority of the minutes based on the timing of remarks. A part or all of the above-mentioned processing in the minutes-taking section may be performed using, for example, AI, or may be performed without using AI. For example, the minutes-taking section can determine the priority of the minutes using an AI model that inputs the timing of remarks and outputs the priority of the minutes.

[0060] The speech promotion unit can determine the order in which speech is encouraged based on the expertise of the participants when encouraging speech. For example, the speech promotion unit preferentially asks participants who have expertise on a particular topic to speak. The speech promotion unit can also determine an effective speech order based on the expertise of the participants. The speech promotion unit can also adjust the order in which speech is asked based on the role or field of expertise of the participants. This enables effective discussion by determining the speech order based on expertise. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech promotion unit can determine the speech order using an AI model that inputs the expertise of the participants and outputs the speech order.

[0061] The speech promotion unit can adjust the order in which speech is promoted based on the content of past speeches of the participants when promoting speech. The speech promotion unit determines an effective speech order based on, for example, the content of past speeches made by the participants. The speech promotion unit can also adjust the optimal speech order by analyzing, for example, the past speech patterns of the participants. The speech promotion unit can also preferentially request speeches related to topics in which the participants have shown interest in the past. This enables effective discussion by adjusting the speech order based on the content of past speeches. A part or all of the above-mentioned processing in the speech promotion unit may be performed, for example, using AI, or may be performed without using AI. For example, the speech promotion unit can adjust the speech order using an AI model that inputs the content of past speeches of the participants and outputs the speech order.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The conference support system may include a translation unit that translates the content of participants' remarks in real time. The translation unit automatically translates the content of remarks, for example, to facilitate communication between participants who speak different languages. For example, content spoken in English is translated into Japanese, and content spoken in Japanese is translated back into English. The translation unit may also include a dictionary function for appropriately translating technical terms and industry-specific words. This facilitates communication between participants who speak different languages, improving the quality of the conference.

[0064] The conference support system may include a display unit that visually displays the content of speech made by participants. The display unit, for example, displays the content of speech as text in real time. This makes it easier for hearing-impaired participants to understand the content of the conference. The display unit may also summarize and display the content of speech. For example, by displaying a short summary of a long speech, participants may be able to easily grasp the important points. Furthermore, the display unit may visually display the content of speech as a graph or chart. This makes it easier to intuitively understand data and statistical information.

[0065] The conference support system may be equipped with a recording unit that can record what participants say and play it back later. The recording unit can, for example, record the entire conference and play back the necessary parts later. This allows people who were unable to attend the conference or who want to review the contents of the conference to understand the contents of the conference through the recording. The recording unit can also separate recordings for each speaker. For example, it can play back only the statements of a specific speaker. Furthermore, the recording unit can also be equipped with a function to convert the recorded contents into text. This allows the recorded contents to be saved as text, making it easier to search and edit.

[0066] The conference support system may include a material providing unit that analyzes the content of participants' remarks and automatically provides related materials. The material providing unit, for example, automatically searches for literature and data related to the content of the remarks and provides them to the participants. This allows participants to quickly obtain necessary information during the conference, and the discussion progresses smoothly. The material providing unit may also provide minutes and summaries of related past conferences based on the content of the remarks. For example, if the same topic was discussed in a past conference, the discussion progresses more efficiently by referring to the minutes. Furthermore, the material providing unit may also provide related external resources (for example, websites and databases) based on the content of the remarks.

[0067] The meeting support system can include an agenda suggestion unit that automatically suggests the next agenda item based on the content of participants' remarks. For example, the agenda suggestion unit automatically suggests the next agenda item to be discussed when the current agenda item is finished. This allows the meeting to proceed smoothly and reduces time waste. The agenda suggestion unit can also suggest related agenda items based on the content of participants' remarks and interests. For example, if there are many participants who show interest in a particular topic, it will suggest agenda items related to that topic. Furthermore, the agenda suggestion unit can analyze minutes and summaries of past meetings to suggest unresolved agenda items. This allows effective discussions to be held without important topics being overlooked.

[0068] The process flow of the first embodiment will be briefly described below.

[0069] Step 1: The collection unit collects participant information. Participant information includes names, job titles, areas of expertise, past speech history, etc. The collection unit collects participant information using a questionnaire. In addition, biometric information of participants can be collected using sensors. Furthermore, participants' interests and concerns can be understood using social media analysis. For example, participants' names and job titles can be collected through a questionnaire, and participants' heart rates and body temperatures can be measured using sensors to understand their level of tension. Social media analysis is used to identify topics that participants are interested in from content they have posted in the past. Step 2: The Facilitator manages the progress of the meeting based on the information collected by the Collector. The Facilitator decides the speaking order and adjusts time allocation. For example, the Facilitator decides the speaking order based on the participants' job titles and expertise, and for important topics, gives priority to participants with specialized knowledge. If the meeting is behind schedule, the Facilitator changes to a faster progress method. Step 3: The summarization unit analyzes the contents of the meeting managed by the facilitator in real time and extracts important points. The summarization unit uses natural language processing technology to analyze the content of the comments and extracts important points based on frequently occurring keywords and the importance of the comments. It can also apply different summarization algorithms depending on the category of the comments. For example, a detailed summarization algorithm is applied to technical comments, and a concise summarization algorithm is applied to comments that involve the exchange of opinions.

[0070] (Example 2) The conference support system according to the embodiment of the present invention is a system that improves the quality of a conference by entrusting the role of a facilitator to an AI. This conference support system collects participant information, manages the progress of the conference, and analyzes the contents of the conference in real time to create a summary. For example, the participant information of the conference and the purpose of the conference are input to the AI. The participant information includes names, positions, fields of expertise, etc. The purpose of the conference includes the agenda and goals. Next, the AI ​​is in charge of the progress of the conference. The AI ​​determines which participant to ask which remark based on the participant information and the purpose of the conference. For example, by asking participants with specialized knowledge about a specific topic to speak, the efficiency of the conference is improved. In addition, the AI ​​manages the order of remarks and time allocation to ensure that the conference proceeds smoothly. Furthermore, the AI ​​is in charge of summarizing the conference and creating the minutes. The remarks are analyzed in real time during the conference and the important points are summarized. After the conference ends, minutes are created based on the summary and provided to the participants. This makes it easy to accurately record the contents of the conference and refer to them later. This system improves the quality of the conference and enables efficient progress by entrusting the role of the facilitator to the AI. In addition, by automating the creation of summaries and minutes, participants can more easily grasp the content of the meeting. This allows the meeting support system to improve the quality of meetings and ensure efficient progress by entrusting the role of facilitator to AI.

[0071] The conference support system according to the embodiment includes a collection unit, a proceeding unit, and a summarizing unit. The collection unit collects participant information. The participant information includes, for example, names, job titles, fields of expertise, and past speech histories, but is not limited to such examples. The collection unit collects participant information using, for example, a questionnaire. The collection unit can also collect biometric information of participants using a sensor. Furthermore, the collection unit can grasp the interests and concerns of participants using social media analysis. For example, the collection unit collects names and job titles of participants through a questionnaire. The heart rate and body temperature of participants are measured using a sensor to grasp the degree of tension. Topics in which participants are interested are identified from contents posted in the past by the participants using social media analysis. The proceeding unit manages the progress of the conference based on the information collected by the collection unit. For example, the proceeding unit determines the order of speech and adjusts time allocation, but is not limited to such examples. The proceeding unit determines the order of speech based on the job titles and expertise of participants, for example. The proceeding unit can also change the proceeding method in real time according to the progress of the conference. For example, the proceeding unit determines the order of speech based on the roles of the participants, and requests participants with specialized knowledge to speak preferentially for important topics. If the meeting is behind schedule, the proceeding method is changed to a quick proceeding method. The summarizing unit analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. The summarizing unit analyzes the contents of the statements using, for example, natural language processing technology, but is not limited to such an example. The summarizing unit extracts important points based on, for example, frequent keywords of the statements and the importance of the statements. The summarizing unit can also apply different summarizing algorithms depending on the category of the statements. For example, the summarizing unit analyzes the contents of the statements using natural language processing technology and extracts frequent keywords. The level of detail of the summary is adjusted based on the importance of the statements, and a detailed summary is provided for important statements. Depending on the category of the statements, a detailed summarizing algorithm is applied to technical statements, and a concise summarizing algorithm is applied to statements for exchanging opinions. As a result, the meeting support system according to the embodiment can improve the quality of the meeting and achieve efficient progress by entrusting the role of the facilitator to AI.

[0072] The collection unit collects participant information. The participant information includes, for example, names, job titles, fields of expertise, and past speech histories, but is not limited to such examples. The collection unit collects participant information, for example, using a questionnaire. The collection unit can also collect biometric information of participants using sensors. Furthermore, the collection unit can grasp the interests and concerns of participants using social media analysis. For example, the collection unit collects the names and job titles of participants through a questionnaire. The sensor is used to measure the heart rate and body temperature of participants to grasp the level of tension. Social media analysis is used to identify topics in which participants are interested from content posted in the past. Specifically, the questionnaire is conducted through an online form or a prior email survey, and collects basic information of participants, expectations for the meeting, and matters of interest. The sensor monitors participants' biometric information in real time using a wearable device or an environmental sensor installed in the meeting room. This makes it possible to grasp the level of tension and concentration of participants and use this information to help progress the meeting. Social media analysis analyzes participants' public profiles and past postings to identify topics and areas of interest. This can be useful for setting meeting agendas and determining the order of speaking. Furthermore, the collection department can centrally manage this information and link it with other systems and departments as necessary. For example, the collected data can be stored on a cloud server and made accessible to the progress department and summary department. In addition, by adjusting the frequency and accuracy of data collection, flexible responses can be made according to specific situations and conditions. This allows the collection department to collect data efficiently and effectively and improve the performance of the entire system.

[0073] The progress unit manages the progress of the meeting based on the information collected by the collection unit. For example, the progress unit determines the order of speaking and adjusts the time allocation, but is not limited to such examples. For example, the progress unit determines the order of speaking based on the titles and expertise of the participants. The progress unit can also change the progress method in real time according to the progress of the meeting. For example, the progress unit determines the order of speaking based on the titles of the participants, and asks participants with specialized knowledge to speak preferentially for important topics. If the meeting is running behind schedule, the progress method is changed to a quicker progress method. Specifically, the progress unit uses AI to analyze the titles and expertise of the participants and past speech history, and automatically determines the optimal speech order. This allows the meeting to proceed smoothly, and the opinions of participants with specialized knowledge can be heard at the appropriate time for important topics. The progress unit also monitors the progress of the meeting in real time and flexibly changes the progress method as necessary. For example, if the meeting is running behind schedule, the time to speak can be shortened or the priority of the topics can be changed to achieve efficient progress. Furthermore, the facilitator can use participants' biometric information to grasp their levels of concentration and tension and take appropriate measures such as taking breaks at appropriate times. This allows the facilitator to reduce the burden on participants and improve the quality of the meeting. Through these functions, the facilitator can efficiently and effectively manage the progress of the meeting and provide an environment in which all participants can actively participate.

[0074] The summarization unit analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. The summarization unit analyzes the contents of the remarks using, for example, natural language processing technology, but is not limited to such an example. The summarization unit extracts important points based on, for example, frequently occurring keywords in the remarks and the importance of the remarks. The summarization unit can also apply different summarization algorithms depending on the category of the remarks. For example, the summarization unit analyzes the contents of the remarks using natural language processing technology and extracts frequently occurring keywords. The level of detail of the summary is adjusted based on the importance of the remarks, and a detailed summary is provided for important remarks. Depending on the category of the remarks, a detailed summarization algorithm is applied for technical remarks, and a concise summarization algorithm is applied for remarks of exchange of opinions. Specifically, the summarization unit converts the audio data of the meeting into text using AI, and analyzes the text data using natural language processing technology. This makes it possible to understand the meaning of the remarks and extract important points. Furthermore, the summarization unit adjusts the level of detail of the summary based on frequently occurring keywords in the remarks and the importance of the remarks. For example, a detailed summary is provided for important topics, and a concise summary is provided for remarks of exchange of opinions. The summarization unit can also apply different summarization algorithms depending on the category of comments. For example, a detailed summarization algorithm is applied to technical comments, and a concise summarization algorithm is applied to comments that exchange opinions. This allows the summarization unit to efficiently summarize the contents of the meeting and quickly provide important information to participants. Furthermore, the summarization unit can update the summary results in real time and provide the latest information as the meeting progresses. This allows the summarization unit to efficiently summarize the contents of the meeting and quickly provide important information to participants.

[0075] The conference support system includes an order management unit that manages the order of speech. The order management unit manages the order of speech. The order management unit determines the order of speech based on, for example, the titles and expertise of the participants, but is not limited to such examples. The order management unit determines the order of speech based on, for example, the titles of the participants, and prioritizes participants with specialized knowledge to speak on important topics. The order management unit can also change the order of speech in real time according to the progress of the conference. For example, the order management unit determines the order of speech based on the titles of the participants, and prioritizes participants with specialized knowledge to speak on important topics. If the conference is running behind schedule, the method is changed to a quick progress method. In this way, the conference progresses smoothly by managing the order of speech. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can determine the order of speech using an AI model that inputs the titles and expertise of the participants and outputs the order of speech.

[0076] The conference support system includes a time management unit that manages the time allocation of remarks. The time management unit manages the time allocation of remarks. The time management unit determines the time allocation based on, for example, the importance of remarks and the titles of participants, but is not limited to such examples. The time management unit determines the time allocation based on, for example, the importance of remarks, and allocates a longer time to important remarks. The time management unit can also change the time allocation in real time according to the progress of the conference. For example, the time management unit determines the time allocation based on the importance of remarks, and allocates a longer time to important remarks. If the conference is behind schedule, the progress method is changed to a quick progress method. In this way, the efficiency of the conference is improved by managing the time allocation of remarks. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can determine the time allocation using an AI model that inputs the importance of remarks and the titles of participants and outputs the time allocation.

[0077] The conference support system includes an analysis unit that analyzes the contents of a speech. The analysis unit analyzes the contents of a speech. The analysis unit analyzes the contents of a speech. The analysis unit analyzes the contents of a speech using, for example, natural language processing technology, but is not limited to such an example. The analysis unit extracts important points based on, for example, frequently occurring keywords in the speech and the importance of the speech. The analysis unit can also apply different analysis algorithms depending on the category of the speech. For example, the analysis unit analyzes the contents of a speech using natural language processing technology and extracts frequently occurring keywords. The level of detail of the analysis is adjusted based on the importance of the speech, and a detailed analysis is performed on important speech. Depending on the category of the speech, a detailed analysis algorithm is applied to technical speech, and a simple analysis algorithm is applied to speech for exchanging opinions. In this way, the contents of the speech can be analyzed to accurately grasp the contents of the conference. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the contents of a speech using a generation AI model that inputs the contents of a speech and outputs important points.

[0078] The meeting support system includes a minutes-taking section that takes minutes based on a summary. The minutes-taking section takes minutes based on the summary. The minutes-taking section takes minutes based on, for example, the level of detail of the summary and the type of information to be recorded, but is not limited to such an example. The minutes-taking section adjusts the length of the minutes based on, for example, the level of detail of the summary, and takes detailed minutes for important remarks. The minutes-taking section can also apply different minutes-taking algorithms depending on the category of remarks. For example, the minutes-taking section adjusts the length of the minutes based on the level of detail of the summary, and takes detailed minutes for important remarks. Depending on the category of remarks, a detailed minutes-taking algorithm is applied to technical remarks, and a concise minutes-taking algorithm is applied to remarks for exchanging opinions. This allows the contents of the meeting to be accurately recorded by automatically taking minutes. Some or all of the above-mentioned processing in the minutes-taking section may be performed using, for example, AI, or may be performed without using AI. For example, the minutes-taking unit can take minutes using an AI model that takes a summary as input and outputs minutes.

[0079] The conference support system includes a speech promotion unit that encourages participants to speak. The speech promotion unit encourages participants to speak. For example, the speech promotion unit asks questions and adjusts the order of speech, but is not limited to such examples. The speech promotion unit determines the order in which speech is encouraged based on the participants' positions and expertise. The speech promotion unit can also change the method of encouraging speech in real time according to the progress of the conference. For example, the speech promotion unit determines the order in which speech is encouraged based on the participants' positions, and prioritizes participants with expertise in important topics. If the conference is running behind schedule, the method is changed to a quick progress method. This encourages speech and promotes lively discussion in the conference. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech promotion unit can determine the method of encouraging speech using an AI model that inputs the participants' positions and expertise and outputs the order in which speech is encouraged.

[0080] The collection unit can estimate the emotion of the participant and determine the priority of the information to be collected based on the emotion. For example, when the participant is nervous, the collection unit preferentially collects information for relaxing the participant. For example, when the participant is excited, the collection unit can also preferentially collect information for calmly advancing the discussion. For example, when the participant is tired, the collection unit can also preferentially collect concise and to the point information. This allows more appropriate information to be collected by determining the priority of information according to the emotion of the participant. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can determine the priority of information using an AI model that inputs emotion data of the participant and outputs the priority of information.

[0081] The collection unit can analyze the past speech history of the participants and select the optimal information collection method. For example, the collection unit preferentially collects information related to topics that the participants have frequently spoken about in the past. For example, the collection unit can also analyze the past speech patterns of the participants and select an effective information collection method. For example, the collection unit can also collect information related to topics that the participants have shown interest in in the past. This makes it possible to effectively collect information by analyzing the past speech history. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can select the information collection method using an AI model that inputs the past speech history of the participants and outputs the optimal information collection method.

[0082] The collection unit can filter information based on the specialty and title of the participant at the time of collection. The collection unit, for example, preferentially collects information related to the specialty of the participant. The collection unit can also filter necessary information according to the role of the participant. The collection unit can also collect highly relevant information based on the expertise of the participant. This makes it possible to collect highly relevant information by filtering information based on the specialty and title. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can filter information using an AI model that uses the specialty and title of the participant as input and filters information.

[0083] The collection unit can estimate the emotion of the participant and adjust the timing of information collection based on the emotion. For example, when the participant is relaxed, the collection unit adjusts the timing of collecting detailed information. For example, when the participant is nervous, the collection unit can also adjust the timing of collecting concise information. For example, when the participant is excited, the collection unit can also adjust the timing of collecting information to calmly proceed with the discussion. This enables more effective information collection by adjusting the timing of information collection based on emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can adjust the timing of information collection using an AI model that inputs emotion data of the participant and outputs the timing of information collection.

[0084] The collection unit can collect highly relevant information preferentially based on the geographical location information of the participant at the time of collection. For example, when the participant is in a specific area, the collection unit preferentially collects information related to the area. The collection unit can also filter highly relevant information based on the geographical location information of the participant. For example, when the participant is moving, the collection unit can also collect necessary information based on the current location. In this way, highly relevant information can be collected preferentially by collecting information based on the geographical location information. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the geographical location information of the participant and outputs highly relevant information.

[0085] The collection unit can analyze the social media activities of the participants at the time of collection and collect related information. The collection unit can, for example, analyze the content of the participants' comments on social media and collect related information. The collection unit can also collect necessary information based on information shared by the participants on social media, for example. The collection unit can also collect information related to topics of interest from the participants' social media activities, for example. In this way, information based on the participants' interests can be collected by analyzing the social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or can be performed without using AI. For example, the collection unit can collect information using an AI model that inputs the participants' social media activities and outputs related information.

[0086] The facilitator can estimate the emotion of the participant and adjust the method of proceeding based on the emotion. For example, when the participant is nervous, the facilitator adopts a method of proceeding to relax the participant. For example, when the participant is excited, the facilitator can also adopt a method of proceeding to calmly proceed with the discussion. For example, when the participant is tired, the facilitator can also adopt a concise and to the point method of proceeding. This allows the conference to proceed more effectively by adjusting the method of proceeding based on the emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the facilitator may be performed using, for example, an AI, or may be performed without using an AI. For example, the facilitator can adjust the method of proceeding using an AI model that inputs emotion data of the participant and outputs a method of proceeding.

[0087] During the proceedings, the proceeding unit can determine the order in which participants are asked to speak based on the expertise of the participants. For example, the proceeding unit preferentially asks participants who have expertise on a particular topic to speak. For example, the proceeding unit can also determine an effective order of speaking based on the expertise of the participants. For example, the proceeding unit can adjust the order of speaking based on the role or field of expertise of the participants. This enables effective discussion by determining the order of speaking based on expertise. Some or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can determine the order of speaking using an AI model that inputs the expertise of participants and outputs the order of speaking.

[0088] The progress unit can apply different progress algorithms depending on the purpose of the meeting during the progress. For example, when the purpose of the meeting is decision-making, the progress unit applies a rapid progress algorithm. For example, when the purpose of the meeting is brainstorming, the progress unit can also apply a progress algorithm that encourages free speech. For example, when the purpose of the meeting is information sharing, the progress unit can also apply a progress algorithm that includes a detailed explanation. This makes it possible to progress according to the purpose by applying a progress algorithm according to the purpose of the meeting. Some or all of the above-mentioned processing in the progress unit may be performed using, for example, AI, or may be performed without using AI. For example, the progress unit can apply the progress algorithm using an AI model that inputs the purpose of the meeting and outputs a progress algorithm.

[0089] The facilitator can estimate the emotion of the participant and adjust the speed of the proceeding based on the emotion. For example, when the participant is nervous, the facilitator adopts a slow proceeding speed. For example, when the participant is excited, the facilitator can also adopt a proceeding speed for calmly proceeding with the discussion. For example, when the participant is tired, the facilitator can also adopt a concise and fast proceeding speed. This allows the proceeding speed to be adjusted based on the emotion, making it possible to proceed with the meeting more effectively. The estimation of the emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the facilitator may be performed, for example, using an AI, or may be performed without using an AI. For example, the facilitator can adjust the proceeding speed using an AI model that inputs emotion data of the participant and outputs the proceeding speed.

[0090] The facilitator can adjust the order of requests for speech based on the content of past speeches of the participants during the discussion. The facilitator determines an effective speech order based on, for example, the content of past speeches of the participants. The facilitator can also adjust the optimal speech order by, for example, analyzing the past speech patterns of the participants. The facilitator can also preferentially request speech related to topics in which the participants have shown interest in the past. This allows for effective discussion by adjusting the speech order based on the content of past speeches. A part or all of the above-mentioned processing in the facilitator may be performed using, for example, AI, or may be performed without using AI. For example, the facilitator can adjust the speech order using an AI model that inputs the content of past speeches of the participants and outputs the speech order.

[0091] The proceeding unit can change the proceeding method in real time according to the progress of the conference during the conference. For example, if the conference is running behind schedule, the proceeding unit changes to a quick proceeding method. For example, if the conference is running ahead of schedule, the proceeding unit can also change to a proceeding method that encourages detailed discussion. For example, the proceeding unit can adjust an appropriate proceeding method in real time according to the progress of the conference. This allows flexible conference progress by changing the proceeding method according to the progress. A part or all of the above-mentioned processing in the proceeding unit may be performed using, for example, AI, or may be performed without using AI. For example, the proceeding unit can change the proceeding method using an AI model that inputs the progress of the conference and outputs the proceeding method.

[0092] The summarizing unit can estimate the emotion of the participant and adjust the expression method of the summary based on the emotion. For example, when the participant is nervous, the summarizing unit provides a concise summary that covers the main points. For example, when the participant is relaxed, the summarizing unit can also provide a summary that includes detailed information. For example, when the participant is tired, the summarizing unit can also provide a visually easy-to-understand summary. In this way, a more appropriate summary is provided by adjusting the expression method of the summary based on the emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarizing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarizing unit can adjust the expression method of the summary using an AI model that inputs emotion data of the participant and outputs the expression method of the summary.

[0093] The summarization unit can adjust the level of detail of the summary based on the importance of the statement when summarizing. The summarization unit can provide a detailed summary for an important statement, for example. The summarization unit can also provide a concise summary for a statement with low importance, for example. The summarization unit can also adjust the level of detail of the summary according to the importance of the statement, for example. As a result, important information is appropriately summarized by adjusting the level of detail of the summary based on the importance of the statement. A part or all of the above-mentioned processing in the summarization unit can be performed, for example, using AI, or can be performed without using AI. For example, the summarization unit can adjust the level of detail of the summary using an AI model that inputs the importance of the statement and outputs the level of detail of the summary.

[0094] The summarization unit can apply different summarization algorithms depending on the category of the utterance when summarizing. For example, the summarization unit applies a detailed summarization algorithm to technical utterances. For example, the summarization unit can also apply a concise summarization algorithm to utterances of an exchange of opinions. The summarization unit can also select an appropriate summarization algorithm depending on the category of the utterance. In this way, an appropriate summary is provided by applying a summarization algorithm depending on the category of the utterance. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can apply a summarization algorithm using an AI model that inputs the category of the utterance and outputs a summarization algorithm.

[0095] The summarization unit can estimate the emotion of the participant and adjust the length of the summary based on the emotion. For example, if the participant is nervous, the summarization unit provides a short summary that covers the main points. For example, if the participant is relaxed, the summarization unit can also provide a longer summary that includes detailed information. For example, if the participant is tired, the summarization unit can also provide a short summary that is visually easy to understand. In this way, a more appropriate summary is provided by adjusting the length of the summary based on the emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the summarization unit can adjust the length of the summary using an AI model that inputs emotion data of the participant and outputs the length of the summary.

[0096] The summarization unit can determine the priority of summarization based on the timing of utterances when summarizing. The summarization unit, for example, prioritizes summarization of content uttered at the beginning of a meeting. The summarization unit can also prioritize summarization of content uttered at the end of a meeting. The summarization unit can also adjust the priority of summarization based on the timing of utterances. As a result, important information is appropriately summarized by determining the priority of summarization based on the timing of utterances. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can determine the priority of summarization using an AI model that inputs the timing of utterances and outputs the priority of summarization.

[0097] The summarization unit can adjust the order of summaries based on the relevance of the utterances when summarizing. The summarization unit, for example, prioritizes summarization of highly relevant utterances. The summarization unit can also summarize less relevant utterances later, for example. The summarization unit can also adjust the order of summaries based on the relevance of the utterances. As a result, important information is appropriately summarized by adjusting the order of summaries based on the relevance of the utterances. A part or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can adjust the order of summaries using an AI model that inputs the relevance of the utterances and outputs the order of summaries.

[0098] The order management unit can estimate the emotion of the participants and adjust the speaking order based on the emotion. For example, if the participant is nervous, the order management unit adjusts the speaking order to relax the participant. For example, if the participant is excited, the order management unit can also adjust the speaking order to calmly proceed with the discussion. For example, if the participant is tired, the order management unit can adjust the speaking order to be concise and to the point. This allows the meeting to proceed more effectively by adjusting the speaking order based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the order management unit can adjust the speaking order using an AI model that inputs emotion data of the participants and outputs the speaking order.

[0099] The order management unit can determine the order based on the expertise of the participants when managing the speaking order. For example, the order management unit preferentially requests participants who have expertise on a specific topic to speak. The order management unit can also determine an effective speaking order based on the expertise of the participants. The order management unit can also adjust the order in which participants are asked to speak, for example, according to their positions and fields of expertise. This enables effective discussion by determining the speaking order based on expertise. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can determine the speaking order using an AI model that inputs the expertise of participants and outputs the speaking order.

[0100] The order management unit can estimate the emotions of the participants and adjust the display method of the speaking order based on the emotions. For example, when a participant is nervous, the order management unit provides a display method that allows the participant to visually relax. For example, when a participant is excited, the order management unit can also provide a display method that allows the participant to calmly proceed with the discussion. For example, when a participant is tired, the order management unit can also provide a simple and highly visible display method. This allows the meeting to proceed more effectively by adjusting the display method based on the emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the order management unit can adjust the display method using an AI model that inputs emotion data of the participants and outputs a display method.

[0101] The order management unit can adjust the order based on the past remarks of the participants when managing the remark order. The order management unit determines an effective remark order based on, for example, the contents of the remarks made by the participants in the past. The order management unit can also adjust the optimal remark order by analyzing, for example, the past remark patterns of the participants. The order management unit can also preferentially request remarks related to topics in which the participants have shown interest in the past. This enables effective discussion by adjusting the remark order based on the past remarks. A part or all of the above-mentioned processing in the order management unit may be performed using, for example, AI, or may be performed without using AI. For example, the order management unit can adjust the remark order using an AI model that inputs the past remarks of the participants and outputs the remark order.

[0102] The time management unit can estimate the emotion of the participant and adjust the time allocation based on the emotion. For example, if the participant is nervous, the time management unit adjusts the time allocation to relax the participant. For example, if the participant is excited, the time management unit can also adjust the time allocation to calmly proceed with the discussion. For example, if the participant is tired, the time management unit can adjust the time allocation to be concise and to the main points. This allows the meeting to proceed more effectively by adjusting the time allocation based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the time management unit can adjust the time allocation using an AI model that inputs emotion data of the participant and outputs the time allocation.

[0103] The time management unit can optimize time allocation according to the progress of the meeting during time management. For example, if the meeting is running behind schedule, the time management unit changes to a quick progress method. For example, if the meeting is running ahead of schedule, the time management unit can also change to a progress method that encourages detailed discussion. For example, the time management unit can adjust an appropriate progress method in real time according to the progress of the meeting. This allows flexible progress of the meeting by optimizing time allocation according to the progress. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can optimize time allocation using an AI model that inputs the progress of the meeting and outputs time allocation.

[0104] The time management unit can estimate the emotions of the participants and determine the priority of time allocation based on the emotions. For example, if the participants are nervous, the time management unit adjusts the priority of time allocation to relax them. For example, if the participants are excited, the time management unit can also adjust the priority of time allocation to calmly advance the discussion. For example, if the participants are tired, the time management unit can also adjust the priority of time allocation to be concise and to the point. This enables more effective progress in the meeting by determining the priority of time allocation based on emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the time management unit can determine the priority of time allocation using an AI model that inputs emotion data of the participants and outputs the priority of time allocation.

[0105] The time management unit can adjust the time allocation based on the past speech times of the participants during time management. For example, if the participant has spoken for a long time in the past, the time management unit shortens the next speech time. For example, if the participant has spoken for a short time in the past, the time management unit can also extend the next speech time. For example, the time management unit can analyze the past speech times of the participants and adjust the optimal time allocation. As a result, by adjusting the time allocation based on the past speech times, it is possible to effectively proceed with the conference. A part or all of the above-mentioned processing in the time management unit may be performed using, for example, AI, or may be performed without using AI. For example, the time management unit can adjust the time allocation using an AI model that inputs the past speech times of the participants and outputs the time allocation.

[0106] The analysis unit can estimate the emotion of the participant and adjust the analysis method of the remark content based on the emotion. For example, when the participant is nervous, the analysis unit adopts a concise and to the point analysis method. For example, when the participant is excited, the analysis unit can also adopt an analysis method for calmly proceeding with the discussion. For example, when the participant is tired, the analysis unit can also adopt a visually easy-to-understand analysis method. This allows for more appropriate analysis by adjusting the analysis method based on the emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can adjust the analysis method using an AI model that inputs emotion data of the participant and outputs an analysis method.

[0107] The analysis unit can adjust the level of detail of the analysis based on the importance of the statement during analysis. The analysis unit, for example, performs a detailed analysis of an important statement. The analysis unit can also perform a concise analysis of a statement with low importance. The analysis unit can also adjust the level of detail of the analysis according to the importance of the statement. As a result, important information is appropriately analyzed by adjusting the level of detail of the analysis based on the importance of the statement. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the level of detail of the analysis using an AI model that inputs the importance of the statement and outputs the level of detail of the analysis.

[0108] The analysis unit can apply different analysis algorithms depending on the category of the statement during analysis. For example, the analysis unit applies a detailed analysis algorithm to technical statements. For example, the analysis unit can also apply a simple analysis algorithm to statements of exchange of opinions. For example, the analysis unit can select an appropriate analysis algorithm depending on the category of the statement. This enables appropriate analysis by applying an analysis algorithm according to the category of the statement. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can apply the analysis algorithm using an AI model that inputs the category of the statement and outputs the analysis algorithm.

[0109] The analysis unit can estimate the emotion of the participant and adjust the display method of the analysis result based on the emotion. For example, when the participant is nervous, the analysis unit provides a display method that allows the participant to visually relax. For example, when the participant is excited, the analysis unit can also provide a display method that allows the participant to calmly proceed with the discussion. For example, when the participant is tired, the analysis unit can also provide a simple and highly visible display method. As a result, by adjusting the display method based on the emotion, more appropriate analysis results are provided. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can adjust the display method using an AI model that inputs emotion data of the participant and outputs a display method.

[0110] The analysis unit can determine the priority of the analysis based on the timing of the speech during the analysis. The analysis unit, for example, preferentially analyzes the content spoken at the beginning of the meeting. The analysis unit can also preferentially analyze the content spoken at the end of the meeting. The analysis unit can also adjust the priority of the analysis based on the timing of the speech. As a result, important information is appropriately analyzed by determining the priority of the analysis based on the timing of the speech. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can determine the priority of the analysis using an AI model that inputs the timing of the speech and outputs the priority of the analysis.

[0111] The analysis unit can adjust the order of analysis based on the relevance of the statements during analysis. The analysis unit, for example, prioritizes analysis of highly relevant statements. The analysis unit can also analyze less relevant statements later, for example. The analysis unit can also adjust the order of analysis based on the relevance of the statements. As a result, important information is appropriately analyzed by adjusting the order of analysis based on the relevance of the statements. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can adjust the order of analysis using an AI model that inputs the relevance of the statements and outputs the order of analysis.

[0112] The minutes creation unit can estimate the emotions of the participants and adjust the expression method of the minutes based on the emotions. For example, when the participants are nervous, the minutes creation unit provides minutes that are concise and to the point. For example, when the participants are relaxed, the minutes creation unit can also provide minutes that include detailed information. For example, when the participants are tired, the minutes creation unit can also provide minutes that are visually easy to understand. In this way, by adjusting the expression method of the minutes based on the emotions, more appropriate minutes are provided. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the minutes creation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the minutes creation unit can adjust the expression method of the minutes using an AI model that inputs emotion data of the participants and outputs the expression method of the minutes.

[0113] The minutes-taking section can adjust the level of detail of the minutes based on the importance of the remarks when taking the minutes. The minutes-taking section can take detailed minutes for important remarks, for example. The minutes-taking section can also take concise minutes for remarks with low importance, for example. The minutes-taking section can also adjust the level of detail of the minutes according to the importance of the remarks, for example. By adjusting the level of detail of the minutes based on the importance of the remarks, important information is appropriately recorded. Some or all of the above-mentioned processing in the minutes-taking section can be performed using, for example, AI, or can be performed without using AI. For example, the minutes-taking section can adjust the level of detail of the minutes using an AI model that inputs the importance of the remarks and outputs the level of detail of the minutes.

[0114] The minutes creation unit can estimate the emotions of the participants and adjust the length of the minutes based on the emotions. For example, if the participants are nervous, the minutes creation unit provides short minutes that are to the point. For example, if the participants are relaxed, the minutes creation unit can also provide longer minutes that include detailed information. For example, if the participants are tired, the minutes creation unit can also provide short minutes that are visually easy to understand. In this way, more appropriate minutes are provided by adjusting the length of the minutes based on the emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the minutes creation unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the minutes creation unit can adjust the length of the minutes using an AI model that inputs emotion data of the participants and outputs the length of the minutes.

[0115] The minutes-taking section can determine the priority of the minutes based on the timing of remarks when taking minutes. The minutes-taking section, for example, preferentially records in the minutes the contents of remarks made at the beginning of the meeting. The minutes-taking section can also preferentially record in the minutes the contents of remarks made at the end of the meeting. The minutes-taking section can also adjust the priority of the minutes based on the timing of remarks. As a result, important information is appropriately recorded by determining the priority of the minutes based on the timing of remarks. A part or all of the above-mentioned processing in the minutes-taking section may be performed using, for example, AI, or may be performed without using AI. For example, the minutes-taking section can determine the priority of the minutes using an AI model that inputs the timing of remarks and outputs the priority of the minutes.

[0116] The speech promotion unit can estimate the emotion of the participant and adjust the method of encouraging speech based on the emotion. For example, when the participant is nervous, the speech promotion unit adopts a speech promotion method for relaxing the participant. For example, when the participant is excited, the speech promotion unit can also adopt a speech promotion method for calmly advancing the discussion. For example, when the participant is tired, the speech promotion unit can also adopt a concise speech promotion method that focuses on the main points. This allows the conference to proceed more effectively by adjusting the method of encouraging speech based on emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speech promotion unit can adjust the speech promotion method using an AI model that inputs emotion data of the participant and outputs a speech promotion method.

[0117] The speech promotion unit can determine the order in which speech is encouraged based on the expertise of the participants when encouraging speech. For example, the speech promotion unit preferentially asks participants who have expertise on a particular topic to speak. The speech promotion unit can also determine an effective speech order based on the expertise of the participants. The speech promotion unit can also adjust the order in which speech is asked based on the role or field of expertise of the participants. This enables effective discussion by determining the speech order based on expertise. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech promotion unit can determine the speech order using an AI model that inputs the expertise of the participants and outputs the speech order.

[0118] The speech promotion unit can estimate the emotion of the participant and adjust the timing of encouraging speech based on the emotion. For example, when the participant is nervous, the speech promotion unit encourages speech at a timing to relax the participant. For example, when the participant is excited, the speech promotion unit can also encourage speech at a timing to calmly advance the discussion. For example, when the participant is tired, the speech promotion unit can also encourage speech at a timing that is concise and to the point. This allows the conference to proceed more effectively by adjusting the timing of encouraging speech based on emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the speech promotion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the speech promotion unit can adjust the timing of encouraging speech using an AI model that inputs emotion data of the participant and outputs the timing of encouraging speech.

[0119] The speech promotion unit can adjust the order in which speech is promoted based on the content of past speeches of the participants when promoting speech. The speech promotion unit determines an effective speech order based on, for example, the content of past speeches made by the participants. The speech promotion unit can also adjust the optimal speech order by analyzing, for example, the past speech patterns of the participants. The speech promotion unit can also preferentially request speeches related to topics in which the participants have shown interest in the past. This enables effective discussion by adjusting the speech order based on the content of past speeches. A part or all of the above-mentioned processing in the speech promotion unit may be performed, for example, using AI, or may be performed without using AI. For example, the speech promotion unit can adjust the speech order using an AI model that inputs the content of past speeches of the participants and outputs the speech order.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The conference support system may include a translation unit that translates the content of participants' remarks in real time. The translation unit automatically translates the content of remarks, for example, to facilitate communication between participants who speak different languages. For example, content spoken in English is translated into Japanese, and content spoken in Japanese is translated back into English. The translation unit may also include a dictionary function for appropriately translating technical terms and industry-specific words. This facilitates communication between participants who speak different languages, improving the quality of the conference.

[0122] The conference support system may include a display unit that visually displays the content of speech made by participants. The display unit, for example, displays the content of speech as text in real time. This makes it easier for hearing-impaired participants to understand the content of the conference. The display unit may also summarize and display the content of speech. For example, by displaying a short summary of a long speech, participants may be able to easily grasp the important points. Furthermore, the display unit may visually display the content of speech as a graph or chart. This makes it easier to intuitively understand data and statistical information.

[0123] The conference support system may be equipped with a recording unit that can record what participants say and play it back later. The recording unit can, for example, record the entire conference and play back the necessary parts later. This allows people who were unable to attend the conference or who want to review the contents of the conference to understand the contents of the conference through the recording. The recording unit can also separate recordings for each speaker. For example, it can play back only the statements of a specific speaker. Furthermore, the recording unit can also be equipped with a function to convert the recorded contents into text. This allows the recorded contents to be saved as text, making it easier to search and edit.

[0124] The conference support system may include a material providing unit that analyzes the content of participants' remarks and automatically provides related materials. The material providing unit, for example, automatically searches for literature and data related to the content of the remarks and provides them to the participants. This allows participants to quickly obtain necessary information during the conference, and the discussion progresses smoothly. The material providing unit may also provide minutes and summaries of related past conferences based on the content of the remarks. For example, if the same topic was discussed in a past conference, the discussion progresses more efficiently by referring to the minutes. Furthermore, the material providing unit may also provide related external resources (for example, websites and databases) based on the content of the remarks.

[0125] The meeting support system can include an agenda suggestion unit that automatically suggests the next agenda item based on the content of participants' remarks. For example, the agenda suggestion unit automatically suggests the next agenda item to be discussed when the current agenda item is finished. This allows the meeting to proceed smoothly and reduces time waste. The agenda suggestion unit can also suggest related agenda items based on the content of participants' remarks and interests. For example, if there are many participants who show interest in a particular topic, it will suggest agenda items related to that topic. Furthermore, the agenda suggestion unit can analyze minutes and summaries of past meetings to suggest unresolved agenda items. This allows effective discussions to be held without important topics being overlooked.

[0126] The conference support system may include an atmosphere adjustment unit that estimates the emotions of the participants and adjusts the atmosphere of the conference based on the emotions. For example, if a participant is nervous, the atmosphere adjustment unit plays music to relax the participant. This allows the participant to relax and speak up more easily. In addition, if a participant is excited, the atmosphere adjustment unit may provide environmental sounds to calmly advance the discussion. For example, playing natural sounds or quiet music allows the participants to calm down and engage in constructive discussion. Furthermore, if a participant is tired, the atmosphere adjustment unit may suggest a short break to refresh the participant. This allows the participant to participate in the conference while feeling refreshed and maintaining concentration.

[0127] The conference support system may include a feedback unit that estimates the emotions of the participants and provides feedback on what is being said based on the emotions. For example, if a participant is nervous, the feedback unit provides positive feedback. This allows the participant to speak with confidence. In addition, if a participant is excited, the feedback unit may provide constructive feedback to calmly advance the discussion. For example, by suggesting specific improvements or next steps, the participant may calmly advance the discussion. Furthermore, if a participant is tired, the feedback unit may provide words of encouragement or suggestions for refreshing. This allows the participant to participate in the conference while maintaining motivation.

[0128] The conference support system can include an order adjustment unit that estimates the emotions of the participants and adjusts the order of speech based on the emotions. For example, if a participant is nervous, the order adjustment unit adjusts the order of speech to relax the participant. This allows the participant to relax and speak more easily. The order adjustment unit can also adjust the order of speech to calmly advance the discussion if the participant is excited. For example, by allowing a calm participant to speak first, the discussion can proceed in a calm atmosphere. Furthermore, if a participant is tired, the order adjustment unit can also adjust the order of speech to be concise and to the point. This allows participants to speak efficiently and the conference to proceed smoothly.

[0129] The conference support system may include a speed adjustment unit that estimates the emotions of the participants and adjusts the progress speed of the conference based on the emotions. For example, the speed adjustment unit adopts a slow progress speed when the participants are nervous. This allows the participants to relax and speak up more easily. The speed adjustment unit can also adjust the progress speed to calmly advance the discussion when the participants are excited. For example, a slow progress speed is adopted so that the discussion does not become overheated. Furthermore, the speed adjustment unit can also adopt a concise and fast progress speed when the participants are tired. This allows the participants to participate in the conference while maintaining their concentration.

[0130] The conference support system may include a summarizing unit that estimates the emotions of participants and summarizes the contents of the conference based on the emotions. For example, if a participant is nervous, the summarizing unit provides a concise summary that focuses on the main points. This makes it easier for the participant to grasp the important points. The summarizing unit may also provide a summary that includes detailed information if the participant is relaxed. For example, providing a summary that includes the background and detailed explanation of the discussion makes it easier for the participant to understand the overall picture of the discussion. Furthermore, the summarizing unit may provide a visually easy-to-understand summary if a participant is tired. This allows the participant to efficiently grasp the contents of the conference through visual information.

[0131] The process flow of the second embodiment will be briefly described below.

[0132] Step 1: The collection unit collects participant information. Participant information includes names, job titles, areas of expertise, past speech history, etc. The collection unit collects participant information using a questionnaire. In addition, biometric information of participants can be collected using sensors. Furthermore, participants' interests and concerns can be understood using social media analysis. For example, participants' names and job titles can be collected through a questionnaire, and participants' heart rates and body temperatures can be measured using sensors to understand their level of tension. Social media analysis is used to identify topics that participants are interested in from content they have posted in the past. Step 2: The Facilitator manages the progress of the meeting based on the information collected by the Collector. The Facilitator decides the speaking order and adjusts time allocation. For example, the Facilitator decides the speaking order based on the participants' job titles and expertise, and for important topics, gives priority to participants with specialized knowledge. If the meeting is behind schedule, the Facilitator changes to a faster progress method. Step 3: The summarization unit analyzes the contents of the meeting managed by the facilitator in real time and extracts important points. The summarization unit uses natural language processing technology to analyze the content of the comments and extracts important points based on frequently occurring keywords and the importance of the comments. It can also apply different summarization algorithms depending on the category of the comments. For example, a detailed summarization algorithm is applied to technical comments, and a concise summarization algorithm is applied to comments that involve the exchange of opinions.

[0133] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0135] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements including the collection unit, progress unit, summary unit, order management unit, time management unit, analysis unit, minutes creation unit, and speech promotion unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects participant information using a sensor or a questionnaire function of the smart device 14. The progress unit manages the progress of the conference by the specific processing unit 290 of the data processing device 12. The summary unit analyzes the content of the speech in real time by the specific processing unit 290 of the data processing device 12 and extracts important points. The order management unit manages the order of the speech by the specific processing unit 290 of the data processing device 12. The time management unit manages the time allocation of the speech by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the content of the speech by the specific processing unit 290 of the data processing device 12. The minutes creation unit creates minutes based on the summary by the specific processing unit 290 of the data processing device 12. The speech promotion unit encourages the participants to speak by the control unit 46A of the smart device 14. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0144] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0147] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0149] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements including the above-mentioned collection unit, progress unit, summary unit, order management unit, time management unit, analysis unit, minutes creation unit, and speech promotion unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects participant information using a sensor or a questionnaire function of the smart glasses 214. The progress unit manages the progress of the conference by the specific processing unit 290 of the data processing device 12. The summary unit analyzes the remarks in real time by the specific processing unit 290 of the data processing device 12 and extracts important points. The order management unit manages the order of remarks by the specific processing unit 290 of the data processing device 12. The time management unit manages the time allocation of remarks by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the remarks by the specific processing unit 290 of the data processing device 12. The minutes creation unit creates minutes based on the summaries by the specific processing unit 290 of the data processing device 12. The speech promotion unit encourages participants to speak by the control unit 46A of the smart glasses 214. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0155] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0160] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0163] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements including the above-mentioned collection unit, progress unit, summarization unit, order management unit, time management unit, analysis unit, minutes creation unit, and speech promotion unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects participant information using a sensor or a questionnaire function of the headset type terminal 314. The progress unit manages the progress of the conference by the specific processing unit 290 of the data processing device 12. The summarization unit analyzes the content of the speech in real time by the specific processing unit 290 of the data processing device 12 and extracts important points. The order management unit manages the order of the speech by the specific processing unit 290 of the data processing device 12. The time management unit manages the time allocation of the speech by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the content of the speech by the specific processing unit 290 of the data processing device 12. The minutes creation unit creates minutes based on the summaries by the specific processing unit 290 of the data processing device 12. The speech promotion unit encourages the participants to speak by the control unit 46A of the headset type terminal 314. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0178] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0180] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] Each of the multiple elements including the above-mentioned collection unit, progress unit, summarization unit, order management unit, time management unit, analysis unit, minutes creation unit, and speech promotion unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects participant information using a sensor or a questionnaire function of the robot 414. The progress unit manages the progress of the conference by the specific processing unit 290 of the data processing device 12. The summarization unit analyzes the content of the speech in real time by the specific processing unit 290 of the data processing device 12 and extracts important points. The order management unit manages the order of the speech by the specific processing unit 290 of the data processing device 12. The time management unit manages the time allocation of the speech by the specific processing unit 290 of the data processing device 12. The analysis unit analyzes the content of the speech by the specific processing unit 290 of the data processing device 12. The minutes creation unit creates minutes based on the summaries by the specific processing unit 290 of the data processing device 12. The speech promotion unit encourages the participants to speak by the control unit 46A of the robot 414. The correspondence between each part and the device or control part is not limited to the above-mentioned example, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0187] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0191] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] In addition, 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 upon request from the data processing device 12.

[0196] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0197] As the hardware resource for executing the specific process, the following various processors can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application specific integrated circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0198] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0202] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0204] (Appendix 1) A collection unit that collects participant information; A progress manager who manages the progress of the meeting based on the collected information; A summarizing unit that analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. A system characterized by: (Appendix 2) Equipped with a sequence control unit that manages the order of speech 2. The system of claim 1, (Appendix 3) Equipped with a time management department that manages the allocation of speaking time 2. The system of claim 1, (Appendix 4) Equipped with an analysis unit that analyzes the contents of statements 2. The system of claim 1, (Appendix 5) Have a minutes-taking department that prepares minutes based on summaries 2. The system of claim 1, (Appendix 6) Equipping participants with a speaking prompter 2. The system of claim 1, (Appendix 7) The collecting unit includes: Estimate participants' emotions and prioritize the information to be collected based on those emotions 2. The system of claim 1, (Appendix 8) The collecting unit includes: Analyze participants' past comment history and select the most appropriate information gathering method 2. The system of claim 1, (Appendix 9) The collecting unit includes: At the time of collection, filter information based on participants' areas of expertise or job titles 2. The system of claim 1, (Appendix 10) The collecting unit includes: Estimate participants' emotions and adjust the timing of information collection based on those emotions 2. The system of claim 1, (Appendix 11) The collecting unit includes: At the time of collection, prioritize collection of relevant information based on the participant's geographic location 2. The system of claim 1, (Appendix 12) The collecting unit includes: At the time of collection, participants’ social media activity will be analyzed to gather relevant information 2. The system of claim 1, (Appendix 13) The progression section includes: Estimate participants' emotions and adjust your approach based on those emotions 2. The system of claim 1, (Appendix 14) The progression section includes: During the meeting, decide in what order participants should be asked to speak based on their expertise. 2. The system of claim 1, (Appendix 15) The progression section includes: During the process, different algorithms are applied depending on the purpose of the meeting. 2. The system of claim 1, (Appendix 16) The progression section includes: Estimate participants' emotions and adjust the pace of the progress based on those emotions 2. The system of claim 1, (Appendix 17) The progression section includes: As you moderate, adjust the order in which participants are asked to speak based on what they have said previously 2. The system of claim 1, (Appendix 18) The progression section includes: Change the way you conduct the meeting in real time according to the progress of the meeting. 2. The system of claim 1, (Appendix 19) The summary portion comprises: Estimate participants' emotions and adjust the way summaries are presented based on those emotions 2. The system of claim 1, (Appendix 20) The summary portion comprises: When summarizing, adjust the level of detail in your summary based on the importance of what is said 2. The system of claim 1, (Appendix 21) The summary portion comprises: When summarizing, different summarization algorithms are applied depending on the category of the utterance. 2. The system of claim 1, (Appendix 22) The summary portion comprises: Estimate participants' emotions and adjust the length of summaries based on those emotions 2. The system of claim 1, (Appendix 23) The summary portion comprises: When summarizing, prioritize summaries based on the timing of comments 2. The system of claim 1, (Appendix 24) The summary portion comprises: When summarizing, adjust the order of summaries based on the relevance of statements 2. The system of claim 1, (Appendix 25) The sequence management unit Estimate participants' emotions and adjust speaking order based on those emotions 3. The system of claim 2, (Appendix 26) The sequence management unit When managing speaking order, determine the order based on participants' expertise 3. The system of claim 2, (Appendix 27) The sequence management unit Estimate participants' emotions and adjust the way they speak based on those emotions 3. The system of claim 2, (Appendix 28) The sequence management unit When managing speaking order, adjust the order based on participants' previous comments 3. The system of claim 2, (Appendix 29) The time management unit Estimate participants' emotions and adjust time allocation based on those emotions 4. The system of claim 3. (Appendix 30) The time management unit When managing time, optimize time allocation according to the progress of the meeting 4. The system of claim 3. (Appendix 31) The time management unit Estimate participants' emotions and prioritize time allocation based on those emotions 4. The system of claim 3. (Appendix 32) The time management unit When managing time, adjust time allocation based on participants' past speaking time 4. The system of claim 3. (Appendix 33) The analysis unit is Infer participants' emotions and adjust how their speech is parsed based on those emotions 5. The system of claim 4. (Appendix 34) The analysis unit is During analysis, adjust the level of detail of the analysis based on the importance of the statement 5. The system of claim 4. (Appendix 35) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the statement. 5. The system of claim 4. (Appendix 36) The analysis unit is Infer participants' emotions and adjust how analysis results are presented based on those emotions 5. The system of claim 4. (Appendix 37) The analysis unit is During analysis, the analysis priority is determined based on the timing of speech. 5. The system of claim 4. (Appendix 38) The analysis unit is During analysis, adjust the order of analysis based on the relevance of utterances 5. The system of claim 4. (Appendix 39) The minutes preparation department comprises: Estimate participants' emotions and adjust the presentation of the minutes based on those emotions 6. The system of claim 5, (Appendix 40) The minutes preparation department comprises: When taking minutes, adjust the level of detail in the minutes based on the importance of what was said 6. The system of claim 5, (Appendix 41) The minutes preparation department comprises: Estimate participants' emotions and adjust the length of the minutes based on those emotions 6. The system of claim 5, (Appendix 42) The minutes preparation department comprises: When taking minutes, prioritize minutes based on the timing of what was said 6. The system of claim 5, (Appendix 43) The speech promotion unit includes: Estimate participants' emotions and tailor prompts based on those emotions 7. The system of claim 6, (Appendix 44) The speech promotion unit includes: During prompting, determine the order in which participants are prompted based on their expertise 7. The system of claim 6, (Appendix 45) The speech promotion unit includes: Estimate participants' emotions and adjust the timing of prompts based on those emotions 7. The system of claim 6, (Appendix 46) The speech promotion unit includes: When encouraging people to speak, adjust the order in which they are prompted based on what participants have said in the past 7. The system of claim 6, [Explanation of symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects participant information; A progress manager who manages the progress of the meeting based on the collected information; A summarizing unit that analyzes the contents of the meeting managed by the proceeding unit in real time and extracts important points. A system characterized by:

2. Equipped with a sequence control unit that manages the order of speech 2. The system of claim 1 .

3. Equipped with a time management department that manages the allocation of speaking time 2. The system of claim 1 .

4. Equipped with an analysis unit that analyzes the contents of statements 2. The system of claim 1 .

5. Have a minutes-taking department that prepares minutes based on summaries 2. The system of claim 1 .

6. Equipping participants with a speaking prompter 2. The system of claim 1 .

7. The collecting unit includes: Estimate participants' emotions and prioritize the information to be collected based on those emotions 2. The system of claim 1 .

8. The collecting unit includes: Analyze participants' past comment history and select the most appropriate information gathering method 2. The system of claim 1 .

Images