System

Abstract

An object of a system according to an embodiment is to enable all participants to equally share their opinions and participate in a discussion.SOLUTION: A system according to an embodiment includes a remark analysis unit, an evaluation unit, a time monitoring unit, a summarization unit, and a task allocation unit. The remark analysis unit analyzes a remark content. The evaluation unit evaluates the remark contents analyzed by the remark analysis unit. The time monitoring unit monitors the speech time based on the speech content evaluated by the evaluation unit. The summarizing part summarizes the speech contents monitored by the time monitoring part. The task allocation unit allocates a task based on the content summarized by the summarization unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have had the problem of making it difficult for all participants in meetings to share their opinions and participate in discussions equally.

[0005] The system according to the embodiment aims to enable all participants to share their opinions and participate in the discussion equally. [Means for solving the problem]

[0006] The system according to the embodiment includes a utterance analysis unit, an evaluation unit, a time monitoring unit, a summarization unit, and a task allocation unit. The utterance analysis unit analyzes the utterance content. The evaluation unit evaluates the utterance content analyzed by the utterance analysis unit. The time monitoring unit monitors the utterance time based on the utterance content evaluated by the evaluation unit. The summarization unit summarizes the utterance content monitored by the time monitoring unit. The task allocation unit assigns tasks based on the content summarized by the summarization unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable all participants to share their opinions and participate in the discussion equally. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) A meeting support system according to an embodiment of the present invention is a system that allows all participants to share their opinions and participate in discussions equally. This system uses generative AI to provide real-time feedback, aiming to realize fair and effective meetings. As a result, the meeting support system allows all participants to share their opinions and participate in discussions equally.

[0029] A meeting support system according to an embodiment includes a utterance analysis unit, an evaluation unit, a time monitoring unit, a summarization unit, and a task allocation unit. The utterance analysis unit analyzes the content of utterances. For example, the generation AI converts the content of utterances into text data using speech recognition technology and analyzes the content. The utterance analysis unit can also analyze the meaning of the content of utterances using text analysis technology. The utterance analysis unit can also perform analysis taking into account the speaker's past utterance history and expertise. For example, the generation AI retrieves past utterance history from a database and compares it with the current utterance content for analysis. The evaluation unit evaluates the utterance content analyzed by the utterance analysis unit. For example, the generation AI evaluates the constructiveness and importance of the utterance content and provides feedback. The evaluation unit can also perform evaluation taking into account the speaker's expertise and past utterance history. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the utterance content based on that knowledge. The time monitoring unit monitors the speaking time based on the utterance content evaluated by the evaluation unit. For example, the generation AI measures each participant's speaking time in real time and distributes it evenly. The time monitoring unit can also adjust the speaking time taking into account the importance of the content of the speech. For example, the generation AI provides additional speaking time for important speech. The summarization unit summarizes the speech content monitored by the time monitoring unit. For example, the generation AI extracts important points from the speech content and creates a summary. The summarization unit can also reference past meeting records and related documents to create the summary. For example, the generation AI retrieves past meeting records from a database and compares them with the current speech content to create a summary. The task allocation unit assigns tasks based on the content summarized by the summarization unit. For example, the generation AI automatically lists tasks decided during the meeting and assigns them to appropriate personnel. The task allocation unit can also assign tasks taking into account each participant's skill set and past performance. For example, the generation AI retrieves each participant's skill set from a database and assigns tasks based on that information. This allows the meeting support system according to the embodiment to enable all participants to share their opinions and participate in the discussion equally.For example, generative AI can analyze what is being said in real time and provide objective evaluations, enabling fair discussions without being influenced by the personal opinions of superiors. It can also improve the fairness and productivity of meetings with features such as equal allocation of speaking time, automatic summarization of important points, and task assignment.

[0030] The utterance analysis unit takes into account the speaker's past utterance history and expertise, allowing it to provide more accurate evaluations. For example, when the generation AI analyzes the content of a utterance, the utterance analysis unit refers to the speaker's past utterance history and evaluates the relevance between past utterances and the current utterance. For example, it evaluates the consistency and depth of the current utterance based on past utterances on a similar topic. The utterance analysis unit also analyzes the content of a utterance taking into account the speaker's expertise. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the content of the utterance based on that knowledge. This improves the accuracy of the evaluation of the content of the utterance.

[0031] The utterance analysis unit translates utterances in different languages ​​in real time, making it possible to provide fair feedback even in international meetings. For example, the generation AI in the utterance analysis unit translates utterance content in real time and analyzes utterances in different languages. For example, it translates utterances in English into Japanese and provides feedback based on that content. The utterance analysis unit also analyzes utterance content using a translation algorithm that supports multiple languages. For example, the generation AI analyzes utterance content using a translation algorithm that supports multiple languages, such as English, French, and Spanish. The utterance analysis unit also translates by referring to a technical dictionary to improve the accuracy of technical terminology translation. For example, the generation AI refers to a dictionary of technical terms and industry terminology to provide accurate translations. This makes it possible to provide fair feedback even in international meetings.

[0032] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0033] The time monitoring unit can dynamically adjust the appropriate speaking time by taking into account the speaker's position and expertise. For example, the generation AI dynamically adjusts speaking time by taking into account the speaker's position. For example, it sets shorter speaking time for senior managers and provides longer speaking time for junior employees. The time monitoring unit also adjusts speaking time by taking into account the speaker's expertise. For example, it provides longer speaking time for speakers with specialized knowledge and shorter speaking time for speakers with less specialized knowledge. The time monitoring unit also comprehensively adjusts speaking time by combining the speaker's position and expertise. For example, it provides shorter speaking time for senior managers with specialized knowledge and provides longer speaking time for junior employees with less specialized knowledge. This makes it possible to adjust speaking time according to the speaker's position and expertise.

[0034] The time monitoring unit can evaluate the importance of the content of comments and provide additional speaking time for important comments. For example, the generation AI evaluates the importance of the content of comments and provides additional speaking time for important comments. For example, longer speaking time is set for comments that touch on the core of the discussion. The time monitoring unit also evaluates the impact of the content of comments and adjusts speaking time. For example, if the content of a comment has a significant impact on the progress of a project, additional speaking time is provided. The time monitoring unit also combines the importance and impact of the content of comments to comprehensively adjust speaking time. For example, if the content of a comment is important and has a high impact, longer speaking time is provided. This makes it possible to provide appropriate speaking time for important comments.

[0035] The time monitoring unit can evenly allocate speech time from different devices. For example, the generation AI in the time monitoring unit monitors speech from different devices and allocates speech time evenly. For example, speech from a smartphone is treated the same as speech from a PC. The time monitoring unit also adjusts speech time according to the type of device. For example, it sets a shorter speech time for speech from a smartphone and a longer speech time for speech from a PC. The time monitoring unit also comprehensively monitors speech from different devices and allocates speech time evenly. For example, it treats speech from different devices such as smartphones, tablets, and PCs equally and allocates speech time. This allows speech from different devices to be treated fairly.

[0036] The time monitoring unit analyzes the speaker's body language and gestures, understands the intention of the speech, and adjusts the speech time accordingly. For example, the generation AI analyzes the speaker's body language, understands the intention of the speech, and adjusts the speech time accordingly. For example, if the speaker raises their hand, the speech time is extended. The time monitoring unit also analyzes the speaker's gestures and adjusts the speech time accordingly. For example, if the speaker points, the speech time is extended. The time monitoring unit also combines body language and gestures to comprehensively analyze the intention of the speech and adjust the speech time accordingly. For example, if the speaker raises their hand and points, the speech time is significantly extended. This makes it possible to adjust the speech time according to the speaker's intention.

[0037] The summarization unit can provide a summary that is appropriate for the context, taking into account the speaker's intention and background information. For example, the summarization unit uses a generation AI to analyze the speaker's intention and provide a summary that is appropriate for the context. For example, it takes into account the background information of the idea proposed by the speaker when creating a summary. The summarization unit also references the speaker's past speech history when creating a summary. For example, it compares past speech content with current speech content to provide a consistent summary. The summarization unit also combines the speaker's intention and background information to comprehensively create a summary. For example, it analyzes the speaker's intention and provides a summary that takes into account background information based on that intention. This makes it possible to provide a summary that takes into account the speaker's intention and background information.

[0038] The summarization unit can provide summaries in different languages ​​in real time, making it possible to provide summaries that are easy to understand even at international meetings. For example, the summarization unit uses a generation AI to translate speech content in real time and provide summaries in different languages. For example, it translates speech in English into Japanese and provides that summary. The summarization unit also uses a translation algorithm that supports multiple languages ​​to create summaries. For example, the generation AI uses a translation algorithm that supports multiple languages, such as English, French, and Spanish, to create summaries. The summarization unit also references a technical dictionary to improve the translation accuracy of technical terms. For example, the generation AI references a dictionary of technical terms and industry terminology to provide accurate translations. This makes it possible to provide summaries that are easy to understand even at international meetings.

[0039] The summarization unit can visualize the content of the utterance and provide a summary that is visually easy to understand. For example, the generation AI ... convert the content of the utterance into a graph or chart and display it visually. The summarization unit can also provide a summary by diagramming the content of the utterance. For example, the generation AI can convert the content of the utterance into a flowchart or mind map and display it visually. When visualizing the content of the utterance, the summarization unit can take into consideration visually easy-to-understand designs and color usage. For example, the generation AI can visualize the content of the utterance using visually easy-to-understand designs and color usage. This makes it possible to provide a summary that is visually easy to understand.

[0040] The task allocation unit can select the most suitable person in charge by taking into account each participant's skill set and past performance. For example, the generation AI registers each participant's skill set in a database and assigns tasks based on that information. For example, it automatically selects tasks suitable for participants with specific skills. The task allocation unit also evaluates each participant's past performance and assigns tasks. For example, it selects an appropriate person in charge based on the results of past projects. The task allocation unit also combines skill sets and past performance to comprehensively select the most suitable person in charge. For example, it assigns tasks to participants who have specific skills and have performed well in the past. This makes it possible to assign optimal tasks by taking into account skill sets and past performance.

[0041] The task allocation unit evaluates the priority and urgency of tasks, enabling efficient task management. For example, the task allocation unit uses a generation AI to evaluate task priority and achieve efficient task management. For example, it prioritizes tasks with high urgency. The task allocation unit also evaluates the urgency of tasks and assigns them. For example, it prioritizes tasks with approaching deadlines. The task allocation unit also combines task priority and urgency to comprehensively manage tasks. For example, it assigns tasks with high importance and urgency as the top priority. This enables efficient task management that takes into account task priority and urgency.

[0042] The task allocation unit can achieve efficient task management by taking into account the relevance of tasks between different projects. For example, the task allocation unit uses a generation AI to analyze the relevance of tasks between different projects and achieve efficient task management. For example, it allocates related tasks collectively. The task allocation unit also manages tasks by optimally allocating resources between projects. For example, it efficiently allocates resources that are common to multiple projects. The task allocation unit also manages tasks by taking into account the dependency of tasks between different projects. For example, if a task for one project cannot start until a task for the next project is completed, the task is assigned taking into account that dependency. This enables efficient task management that takes into account the relevance of tasks between different projects.

[0043] The task allocation unit monitors the progress of tasks in real time and can reallocate tasks as necessary. For example, the generation AI of the task allocation unit monitors the progress of tasks in real time and reallocates tasks as necessary. For example, it reallocates tasks that are behind schedule to other participants. The task allocation unit also reallocates resources based on the progress of tasks. For example, it allocates additional resources to tasks that are behind schedule. The task allocation unit also comprehensively monitors the progress of tasks and achieves efficient task management. For example, it monitors the overall progress in real time and reallocates tasks or reallocates resources as necessary. This makes it possible to monitor the progress of tasks in real time and reallocate tasks as necessary.

[0044] The meeting progress monitoring unit can refer to past meeting data and propose the optimal way to proceed. In the meeting progress monitoring unit, for example, a generation AI refers to past meeting data and proposes the optimal way to proceed. For example, the current meeting is conducted based on the way past successful meetings were conducted. The meeting progress monitoring unit also analyzes past meeting data to propose a way to proceed. For example, the optimal way to proceed is proposed based on the flow of discussion in past meetings and the reactions of participants. The meeting progress monitoring unit also comprehensively analyzes past meeting data and the current meeting situation to propose the optimal way to proceed. For example, the progress of the current discussion is evaluated based on past meeting data and an appropriate way to proceed is proposed. In this way, the optimal way to proceed can be proposed by referring to past meeting data.

[0045] The meeting progress monitoring unit can propose appropriate agenda items by taking into account the expertise and roles of participants. For example, the generative AI analyzes the expertise of participants and proposes appropriate agenda items based on that knowledge. For example, if a technical expert is participating, it will prioritize proposing technical agenda items. The meeting progress monitoring unit also proposes agenda items by taking into account the roles of participants. For example, if a project manager is participating, it will propose agenda items related to the progress of the project. The meeting progress monitoring unit also proposes comprehensive agenda items by combining the expertise and roles of participants. For example, for a participant who is both a technical expert and a project manager, it will propose technical agenda items and agenda items related to the progress of the project. This makes it possible to propose appropriate agenda items by taking into account the expertise and roles of participants.

[0046] The meeting progress monitoring unit can refer to best practices from different industries and fields and propose the optimal way to proceed. For example, the generation AI can refer to best practices from different industries and fields and propose the optimal way to proceed. For example, it can propose a way to proceed with a meeting based on best practices from the IT industry. The meeting progress monitoring unit can also propose a way to proceed based on success stories from different industries and fields. For example, it can propose an efficient way to advance discussions based on success stories from the manufacturing industry. The meeting progress monitoring unit can also propose a comprehensive way to proceed by combining best practices and success stories from different industries and fields. For example, it can propose the optimal way to proceed based on best practices from the IT industry and success stories from the manufacturing industry. This makes it possible to propose the optimal way to proceed by referring to best practices from different industries and fields.

[0047] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0048] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0049] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0050] The utterance analysis unit takes into account the speaker's past utterance history and expertise, allowing it to provide more accurate evaluations. For example, when the generation AI analyzes the content of a utterance, the utterance analysis unit refers to the speaker's past utterance history and evaluates the relevance between past utterances and the current utterance. For example, it evaluates the consistency and depth of the current utterance based on past utterances on a similar topic. The utterance analysis unit also analyzes the content of a utterance taking into account the speaker's expertise. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the content of the utterance based on that knowledge. This improves the accuracy of the evaluation of the content of the utterance.

[0051] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0052] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The meeting support system can further include a health monitoring unit that monitors the health of participants. The health monitoring unit, for example, monitors participants' heart rates and stress levels in real time and provides feedback according to their health status. For example, if a participant's heart rate is high, it can provide advice to relax. The health monitoring unit can also adjust the progress of the meeting based on the participants' health data. For example, it can suggest that a participant with a high stress level take a break. This makes it possible to proceed with the meeting while taking into account the participants' health status.

[0055] The meeting support system can further include a schedule management unit that manages the schedules of participants. The schedule management unit, for example, synchronizes the calendars of each participant and suggests the optimal meeting time. For example, it automatically selects a time slot when everyone can attend. The schedule management unit can also dynamically adjust the schedule according to the progress of the meeting. For example, if a discussion drags on, it will automatically reschedule the next appointment. This enables efficient meeting management that takes into account the schedules of participants.

[0056] The meeting support system can further include an anonymous opinion collection unit that collects participants' opinions anonymously. The anonymous opinion collection unit, for example, provides an anonymous platform where participants can freely post their opinions. For example, by posting opinions anonymously, participants can share content that they would find difficult to speak out about. The anonymous opinion collection unit can also automatically classify the collected opinions and provide them as material for discussion. For example, opinions on the same topic can be grouped and displayed. This can provide an environment where participants can freely share their opinions.

[0057] The meeting support system can further include a recording and playback unit that can record participants' comments and play them back later. The recording and playback unit, for example, can automatically record comments made during a meeting and play them back later. For example, the recording can be played back to reconfirm important comments. The recording and playback unit can also convert recorded data into text and save it in a searchable format. For example, it can search for and play back comments containing specific keywords. This provides an environment in which the contents of the meeting can be reviewed later.

[0058] The meeting support system can further include a translation unit that translates participants' comments in real time. The translation unit, for example, translates comments in different languages ​​in real time, enabling smooth communication even in international meetings. For example, it can translate comments in English into Japanese and provide that content to other participants. The translation unit can also refer to a technical dictionary to improve the accuracy of technical terminology translations. For example, it can refer to a dictionary of technical terms and industry terminology to provide accurate translations. This enables smooth communication even between participants who speak different languages.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The utterance analysis unit analyzes the content of the utterance. For example, the generation AI uses voice recognition technology to convert the utterance content into text data and analyzes that content. The utterance analysis unit can also use text analysis technology to analyze the meaning of the utterance content. Furthermore, the analysis can take into account the speaker's past utterance history and expertise. Step 2: The evaluation unit evaluates the utterances analyzed by the utterance analysis unit. For example, the generation AI evaluates the constructiveness and importance of the utterances and provides feedback. It can also take into account the speaker's expertise and past utterance history when making an evaluation. Step 3: The time monitoring unit monitors the speaking time based on the speech content evaluated by the evaluation unit. For example, the generation AI measures each participant's speaking time in real time and distributes it evenly. It can also adjust speaking time taking into account the importance of the speech content. Step 4: The summarization unit summarizes the speech monitored by the time monitoring unit. For example, the generation AI can extract key points from the speech and create a summary. It can also refer to past meeting records and related documents to create a summary. Step 5: The task assigner assigns tasks based on the summary. For example, the generative AI can automatically list the tasks decided during the meeting and assign them to the appropriate person. It can also assign tasks taking into account each participant's skill set and past performance.

[0061] (Example 2) A meeting support system according to an embodiment of the present invention is a system that allows all participants to share their opinions and participate in discussions equally. This system uses generative AI to provide real-time feedback, aiming to realize fair and effective meetings. As a result, the meeting support system allows all participants to share their opinions and participate in discussions equally.

[0062] A meeting support system according to an embodiment includes a utterance analysis unit, an evaluation unit, a time monitoring unit, a summarization unit, and a task allocation unit. The utterance analysis unit analyzes the content of utterances. For example, the generation AI converts the content of utterances into text data using speech recognition technology and analyzes the content. The utterance analysis unit can also analyze the meaning of the content of utterances using text analysis technology. The utterance analysis unit can also perform analysis taking into account the speaker's past utterance history and expertise. For example, the generation AI retrieves past utterance history from a database and compares it with the current utterance content for analysis. The evaluation unit evaluates the utterance content analyzed by the utterance analysis unit. For example, the generation AI evaluates the constructiveness and importance of the utterance content and provides feedback. The evaluation unit can also perform evaluation taking into account the speaker's expertise and past utterance history. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the utterance content based on that knowledge. The time monitoring unit monitors the speaking time based on the utterance content evaluated by the evaluation unit. For example, the generation AI measures each participant's speaking time in real time and distributes it evenly. The time monitoring unit can also adjust the speaking time taking into account the importance of the content of the speech. For example, the generation AI provides additional speaking time for important speech. The summarization unit summarizes the speech content monitored by the time monitoring unit. For example, the generation AI extracts important points from the speech content and creates a summary. The summarization unit can also reference past meeting records and related documents to create the summary. For example, the generation AI retrieves past meeting records from a database and compares them with the current speech content to create a summary. The task allocation unit assigns tasks based on the content summarized by the summarization unit. For example, the generation AI automatically lists tasks decided during the meeting and assigns them to appropriate personnel. The task allocation unit can also assign tasks taking into account each participant's skill set and past performance. For example, the generation AI retrieves each participant's skill set from a database and assigns tasks based on that information. This allows the meeting support system according to the embodiment to enable all participants to share their opinions and participate in the discussion equally.For example, generative AI can analyze what is being said in real time and provide objective evaluations, enabling fair discussions without being influenced by the personal opinions of superiors. It can also improve the fairness and productivity of meetings with features such as equal allocation of speaking time, automatic summarization of important points, and task assignment.

[0063] The utterance analysis unit takes into account the speaker's past utterance history and expertise, allowing it to provide more accurate evaluations. For example, when the generation AI analyzes the content of a utterance, the utterance analysis unit refers to the speaker's past utterance history and evaluates the relevance between past utterances and the current utterance. For example, it evaluates the consistency and depth of the current utterance based on past utterances on a similar topic. The utterance analysis unit also analyzes the content of a utterance taking into account the speaker's expertise. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the content of the utterance based on that knowledge. This improves the accuracy of the evaluation of the content of the utterance.

[0064] The utterance analysis unit can analyze the tone and speed of the speaker's voice to estimate their emotional state and reflect this in the feedback. For example, the generation AI in the utterance analysis unit analyzes the tone of the speaker's voice to estimate their emotional state. For example, if the voice tone is high, it may determine that the speaker is excited and provide calm feedback. The utterance analysis unit also analyzes the speed of the speaker's voice to estimate their emotional state. For example, if the speaker speaks at a fast speed, it may determine that the speaker is nervous and provide feedback to relax. The utterance analysis unit also combines the tone and speed of the voice to comprehensively analyze the emotional state. For example, if the voice tone is high and the speed is fast, it may determine that the speaker is excited and provide calm feedback. This makes it possible to provide feedback that takes the speaker's emotional state into consideration.

[0065] The utterance analysis unit translates utterances in different languages ​​in real time, making it possible to provide fair feedback even in international meetings. For example, the generation AI in the utterance analysis unit translates utterance content in real time and analyzes utterances in different languages. For example, it translates utterances in English into Japanese and provides feedback based on that content. The utterance analysis unit also analyzes utterance content using a translation algorithm that supports multiple languages. For example, the generation AI analyzes utterance content using a translation algorithm that supports multiple languages, such as English, French, and Spanish. The utterance analysis unit also translates by referring to a technical dictionary to improve the accuracy of technical terminology translation. For example, the generation AI refers to a dictionary of technical terms and industry terminology to provide accurate translations. This makes it possible to provide fair feedback even in international meetings.

[0066] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0067] The time monitoring unit can dynamically adjust the appropriate speaking time by taking into account the speaker's position and expertise. For example, the generation AI dynamically adjusts speaking time by taking into account the speaker's position. For example, it sets shorter speaking time for senior managers and provides longer speaking time for junior employees. The time monitoring unit also adjusts speaking time by taking into account the speaker's expertise. For example, it provides longer speaking time for speakers with specialized knowledge and shorter speaking time for speakers with less specialized knowledge. The time monitoring unit also comprehensively adjusts speaking time by combining the speaker's position and expertise. For example, it provides shorter speaking time for senior managers with specialized knowledge and provides longer speaking time for junior employees with less specialized knowledge. This makes it possible to adjust speaking time according to the speaker's position and expertise.

[0068] The time monitoring unit can evaluate the importance of the content of comments and provide additional speaking time for important comments. For example, the generation AI evaluates the importance of the content of comments and provides additional speaking time for important comments. For example, longer speaking time is set for comments that touch on the core of the discussion. The time monitoring unit also evaluates the impact of the content of comments and adjusts speaking time. For example, if the content of a comment has a significant impact on the progress of a project, additional speaking time is provided. The time monitoring unit also combines the importance and impact of the content of comments to comprehensively adjust speaking time. For example, if the content of a comment is important and has a high impact, longer speaking time is provided. This makes it possible to provide appropriate speaking time for important comments.

[0069] The time monitoring unit can evenly allocate speech time from different devices. For example, the generation AI in the time monitoring unit monitors speech from different devices and allocates speech time evenly. For example, speech from a smartphone is treated the same as speech from a PC. The time monitoring unit also adjusts speech time according to the type of device. For example, it sets a shorter speech time for speech from a smartphone and a longer speech time for speech from a PC. The time monitoring unit also comprehensively monitors speech from different devices and allocates speech time evenly. For example, it treats speech from different devices such as smartphones, tablets, and PCs equally and allocates speech time. This allows speech from different devices to be treated fairly.

[0070] The time monitoring unit analyzes the speaker's body language and gestures, understands the intention of the speech, and adjusts the speech time accordingly. For example, the generation AI analyzes the speaker's body language, understands the intention of the speech, and adjusts the speech time accordingly. For example, if the speaker raises their hand, the speech time is extended. The time monitoring unit also analyzes the speaker's gestures and adjusts the speech time accordingly. For example, if the speaker points, the speech time is extended. The time monitoring unit also combines body language and gestures to comprehensively analyze the intention of the speech and adjust the speech time accordingly. For example, if the speaker raises their hand and points, the speech time is significantly extended. This makes it possible to adjust the speech time according to the speaker's intention.

[0071] The summarization unit can provide a summary that is appropriate for the context, taking into account the speaker's intention and background information. For example, the summarization unit uses a generation AI to analyze the speaker's intention and provide a summary that is appropriate for the context. For example, it takes into account the background information of the idea proposed by the speaker when creating a summary. The summarization unit also references the speaker's past speech history when creating a summary. For example, it compares past speech content with current speech content to provide a consistent summary. The summarization unit also combines the speaker's intention and background information to comprehensively create a summary. For example, it analyzes the speaker's intention and provides a summary that takes into account background information based on that intention. This makes it possible to provide a summary that takes into account the speaker's intention and background information.

[0072] The summarization unit can provide summaries in different languages ​​in real time, making it possible to provide summaries that are easy to understand even at international meetings. For example, the summarization unit uses a generation AI to translate speech content in real time and provide summaries in different languages. For example, it translates speech in English into Japanese and provides that summary. The summarization unit also uses a translation algorithm that supports multiple languages ​​to create summaries. For example, the generation AI uses a translation algorithm that supports multiple languages, such as English, French, and Spanish, to create summaries. The summarization unit also references a technical dictionary to improve the translation accuracy of technical terms. For example, the generation AI references a dictionary of technical terms and industry terminology to provide accurate translations. This makes it possible to provide summaries that are easy to understand even at international meetings.

[0073] The summarization unit can visualize the content of the utterance and provide a summary that is visually easy to understand. For example, the generation AI ... convert the content of the utterance into a graph or chart and display it visually. The summarization unit can also provide a summary by diagramming the content of the utterance. For example, the generation AI can convert the content of the utterance into a flowchart or mind map and display it visually. When visualizing the content of the utterance, the summarization unit can take into consideration visually easy-to-understand designs and color usage. For example, the generation AI can visualize the content of the utterance using visually easy-to-understand designs and color usage. This makes it possible to provide a summary that is visually easy to understand.

[0074] The task allocation unit can select the most suitable person in charge by taking into account each participant's skill set and past performance. For example, the generation AI registers each participant's skill set in a database and assigns tasks based on that information. For example, it automatically selects tasks suitable for participants with specific skills. The task allocation unit also evaluates each participant's past performance and assigns tasks. For example, it selects an appropriate person in charge based on the results of past projects. The task allocation unit also combines skill sets and past performance to comprehensively select the most suitable person in charge. For example, it assigns tasks to participants who have specific skills and have performed well in the past. This makes it possible to assign optimal tasks by taking into account skill sets and past performance.

[0075] The task allocation unit evaluates the priority and urgency of tasks, enabling efficient task management. For example, the task allocation unit uses a generation AI to evaluate task priority and achieve efficient task management. For example, it prioritizes tasks with high urgency. The task allocation unit also evaluates the urgency of tasks and assigns them. For example, it prioritizes tasks with approaching deadlines. The task allocation unit also combines task priority and urgency to comprehensively manage tasks. For example, it assigns tasks with high importance and urgency as the top priority. This enables efficient task management that takes into account task priority and urgency.

[0076] The task allocation unit can achieve efficient task management by taking into account the relevance of tasks between different projects. For example, the task allocation unit uses a generation AI to analyze the relevance of tasks between different projects and achieve efficient task management. For example, it allocates related tasks collectively. The task allocation unit also manages tasks by optimally allocating resources between projects. For example, it efficiently allocates resources that are common to multiple projects. The task allocation unit also manages tasks by taking into account the dependency of tasks between different projects. For example, if a task for one project cannot start until a task for the next project is completed, the task is assigned taking into account that dependency. This enables efficient task management that takes into account the relevance of tasks between different projects.

[0077] The task allocation unit monitors the progress of tasks in real time and can reallocate tasks as necessary. For example, the generation AI of the task allocation unit monitors the progress of tasks in real time and reallocates tasks as necessary. For example, it reallocates tasks that are behind schedule to other participants. The task allocation unit also reallocates resources based on the progress of tasks. For example, it allocates additional resources to tasks that are behind schedule. The task allocation unit also comprehensively monitors the progress of tasks and achieves efficient task management. For example, it monitors the overall progress in real time and reallocates tasks or reallocates resources as necessary. This makes it possible to monitor the progress of tasks in real time and reallocate tasks as necessary.

[0078] The task allocation unit uses the emotion estimation function to analyze the emotions of participants and allocate emotionally positive tasks, thereby improving motivation. The task allocation unit, for example, uses the emotion estimation function to analyze the emotions of participants in real time and allocate positive tasks. For example, it prioritizes allocation of tasks that participants are interested in. The task allocation unit also allocates tasks based on the emotional state of participants. For example, if a participant is feeling stressed, it allocates a task that is less burdensome. The task allocation unit also uses the emotion estimation function to comprehensively analyze the emotions of participants and allocate tasks that improve motivation. For example, it prioritizes allocation of tasks that give participants a sense of accomplishment. In this way, the motivation of participants can be improved by allocating emotionally positive tasks.

[0079] The meeting progress monitoring unit can refer to past meeting data and propose the optimal way to proceed. In the meeting progress monitoring unit, for example, a generation AI refers to past meeting data and proposes the optimal way to proceed. For example, the current meeting is conducted based on the way past successful meetings were conducted. The meeting progress monitoring unit also analyzes past meeting data to propose a way to proceed. For example, the optimal way to proceed is proposed based on the flow of discussion in past meetings and the reactions of participants. The meeting progress monitoring unit also comprehensively analyzes past meeting data and the current meeting situation to propose the optimal way to proceed. For example, the progress of the current discussion is evaluated based on past meeting data and an appropriate way to proceed is proposed. In this way, the optimal way to proceed can be proposed by referring to past meeting data.

[0080] The meeting progress monitoring unit can propose appropriate agenda items by taking into account the expertise and roles of participants. For example, the generative AI analyzes the expertise of participants and proposes appropriate agenda items based on that knowledge. For example, if a technical expert is participating, it will prioritize proposing technical agenda items. The meeting progress monitoring unit also proposes agenda items by taking into account the roles of participants. For example, if a project manager is participating, it will propose agenda items related to the progress of the project. The meeting progress monitoring unit also proposes comprehensive agenda items by combining the expertise and roles of participants. For example, for a participant who is both a technical expert and a project manager, it will propose technical agenda items and agenda items related to the progress of the project. This makes it possible to propose appropriate agenda items by taking into account the expertise and roles of participants.

[0081] The meeting progress monitoring unit can refer to best practices from different industries and fields and propose the optimal way to proceed. For example, the generation AI can refer to best practices from different industries and fields and propose the optimal way to proceed. For example, it can propose a way to proceed with a meeting based on best practices from the IT industry. The meeting progress monitoring unit can also propose a way to proceed based on success stories from different industries and fields. For example, it can propose an efficient way to advance discussions based on success stories from the manufacturing industry. The meeting progress monitoring unit can also propose a comprehensive way to proceed by combining best practices and success stories from different industries and fields. For example, it can propose the optimal way to proceed based on best practices from the IT industry and success stories from the manufacturing industry. This makes it possible to propose the optimal way to proceed by referring to best practices from different industries and fields.

[0082] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0083] The meeting progress monitoring unit can use the emotion estimation function to analyze the emotions of the participants and adjust the meeting progress method so that the discussion continues to be emotionally positive. The meeting progress monitoring unit, for example, uses the emotion estimation function to analyze the emotions of the participants in real time and adjust the meeting progress method so that the discussion continues to be emotionally positive. For example, the meeting progress monitoring unit changes the agenda at an appropriate time so that the participants can speak in a relaxed manner. The meeting progress monitoring unit also adjusts the meeting progress method based on the emotional state of the participants. For example, if a participant is feeling stressed, the meeting progress monitoring unit suggests a meeting progress method that will help them relax. The meeting progress monitoring unit also uses the emotion estimation function to comprehensively analyze the emotions of the participants and adjust the meeting progress method so that the discussion continues to be emotionally positive. For example, the meeting progress monitoring unit prioritizes proposing agenda items that interest the participants to stimulate the discussion. In this way, the meeting progress monitoring unit can adjust the meeting progress method so that the discussion continues to be emotionally positive.

[0084] The utterance analysis unit can analyze the speaker's emotions in real time and provide emotionally positive feedback. The utterance analysis unit, for example, uses an emotion estimation function to analyze the speaker's emotions in real time and provide positive feedback. For example, if the speaker is feeling anxious, it provides words of encouragement. The utterance analysis unit also provides feedback based on the speaker's emotional state. For example, if the speaker is confident, it provides feedback that further increases that confidence. The utterance analysis unit also uses the emotion estimation function to comprehensively analyze the speaker's emotions and provide positive feedback. For example, if the speaker is excited, it provides feedback that calms the excitement. In this way, by providing emotionally positive feedback, it is possible to stimulate discussions.

[0085] The utterance analysis unit can analyze the tone and speed of the speaker's voice to estimate their emotional state and reflect this in the feedback. For example, the generation AI in the utterance analysis unit analyzes the tone of the speaker's voice to estimate their emotional state. For example, if the voice tone is high, it may determine that the speaker is excited and provide calm feedback. The utterance analysis unit also analyzes the speed of the speaker's voice to estimate their emotional state. For example, if the speaker speaks at a fast speed, it may determine that the speaker is nervous and provide feedback to relax. The utterance analysis unit also combines the tone and speed of the voice to comprehensively analyze the emotional state. For example, if the voice tone is high and the speed is fast, it may determine that the speaker is excited and provide calm feedback. This makes it possible to provide feedback that takes the speaker's emotional state into consideration.

[0086] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0087] The time monitoring unit can analyze the speaker's emotions and adjust the speech time so that emotionally positive speech continues. The time monitoring unit, for example, uses an emotion estimation function to analyze the speaker's emotions and adjust the speech time so that positive speech continues. For example, the time monitoring unit extends the speech time at an appropriate time so that the speaker can speak with confidence. The time monitoring unit also adjusts the speech time based on the speaker's emotional state. For example, if the speaker is feeling stressed, it provides speech time that allows the speaker to relax. The time monitoring unit also uses the emotion estimation function to comprehensively analyze the speaker's emotions and adjust the speech time so that positive speech continues. For example, if the speaker is excited, it provides speech time that calms the excitement. In this way, the speech time can be adjusted so that emotionally positive speech continues.

[0088] The summarization unit can use the emotion estimation function to analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. The summarization unit, for example, uses the emotion estimation function to analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. For example, the summarization unit extracts points that the speaker wants to emphasize from emotion data and reflects them in the summary. The summarization unit also provides a summary based on the speaker's emotional state. For example, if the speaker is excited, the summarization unit provides a summary that reflects that excitement. The summarization unit also uses the emotion estimation function to comprehensively analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. For example, the summarization unit extracts points that the speaker wants to emphasize emotionally and provides a summary that emphasizes those points. This makes it possible to provide a summary that emphasizes emotionally important points.

[0089] The task allocation unit uses the emotion estimation function to analyze the emotions of participants and allocate emotionally positive tasks, thereby improving motivation. The task allocation unit, for example, uses the emotion estimation function to analyze the emotions of participants in real time and allocate positive tasks. For example, it prioritizes allocation of tasks that participants are interested in. The task allocation unit also allocates tasks based on the emotional state of participants. For example, if a participant is feeling stressed, it allocates a task that is less burdensome. The task allocation unit also uses the emotion estimation function to comprehensively analyze the emotions of participants and allocate tasks that improve motivation. For example, it prioritizes allocation of tasks that give participants a sense of accomplishment. In this way, the motivation of participants can be improved by allocating emotionally positive tasks.

[0090] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0091] The utterance analysis unit takes into account the speaker's past utterance history and expertise, allowing it to provide more accurate evaluations. For example, when the generation AI analyzes the content of a utterance, the utterance analysis unit refers to the speaker's past utterance history and evaluates the relevance between past utterances and the current utterance. For example, it evaluates the consistency and depth of the current utterance based on past utterances on a similar topic. The utterance analysis unit also analyzes the content of a utterance taking into account the speaker's expertise. For example, the generation AI retrieves the speaker's expertise from a database and evaluates the content of the utterance based on that knowledge. This improves the accuracy of the evaluation of the content of the utterance.

[0092] The utterance analysis unit can analyze the tone and speed of the speaker's voice to estimate their emotional state and reflect this in the feedback. For example, the generation AI in the utterance analysis unit analyzes the tone of the speaker's voice to estimate their emotional state. For example, if the voice tone is high, it may determine that the speaker is excited and provide calm feedback. The utterance analysis unit also analyzes the speed of the speaker's voice to estimate their emotional state. For example, if the speaker speaks at a fast speed, it may determine that the speaker is nervous and provide feedback to relax. The utterance analysis unit also combines the tone and speed of the voice to comprehensively analyze the emotional state. For example, if the voice tone is high and the speed is fast, it may determine that the speaker is excited and provide calm feedback. This makes it possible to provide feedback that takes the speaker's emotional state into consideration.

[0093] The utterance analysis unit can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the generation AI can visualize the content of utterances and provide visually easy-to-understand feedback. For example, the utterance analysis unit can convert the content of utterances into a graph or chart and display it visually. The utterance analysis unit can also provide feedback by diagramming the content of utterances. For example, the utterance analysis unit can convert the content of utterances into a flowchart or mind map and display it visually. When visualizing the content of utterances, the utterance analysis unit can take into consideration visually easy-to-understand designs and colors. For example, the generation AI can visualize the content of utterances using visually easy-to-understand designs and colors. This makes it possible to provide visually easy-to-understand feedback.

[0094] The time monitoring unit can analyze the speaker's emotions and adjust the speech time so that emotionally positive speech continues. The time monitoring unit, for example, uses an emotion estimation function to analyze the speaker's emotions and adjust the speech time so that positive speech continues. For example, the time monitoring unit extends the speech time at an appropriate time so that the speaker can speak with confidence. The time monitoring unit also adjusts the speech time based on the speaker's emotional state. For example, if the speaker is feeling stressed, it provides speech time that allows the speaker to relax. The time monitoring unit also uses the emotion estimation function to comprehensively analyze the speaker's emotions and adjust the speech time so that positive speech continues. For example, if the speaker is excited, it provides speech time that calms the excitement. In this way, the speech time can be adjusted so that emotionally positive speech continues.

[0095] The summarization unit can use the emotion estimation function to analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. The summarization unit, for example, uses the emotion estimation function to analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. For example, the summarization unit extracts points that the speaker wants to emphasize from emotion data and reflects them in the summary. The summarization unit also provides a summary based on the speaker's emotional state. For example, if the speaker is excited, the summarization unit provides a summary that reflects that excitement. The summarization unit also uses the emotion estimation function to comprehensively analyze the speaker's emotions and provide a summary that emphasizes emotionally important points. For example, the summarization unit extracts points that the speaker wants to emphasize emotionally and provides a summary that emphasizes those points. This makes it possible to provide a summary that emphasizes emotionally important points.

[0096] The task allocation unit uses the emotion estimation function to analyze the emotions of participants and allocate emotionally positive tasks, thereby improving motivation. The task allocation unit, for example, uses the emotion estimation function to analyze the emotions of participants in real time and allocate positive tasks. For example, it prioritizes allocation of tasks that participants are interested in. The task allocation unit also allocates tasks based on the emotional state of participants. For example, if a participant is feeling stressed, it allocates a task that is less burdensome. The task allocation unit also uses the emotion estimation function to comprehensively analyze the emotions of participants and allocate tasks that improve motivation. For example, it prioritizes allocation of tasks that give participants a sense of accomplishment. In this way, the motivation of participants can be improved by allocating emotionally positive tasks.

[0097] The meeting progress monitoring unit can visualize the progress and provide a visually easy-to-understand progress method. For example, the generation AI in the meeting progress monitoring unit visualizes the progress of the meeting and provides a visually easy-to-understand progress method. For example, the progress is converted into a graph or chart and displayed visually. The meeting progress monitoring unit also provides a progress method by diagramming the progress. For example, the progress is converted into a flowchart or mind map and displayed visually. The meeting progress monitoring unit also takes into consideration visually easy-to-understand designs and colors when visualizing the progress. For example, the generation AI visualizes the progress using visually easy-to-understand designs and colors. This makes it possible to provide a visually easy-to-understand progress method.

[0098] The meeting progress monitoring unit can use the emotion estimation function to analyze the emotions of the participants and adjust the meeting progress method so that the discussion continues to be emotionally positive. The meeting progress monitoring unit, for example, uses the emotion estimation function to analyze the emotions of the participants in real time and adjust the meeting progress method so that the discussion continues to be emotionally positive. For example, the meeting progress monitoring unit changes the agenda at an appropriate time so that the participants can speak in a relaxed manner. The meeting progress monitoring unit also adjusts the meeting progress method based on the emotional state of the participants. For example, if a participant is feeling stressed, the meeting progress monitoring unit suggests a meeting progress method that will help them relax. The meeting progress monitoring unit also uses the emotion estimation function to comprehensively analyze the emotions of the participants and adjust the meeting progress method so that the discussion continues to be emotionally positive. For example, the meeting progress monitoring unit prioritizes proposing agenda items that interest the participants to stimulate the discussion. In this way, the meeting progress monitoring unit can adjust the meeting progress method so that the discussion continues to be emotionally positive.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The meeting support system can further include a health monitoring unit that monitors the health of participants. The health monitoring unit, for example, monitors participants' heart rates and stress levels in real time and provides feedback according to their health status. For example, if a participant's heart rate is high, it can provide advice to relax. The health monitoring unit can also adjust the progress of the meeting based on the participants' health data. For example, it can suggest that a participant with a high stress level take a break. This makes it possible to proceed with the meeting while taking into account the participants' health status.

[0101] The meeting support system can further include a schedule management unit that manages the schedules of participants. The schedule management unit, for example, synchronizes the calendars of each participant and suggests the optimal meeting time. For example, it automatically selects a time slot when everyone can attend. The schedule management unit can also dynamically adjust the schedule according to the progress of the meeting. For example, if a discussion drags on, it will automatically reschedule the next appointment. This enables efficient meeting management that takes into account the schedules of participants.

[0102] The meeting support system can further include an anonymous opinion collection unit that collects participants' opinions anonymously. The anonymous opinion collection unit, for example, provides an anonymous platform where participants can freely post their opinions. For example, by posting opinions anonymously, participants can share content that they would find difficult to speak out about. The anonymous opinion collection unit can also automatically classify the collected opinions and provide them as material for discussion. For example, opinions on the same topic can be grouped and displayed. This can provide an environment where participants can freely share their opinions.

[0103] The meeting support system can further include a recording and playback unit that can record participants' comments and play them back later. The recording and playback unit, for example, can automatically record comments made during a meeting and play them back later. For example, the recording can be played back to reconfirm important comments. The recording and playback unit can also convert recorded data into text and save it in a searchable format. For example, it can search for and play back comments containing specific keywords. This provides an environment in which the contents of the meeting can be reviewed later.

[0104] The meeting support system can further include a translation unit that translates participants' comments in real time. The translation unit, for example, translates comments in different languages ​​in real time, enabling smooth communication even in international meetings. For example, it can translate comments in English into Japanese and provide that content to other participants. The translation unit can also refer to a technical dictionary to improve the accuracy of technical terminology translations. For example, it can refer to a dictionary of technical terms and industry terminology to provide accurate translations. This enables smooth communication even between participants who speak different languages.

[0105] The utterance analysis unit can estimate the user's emotions and adjust the tone of the utterance content based on the estimated user emotions. For example, if the user is nervous, it can provide feedback in a relaxing tone. The utterance analysis unit can also adjust the emphasis of the utterance content based on the user's emotional state. For example, if the user is excited, it can provide advice to speak calmly. The utterance analysis unit can also use the emotion estimation function to comprehensively analyze the user's emotions and provide appropriate feedback. For example, if the user is feeling anxious, it can provide feedback that gives a sense of security. This makes it possible to provide feedback that suits the user's emotional state.

[0106] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria for the content of comments based on the estimated user emotions. For example, if the user is confident, the evaluation can reflect that confidence. The evaluation unit can also adjust the evaluation feedback based on the user's emotional state. For example, if the user is feeling stressed, the evaluation unit can provide words of encouragement. The evaluation unit can also use the emotion estimation function to comprehensively analyze the user's emotions and provide an appropriate evaluation. For example, if the user is excited, the evaluation unit can provide feedback to calm the user down. This makes it possible to provide an evaluation that corresponds to the user's emotional state.

[0107] The time monitoring unit can estimate the user's emotions and adjust the speech time based on the estimated user emotions. For example, if the user is speaking with confidence, the speech time is extended. The time monitoring unit can also adjust the speech time based on the user's emotional state. For example, if the user is feeling stressed, the time monitoring unit provides a speech time that allows the user to relax. The time monitoring unit also uses the emotion estimation function to comprehensively analyze the user's emotions and provide an appropriate speech time. For example, if the user is excited, the time monitoring unit provides a speech time that will calm the user down. This makes it possible to adjust the speech time according to the user's emotional state.

[0108] The summarization unit can estimate the user's emotions and adjust the summary content based on the estimated user emotions. For example, it can extract points that the user wants to emphasize from the emotion data and reflect them in the summary. The summarization unit can also adjust the summary content based on the user's emotional state. For example, if the user is excited, it can provide a summary that reflects that excitement. The summarization unit can also use the emotion estimation function to comprehensively analyze the user's emotions and provide an appropriate summary. For example, if the user is feeling anxious, it can provide a summary that gives a sense of security. This makes it possible to provide a summary that suits the user's emotional state.

[0109] The task allocation unit can estimate the user's emotions and adjust task allocation based on the estimated user's emotions. For example, it prioritizes the allocation of tasks that interest the user. The task allocation unit can also allocate tasks based on the user's emotional state. For example, if the user is feeling stressed, it assigns a task that is less burdensome. The task allocation unit also uses an emotion estimation function to comprehensively analyze the user's emotions and assign appropriate tasks. For example, it prioritizes the allocation of tasks that give the user a sense of accomplishment. This makes it possible to allocate tasks according to the user's emotional state.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The utterance analysis unit analyzes the content of the utterance. For example, the generation AI uses voice recognition technology to convert the utterance content into text data and analyzes that content. The utterance analysis unit can also use text analysis technology to analyze the meaning of the utterance content. Furthermore, the analysis can take into account the speaker's past utterance history and expertise. Step 2: The evaluation unit evaluates the utterances analyzed by the utterance analysis unit. For example, the generation AI evaluates the constructiveness and importance of the utterances and provides feedback. It can also take into account the speaker's expertise and past utterance history when making an evaluation. Step 3: The time monitoring unit monitors the speaking time based on the speech content evaluated by the evaluation unit. For example, the generation AI measures each participant's speaking time in real time and distributes it evenly. It can also adjust speaking time taking into account the importance of the speech content. Step 4: The summarization unit summarizes the speech monitored by the time monitoring unit. For example, the generation AI can extract key points from the speech and create a summary. It can also refer to past meeting records and related documents to create a summary. Step 5: The task assigner assigns tasks based on the summary. For example, the generative AI can automatically list the tasks decided during the meeting and assign them to the appropriate person. It can also assign tasks taking into account each participant's skill set and past performance.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0114] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] 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.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0122] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] 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.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] 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.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0140] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] 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.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0152] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0153] 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.

[0154] 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.

[0155] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0156] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0157] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0158] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0159] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0160] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0161] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0162] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0163] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0164] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0165] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0166] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0167] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0168] 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.

[0169] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0170] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0171] 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.

[0172] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0173] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0174] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0175] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0176] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0177] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0178] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0179] 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 speech analysis unit that analyzes speech content; an evaluation unit that evaluates the content of the utterances analyzed by the utterance analysis unit; a time monitoring unit that monitors speech time based on the speech content evaluated by the evaluation unit; a summarizing unit that summarizes the speech content monitored by the time monitoring unit; a task allocation unit that allocates tasks based on the content summarized by the summarization unit; A system characterized by:

2. The utterance analysis unit Analyzes the speaker's tone and speed of voice to estimate their emotional state and reflect it in feedback 2. The system of claim 1.

3. The time monitoring unit Dynamically adjust the appropriate speaking time, taking into account the speaker's position and expertise 2. The system of claim 1.

4. The summary section Referencing past meeting notes and related documents to provide a more accurate summary 2. The system of claim 1.

5. The task allocation unit Select the best person to work with, taking into account each participant's skill set and past performance 2. The system of claim 1.

Images