System

Abstract

An object of a system according to an embodiment is to analyze statements during a meeting in real time and generate appropriate advice and suggestions.SOLUTION: A system according to an embodiment includes a voice recognizer, a natural language processor, and an advice generator. The speech recognition unit recognizes speech during a conference in real time. The natural language processor analyzes the speech recognized by the voice recognizer. The advice generation unit generates advice or a proposal on the basis of the statement content analyzed by the natural language processing 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 make it difficult to provide advice or suggestions in real time during a meeting, and there is room for improvement in terms of improving the quality and effectiveness of meetings.

[0005] The system according to the embodiment aims to analyze comments made during a meeting in real time and generate appropriate advice and suggestions. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, a natural language processing unit, and an advice generation unit. The speech recognition unit recognizes utterances made during a meeting in real time. The natural language processing unit analyzes the utterances recognized by the speech recognition unit. The advice generation unit generates advice or suggestions based on the utterances analyzed by the natural language processing unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze comments made during a meeting in real time and generate appropriate advice and suggestions. [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 non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a 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 moderation support system according to an embodiment of the present invention utilizes generative AI to improve the progress of meetings and the quality of discussions. This system integrates single-channel speaker automatic speech recognition, natural language processing AI, and a task management tool to analyze the progress of meetings and the content of comments in real time and provide appropriate advice and suggestions. This enables the moderation support system to improve the progress of meetings and the quality of discussions.

[0029] A moderation support system according to an embodiment includes a speech recognition unit, a natural language processing unit, and an advice generation unit. The speech recognition unit recognizes utterances made during a meeting in real time. For example, the speech recognition unit converts the utterances made during the meeting into text data. The speech recognition unit can also analyze the tone and speed of the speaker's voice to estimate the speaker's emotional state. The natural language processing unit analyzes the utterances recognized by the speech recognition unit. For example, the natural language processing unit analyzes the content of the utterances to identify important points and topics requiring follow-up. The natural language processing unit can also analyze the context of the utterances and automatically refer to related past meeting data. The advice generation unit generates advice or suggestions based on the utterance content analyzed by the natural language processing unit. For example, the advice generation unit generates advice such as, "Why don't you ask for more specific opinions on this topic?" The advice generation unit can also generate advice based on the speaker's emotions using an emotion estimation function. This enables the moderation support system according to an embodiment to improve the progress of meetings and the quality of discussions. For example, generative AI can analyze the progress of a meeting and the content of comments, and provide appropriate advice and suggestions, improving the efficiency of the meeting and making it easier for the opinions of all participants to be reflected.

[0030] The speech recognition unit can analyze background sounds of speech content and record environmental information of the conference. The speech recognition unit, for example, builds a system that analyzes background sounds of speech content and records environmental information of the conference. For example, if the noise level is high, it determines that the progress of the conference is being hindered. This allows the environmental information of the conference to be grasped and used to help the progress of the conference.

[0031] The speech recognition unit translates speech content in real time, making it possible to accommodate participants who speak different languages. The speech recognition unit, for example, builds a system that translates speech content in real time and accommodates participants who speak different languages. For example, speech in English can be instantly translated into Japanese. This makes it possible to accommodate participants who speak different languages.

[0032] The speech recognition unit can summarize what is said and automatically generate minutes after the meeting ends. The speech recognition unit, for example, can build a system that summarizes what is said and automatically generates minutes after the meeting ends. For example, it can extract important points and create concise minutes. This makes it possible to automatically generate minutes after the meeting ends.

[0033] The natural language processing unit can analyze the context of the utterances and automatically refer to related past conference data. The natural language processing unit, for example, builds a system that analyzes the context of the utterances and automatically refers to related past conference data. For example, it automatically displays past conference data on the same topic. This allows referring to past conference data to be useful in progressing the conference.

[0034] The natural language processing unit can extract keywords from speech content and automatically search for related external data. The natural language processing unit, for example, builds a system that extracts keywords from speech content and automatically searches for related external data. For example, it can automatically display industry news and market data. This makes it possible to search for external data and use it to help progress the meeting.

[0035] The natural language processing unit can visualize the content of speech and display it as an infographic. The natural language processing unit, for example, builds a system that visualizes the content of speech and displays it as an infographic. For example, the content of speech is visually displayed in graphs or charts. This makes it possible to visualize the content of speech and help the meeting proceed.

[0036] The natural language processing unit can store the content of speeches on the cloud and analyze them in cooperation with other conferences. The natural language processing unit, for example, builds a system that stores the content of speeches on the cloud and analyzes them in cooperation with other conferences. For example, it integrates and analyzes data from multiple conferences. This allows the content of speeches to be stored on the cloud and analyzed in cooperation with other conferences, which can be useful for progressing the conference.

[0037] The advice generation unit can refer to past success cases when generating advice or proposals and make optimal proposals. The advice generation unit, for example, builds a system that refers to past success cases when generating advice or proposals and makes optimal proposals. For example, successful proposals are automatically displayed based on past meeting data. This allows optimal proposals to be made by referring to past success cases.

[0038] The advice generation unit can customize the content of advice or suggestions according to the expertise or position of the participant. The advice generation unit, for example, builds a system that customizes the content of advice or suggestions according to the expertise or position of the participant. For example, detailed technical suggestions are made to participants with technical knowledge. In this way, customizing advice or suggestions according to the expertise or position of the participant can be useful in progressing the meeting.

[0039] The advice generation unit can present advice or suggestions as visual notes or mind maps. The advice generation unit, for example, builds a system that presents advice or suggestions as visual notes. For example, important points are indicated with diagrams or icons. In this way, presenting advice or suggestions as visual notes or mind maps can be useful for progressing a meeting.

[0040] A task management tool can automatically track the progress of tasks and report it during a meeting. For example, a task management tool can build a system that automatically tracks the progress of tasks registered in the task management tool and reports it during a meeting. For example, the completion status and progress rate of tasks can be displayed in real time. This allows the task progress to be automatically tracked and reported during a meeting, which can be useful for the progress of the meeting.

[0041] The task management tool can automatically adjust the priority of tasks based on the progress of the meeting or the content of comments. The task management tool builds a system that automatically adjusts the priority of tasks based on the progress of the meeting or the content of comments. For example, tasks related to important agenda items are processed first. This can help the meeting proceed by automatically adjusting the priority of tasks based on the progress of the meeting or the content of comments.

[0042] Task management tools can be linked with calendar apps to automatically set task deadlines. For example, task management tools can be linked with calendar apps to build a system that automatically sets task deadlines. For example, task deadlines can be set based on meeting schedules. This automatically setting task deadlines can help with meeting progress.

[0043] Task management tools can be linked with project management tools to share task progress across the entire project. For example, task management tools can link with project management tools to build a system that shares task progress across the entire project. For example, task progress can be displayed in real time. This allows task progress to be shared across the entire project, which can be useful for advancing meetings.

[0044] A system will be built that analyzes what the moderator says and allows the generative AI to provide complementary information. For example, data and materials related to what was said will be automatically displayed. This will allow the generative AI to analyze what the moderator says and provide complementary information, which will be useful for the progress of the meeting.

[0045] It is possible to monitor the moderator's progress in real time and provide advice at the appropriate time. We will build a system that monitors the moderator's progress in real time and provides advice at the appropriate time. For example, it will analyze the progress of an agenda and suggest the next step. This will allow the moderator's progress to be monitored in real time and advice to be provided at the appropriate time, which will be useful for the progress of the meeting.

[0046] It is possible to translate what the moderator says in real time and accommodate participants who speak different languages. We are building a system that translates what the moderator says in real time and accommodates participants who speak different languages. For example, something said in English can be instantly translated into Japanese. This will help the meeting progress by translating what the moderator says in real time and accommodating participants who speak different languages.

[0047] The moderator's progress can be visualized and displayed as an infographic. A system can be built to visualize the moderator's progress and display it as an infographic. For example, the progress of an agenda item can be visually displayed in graphs and charts. This allows the moderator's progress to be visualized and displayed as an infographic, which can be useful for advancing a meeting.

[0048] The advice providing unit with a broad perspective can analyze past meeting data and provide advice based on long-term trends. The advice providing unit with a broad perspective, for example, builds a system that analyzes past meeting data and provides advice based on long-term trends. For example, it proposes future agenda items based on past data. In this way, analyzing past meeting data and providing advice based on long-term trends can be useful for progressing meetings.

[0049] The advice providing unit with a broad perspective can refer to external data and provide advice based on the latest information. The advice providing unit with a broad perspective, for example, builds a system that refers to external data and provides advice based on the latest information. For example, industry news and market data are automatically collected and displayed during a meeting. This makes it possible to refer to external data and provide advice based on the latest information, which can be useful for progressing the meeting.

[0050] The advice providing unit with a broad perspective can visualize advice and display it as an infographic. The advice providing unit with a broad perspective, for example, builds a system that visualizes advice and displays it as an infographic. For example, the advice content is visually displayed in graphs or charts. In this way, visualizing advice and displaying it as an infographic can be useful in progressing a meeting.

[0051] The advice providing unit with a broad perspective can display advice in cooperation with other conference tools. The advice providing unit with a broad perspective, for example, builds a system that displays advice in cooperation with other conference tools. For example, the advice is displayed directly on a video conference system. In this way, by displaying advice in cooperation with other conference tools, it can be useful for progressing the conference.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The moderation support system can further include a gesture recognition unit that analyzes the speaker's gestures. For example, the gesture recognition unit captures the speaker's hand movements and facial expressions with a camera and analyzes them in real time. This allows the system to understand the speaker's non-verbal communication and use this information to help advance the meeting. For example, if a speaker raises their hand, the system can estimate the speaker's intention and notify the moderator. In addition, if the speaker looks confused, the system can suggest appropriate follow-up measures.

[0054] The moderation support system can further include a concentration measurement unit that measures the concentration level of participants. For example, the concentration measurement unit captures participants' gazes and postures with a camera and analyzes them in real time. This allows the system to grasp the participants' concentration levels and use this information to help progress the meeting. For example, if a participant looks away from the screen, the system can alert the moderator. It can also suggest a break if a participant remains in the same position for a long period of time.

[0055] The moderation support system can further include a progress visualization unit that visualizes the progress of a meeting. The progress visualization unit displays the progress of the meeting in a timeline format, for example. This allows all participants to understand the progress of the meeting at a glance. For example, visually displaying the current agenda item and the next agenda item can help the meeting flow smoothly. Time management can also be supported by displaying the remaining speaking time.

[0056] The moderation support system can further include a speech frequency analysis unit that analyzes the frequency of speech of participants. The speech frequency analysis unit, for example, analyzes the number of times each participant speaks and the duration of their speech in real time. This allows the moderator to be notified when a particular participant is speaking too much or, conversely, when a particular participant is not speaking enough. For example, it can make suggestions to participants who speak little to encourage them to speak more. It can also suggest that participants who speak a lot should refrain from speaking.

[0057] The moderation support system may further include an external data collection unit that automatically collects external data related to the meeting agenda. The external data collection unit may, for example, automatically search news articles and academic papers on the Internet to provide information related to the meeting agenda. This makes it possible to provide reference materials in real time to deepen the meeting discussion. For example, displaying the latest research results related to the agenda can improve the quality of the discussion. Furthermore, providing related statistical data can also help advance the discussion in concrete terms.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The speech recognition unit recognizes what is said during the meeting in real time. For example, the speech recognition unit converts what is said during the meeting into text data. The speech recognition unit can also analyze the tone and speed of the speaker's voice to estimate their emotional state. Step 2: The natural language processor analyzes the utterances recognized by the speech recognition unit. For example, the natural language processor analyzes the utterances and identifies important points and topics that require follow-up. The natural language processor can also analyze the context of the utterances and automatically reference related past meeting data. Step 3: The advice generation unit generates advice or suggestions based on the utterance content analyzed by the natural language processing unit. For example, the advice generation unit generates advice such as, "Why don't you ask for more specific opinions on this topic?" The advice generation unit can also use an emotion estimation function to generate advice based on the speaker's emotions.

[0060] (Example 2) A moderation support system according to an embodiment of the present invention utilizes generative AI to improve the progress of meetings and the quality of discussions. This system integrates single-channel speaker automatic speech recognition, natural language processing AI, and a task management tool to analyze the progress of meetings and the content of comments in real time and provide appropriate advice and suggestions. This enables the moderation support system to improve the progress of meetings and the quality of discussions.

[0061] A moderation support system according to an embodiment includes a speech recognition unit, a natural language processing unit, and an advice generation unit. The speech recognition unit recognizes utterances made during a meeting in real time. For example, the speech recognition unit converts the utterances made during the meeting into text data. The speech recognition unit can also analyze the tone and speed of the speaker's voice to estimate the speaker's emotional state. The natural language processing unit analyzes the utterances recognized by the speech recognition unit. For example, the natural language processing unit analyzes the content of the utterances to identify important points and topics requiring follow-up. The natural language processing unit can also analyze the context of the utterances and automatically refer to related past meeting data. The advice generation unit generates advice or suggestions based on the utterance content analyzed by the natural language processing unit. For example, the advice generation unit generates advice such as, "Why don't you ask for more specific opinions on this topic?" The advice generation unit can also generate advice based on the speaker's emotions using an emotion estimation function. This enables the moderation support system according to an embodiment to improve the progress of meetings and the quality of discussions. For example, generative AI can analyze the progress of a meeting and the content of comments, and provide appropriate advice and suggestions, improving the efficiency of the meeting and making it easier for the opinions of all participants to be reflected.

[0062] The speech recognition unit can analyze the tone or speed of a speaker's voice and estimate and record their emotional state. The speech recognition unit, for example, analyzes the tone and speed of a speaker's voice in real time to build a system that estimates their emotional state. For example, it can estimate whether the speaker is nervous or relaxed based on the pitch of their voice and the speed at which they speak. This allows the speaker's emotional state to be understood and can be used to help progress the meeting.

[0063] The speech recognition unit can analyze background sounds of speech content and record environmental information of the conference. The speech recognition unit, for example, builds a system that analyzes background sounds of speech content and records environmental information of the conference. For example, if the noise level is high, it determines that the progress of the conference is being hindered. This allows the environmental information of the conference to be grasped and used to help the progress of the conference.

[0064] The speech recognition unit can use the emotion estimation function to estimate the speaker's emotion in real time and record changes in emotion. For example, the speech recognition unit uses the emotion estimation function to build a system that estimates the speaker's emotion in real time and records changes in emotion. For example, it records changes in the speaker's emotion every time they change. This makes it possible to understand changes in the speaker's emotion and use this information to help progress the meeting.

[0065] The speech recognition unit translates speech content in real time, making it possible to accommodate participants who speak different languages. The speech recognition unit, for example, builds a system that translates speech content in real time and accommodates participants who speak different languages. For example, speech in English can be instantly translated into Japanese. This makes it possible to accommodate participants who speak different languages.

[0066] The speech recognition unit can summarize what is said and automatically generate minutes after the meeting ends. The speech recognition unit, for example, can build a system that summarizes what is said and automatically generates minutes after the meeting ends. For example, it can extract important points and create concise minutes. This makes it possible to automatically generate minutes after the meeting ends.

[0067] The speech recognition unit can use the emotion estimation function to provide feedback based on the speaker's emotion in real time. The speech recognition unit, for example, uses the emotion estimation function to build a system that provides feedback based on the speaker's emotion in real time. For example, if the speaker is nervous, advice to relax is given. This makes it possible to provide feedback based on the speaker's emotion in real time.

[0068] The natural language processing unit can analyze the context of the utterances and automatically refer to related past conference data. The natural language processing unit, for example, builds a system that analyzes the context of the utterances and automatically refers to related past conference data. For example, it automatically displays past conference data on the same topic. This allows referring to past conference data to be useful in progressing the conference.

[0069] The natural language processing unit can extract keywords from speech content and automatically search for related external data. The natural language processing unit, for example, builds a system that extracts keywords from speech content and automatically searches for related external data. For example, it can automatically display industry news and market data. This makes it possible to search for external data and use it to help progress the meeting.

[0070] The natural language processing unit can use the emotion estimation function to analyze the emotional nuances of the speech content and generate advice based on the emotion. For example, the natural language processing unit uses the emotion estimation function to build a system that analyzes the emotional nuances of the speech content and generates advice based on the emotion. For example, if the speaker is feeling anxious, the system can provide reassuring advice. In this way, generating advice based on emotion can be useful for progressing the meeting.

[0071] The natural language processing unit can visualize the content of speech and display it as an infographic. The natural language processing unit, for example, builds a system that visualizes the content of speech and displays it as an infographic. For example, the content of speech is visually displayed in graphs or charts. This makes it possible to visualize the content of speech and help the meeting proceed.

[0072] The natural language processing unit can store the content of speeches on the cloud and analyze them in cooperation with other conferences. The natural language processing unit, for example, builds a system that stores the content of speeches on the cloud and analyzes them in cooperation with other conferences. For example, it integrates and analyzes data from multiple conferences. This allows the content of speeches to be stored on the cloud and analyzed in cooperation with other conferences, which can be useful for progressing the conference.

[0073] The natural language processing unit can use the emotion estimation function to collect participants' emotional reactions to the content of comments and reflect them in the analysis results. The natural language processing unit, for example, uses the emotion estimation function to build a system that collects participants' emotional reactions to the content of comments and reflects them in the analysis results. For example, it analyzes participants' facial expressions and voices and calculates an emotion score. In this way, collecting participants' emotional reactions to the content of comments and reflecting them in the analysis results can be useful for progressing the meeting.

[0074] The advice generation unit can refer to past success cases when generating advice or proposals and make optimal proposals. The advice generation unit, for example, builds a system that refers to past success cases when generating advice or proposals and makes optimal proposals. For example, successful proposals are automatically displayed based on past meeting data. This allows optimal proposals to be made by referring to past success cases.

[0075] The advice generation unit can customize the content of advice or suggestions according to the expertise or position of the participant. The advice generation unit, for example, builds a system that customizes the content of advice or suggestions according to the expertise or position of the participant. For example, detailed technical suggestions are made to participants with technical knowledge. In this way, customizing advice or suggestions according to the expertise or position of the participant can be useful in progressing the meeting.

[0076] The advice generation unit can use the emotion estimation function to generate advice or suggestions based on the emotional states of the participants. For example, the advice generation unit uses the emotion estimation function to build a system that generates advice or suggestions based on the emotional states of the participants. For example, if a participant is feeling anxious, the advice generation unit can provide reassuring advice. In this way, generating advice or suggestions based on the emotional states of the participants can be useful in progressing the meeting.

[0077] The advice generation unit can present advice or suggestions as visual notes or mind maps. The advice generation unit, for example, builds a system that presents advice or suggestions as visual notes. For example, important points are indicated with diagrams or icons. In this way, presenting advice or suggestions as visual notes or mind maps can be useful for progressing a meeting.

[0078] The advice generation unit can use the emotion estimation function to monitor participants' emotional reactions to advice or suggestions in real time and reflect the feedback. The advice generation unit, for example, uses the emotion estimation function to build a system that monitors participants' emotional reactions to advice or suggestions in real time. For example, it analyzes participants' facial expressions and voices and calculates an emotion score. This makes it possible to monitor participants' emotional reactions to advice or suggestions in real time and reflect feedback, which can be useful in progressing the meeting.

[0079] A task management tool can automatically track the progress of tasks and report it during a meeting. For example, a task management tool can build a system that automatically tracks the progress of tasks registered in the task management tool and reports it during a meeting. For example, the completion status and progress rate of tasks can be displayed in real time. This allows the task progress to be automatically tracked and reported during a meeting, which can be useful for the progress of the meeting.

[0080] The task management tool can automatically adjust the priority of tasks based on the progress of the meeting or the content of comments. The task management tool builds a system that automatically adjusts the priority of tasks based on the progress of the meeting or the content of comments. For example, tasks related to important agenda items are processed first. This can help the meeting proceed by automatically adjusting the priority of tasks based on the progress of the meeting or the content of comments.

[0081] The task management tool can use the emotion estimation function to analyze participants' emotional reactions to tasks and optimize task allocation. For example, the task management tool uses the emotion estimation function to build a system that analyzes participants' emotional reactions to tasks and optimizes task allocation. For example, tasks are reassigned based on participants' emotion scores. This can be useful for progressing a meeting by analyzing participants' emotional reactions to tasks and optimizing task allocation.

[0082] Task management tools can be linked with calendar apps to automatically set task deadlines. For example, task management tools can be linked with calendar apps to build a system that automatically sets task deadlines. For example, task deadlines can be set based on meeting schedules. This automatically setting task deadlines can help with meeting progress.

[0083] Task management tools can be linked with project management tools to share task progress across the entire project. For example, task management tools can link with project management tools to build a system that shares task progress across the entire project. For example, task progress can be displayed in real time. This allows task progress to be shared across the entire project, which can be useful for advancing meetings.

[0084] The task management tool can use the emotion estimation function to monitor participants' emotional reactions to task progress in real time and reflect feedback. The task management tool, for example, uses the emotion estimation function to build a system that monitors participants' emotional reactions to task progress in real time. For example, the emotion estimation function analyzes participants' facial expressions and voices to calculate an emotion score. This allows participants' emotional reactions to task progress to be monitored in real time and feedback to be reflected, which can be useful for progressing the meeting.

[0085] A system will be built that analyzes what the moderator says and allows the generative AI to provide complementary information. For example, data and materials related to what was said will be automatically displayed. This will allow the generative AI to analyze what the moderator says and provide complementary information, which will be useful for the progress of the meeting.

[0086] It is possible to monitor the moderator's progress in real time and provide advice at the appropriate time. We will build a system that monitors the moderator's progress in real time and provides advice at the appropriate time. For example, it will analyze the progress of an agenda and suggest the next step. This will allow the moderator's progress to be monitored in real time and advice to be provided at the appropriate time, which will be useful for the progress of the meeting.

[0087] It is possible to analyze the emotional state of the moderator and make suggestions to reduce stress. We will build a system that analyzes the emotional state of the moderator and makes suggestions to reduce stress. For example, if the moderator is feeling nervous, it will suggest ways to relax. This will help the meeting proceed by analyzing the emotional state of the moderator and making suggestions to reduce stress.

[0088] It is possible to translate what the moderator says in real time and accommodate participants who speak different languages. We are building a system that translates what the moderator says in real time and accommodates participants who speak different languages. For example, something said in English can be instantly translated into Japanese. This will help the meeting progress by translating what the moderator says in real time and accommodating participants who speak different languages.

[0089] The moderator's progress can be visualized and displayed as an infographic. A system can be built to visualize the moderator's progress and display it as an infographic. For example, the progress of an agenda item can be visually displayed in graphs and charts. This allows the moderator's progress to be visualized and displayed as an infographic, which can be useful for advancing a meeting.

[0090] It is possible to provide feedback based on the moderator's emotional state in real time. We will build a system that provides feedback based on the moderator's emotional state in real time. For example, if the moderator is nervous, advice can be given to them to relax. In this way, providing feedback based on the moderator's emotional state in real time can be useful for progressing the meeting.

[0091] The advice providing unit with a broad perspective can analyze past meeting data and provide advice based on long-term trends. The advice providing unit with a broad perspective, for example, builds a system that analyzes past meeting data and provides advice based on long-term trends. For example, it proposes future agenda items based on past data. In this way, analyzing past meeting data and providing advice based on long-term trends can be useful for progressing meetings.

[0092] The advice providing unit with a broad perspective can refer to external data and provide advice based on the latest information. The advice providing unit with a broad perspective, for example, builds a system that refers to external data and provides advice based on the latest information. For example, industry news and market data are automatically collected and displayed during a meeting. This makes it possible to refer to external data and provide advice based on the latest information, which can be useful for progressing the meeting.

[0093] The advice providing unit with a broad perspective can use the emotion estimation function to analyze the emotional states of participants and provide advice based on their emotions. The advice providing unit with a broad perspective can, for example, use the emotion estimation function to build a system that analyzes the emotional states of participants and provides advice based on their emotions. For example, if a participant is feeling anxious, the system can provide reassuring advice. In this way, analyzing the emotional states of participants and providing advice based on their emotions can be useful in progressing the meeting.

[0094] The advice providing unit with a broad perspective can visualize advice and display it as an infographic. The advice providing unit with a broad perspective, for example, builds a system that visualizes advice and displays it as an infographic. For example, the advice content is visually displayed in graphs or charts. In this way, visualizing advice and displaying it as an infographic can be useful in progressing a meeting.

[0095] The advice providing unit with a broad perspective can display advice in cooperation with other conference tools. The advice providing unit with a broad perspective, for example, builds a system that displays advice in cooperation with other conference tools. For example, the advice is displayed directly on a video conference system. In this way, by displaying advice in cooperation with other conference tools, it can be useful for progressing the conference.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] The moderation support system can further include a gesture recognition unit that analyzes the speaker's gestures. For example, the gesture recognition unit captures the speaker's hand movements and facial expressions with a camera and analyzes them in real time. This allows the system to understand the speaker's non-verbal communication and use this information to help advance the meeting. For example, if a speaker raises their hand, the system can estimate the speaker's intention and notify the moderator. In addition, if the speaker looks confused, the system can suggest appropriate follow-up measures.

[0098] The moderation support system can further include a concentration measurement unit that measures the concentration level of participants. For example, the concentration measurement unit captures participants' gazes and postures with a camera and analyzes them in real time. This allows the system to grasp the participants' concentration levels and use this information to help progress the meeting. For example, if a participant looks away from the screen, the system can alert the moderator. It can also suggest a break if a participant remains in the same position for a long period of time.

[0099] The moderation support system can further include a progress visualization unit that visualizes the progress of a meeting. The progress visualization unit displays the progress of the meeting in a timeline format, for example. This allows all participants to understand the progress of the meeting at a glance. For example, visually displaying the current agenda item and the next agenda item can help the meeting flow smoothly. Time management can also be supported by displaying the remaining speaking time.

[0100] The moderation support system can further include a speech frequency analysis unit that analyzes the frequency of speech of participants. The speech frequency analysis unit, for example, analyzes the number of times each participant speaks and the duration of their speech in real time. This allows the moderator to be notified when a particular participant is speaking too much or, conversely, when a particular participant is not speaking enough. For example, it can make suggestions to participants who speak little to encourage them to speak more. It can also suggest that participants who speak a lot should refrain from speaking.

[0101] The moderation support system may further include an external data collection unit that automatically collects external data related to the meeting agenda. The external data collection unit may, for example, automatically search news articles and academic papers on the Internet to provide information related to the meeting agenda. This makes it possible to provide reference materials in real time to deepen the meeting discussion. For example, displaying the latest research results related to the agenda can improve the quality of the discussion. Furthermore, providing related statistical data can also help advance the discussion in concrete terms.

[0102] The moderation support system may further include an emotion adjustment unit that estimates the emotions of participants and adjusts the progress of the meeting based on the estimated emotions. The emotion adjustment unit, for example, analyzes the facial expressions and tone of voice of participants to estimate their emotional state. This makes it possible to suggest a break if a participant is feeling stressed. For example, if a participant is tired, it can suggest a break to refresh themselves. It can also provide advice to calm down if a participant is excited.

[0103] The moderation support system can further include a speech adjustment unit that estimates the speaker's emotions and adjusts the content of the speech based on the estimated emotions. The speech adjustment unit, for example, analyzes the tone and speed of the speaker's voice to estimate the speaker's emotional state. This makes it possible to give advice to relax if the speaker is nervous. For example, if the speaker is feeling anxious, the unit can give reassuring advice. Also, if the speaker is angry, the unit can give advice to stay calm.

[0104] The moderation support system can further include an agenda adjustment unit that estimates the emotions of participants and adjusts the agenda based on the estimated emotions. The agenda adjustment unit, for example, analyzes the facial expressions and tone of voice of participants to estimate their emotional state. This makes it possible to quickly end an agenda that participants are not interested in. For example, if a participant is bored, the agenda adjustment unit can suggest moving on to the next agenda item. It can also suggest extending an agenda item that participants are interested in.

[0105] The moderation support system may further include a feedback providing unit that estimates the emotions of participants and provides feedback based on the estimated emotions. The feedback providing unit may, for example, analyze the facial expressions and tone of voice of participants to estimate their emotional state. This may allow the system to provide reassuring feedback to participants who are feeling anxious. For example, if a participant is nervous, the system may provide advice to encourage them to relax. Also, if a participant is angry, the system may provide feedback to encourage them to calm down.

[0106] The moderation support system may further include a progress optimization unit that estimates the emotions of participants and optimizes the progress of the meeting based on the estimated emotions. The progress optimization unit may, for example, analyze the facial expressions and tone of voice of participants to estimate their emotional state. This may enable the system to suggest a break if a participant is feeling stressed. For example, the system may suggest a break to refresh a participant if a participant is tired. The system may also provide advice to calm a participant if the participant is excited.

[0107] The processing flow of the second embodiment will be briefly explained below.

[0108] Step 1: The speech recognition unit recognizes what is said during the meeting in real time. For example, the speech recognition unit converts what is said during the meeting into text data. The speech recognition unit can also analyze the tone and speed of the speaker's voice to estimate their emotional state. Step 2: The natural language processor analyzes the utterances recognized by the speech recognition unit. For example, the natural language processor analyzes the utterances and identifies important points and topics that require follow-up. The natural language processor can also analyze the context of the utterances and automatically reference related past meeting data. Step 3: The advice generation unit generates advice or suggestions based on the utterance content analyzed by the natural language processing unit. For example, the advice generation unit generates advice such as, "Why don't you ask for more specific opinions on this topic?" The advice generation unit can also use an emotion estimation function to generate advice based on the speaker's emotions.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0113] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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]

[0176] 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 recognition unit that recognizes statements made during a meeting in real time; a natural language processing unit that analyzes the utterance recognized by the speech recognition unit; an advice generation unit that generates advice or suggestions based on the utterance content analyzed by the natural language processing unit; A system characterized by:

2. The voice recognition unit Translate the speech in real time to accommodate participants with different languages 2. The system of claim 1.

3. The natural language processing unit Analyze the context of the remarks and automatically reference related past meeting data 2. The system of claim 1.

4. The advice generation unit When generating the advice or proposal, the best proposal is made by referring to past success stories.

2. The system of claim 1.

5. Task management tools Analyzing participants' emotional responses to tasks and optimizing the allocation of tasks.

2. The system of claim 1.

6. Analyze the moderator's emotional state and make suggestions to reduce stress 2. The system of claim 1.

7. The advice department offers a wide range of Analyze participants' emotional state and provide emotion-based advice 2. The system of claim 1.

Images