system

Abstract

An object of a system according to an embodiment is to efficiently create minutes of a meeting.SOLUTION: A system according to an embodiment includes an input information acquisition unit, a problem extraction unit, an examination history extraction unit, a conclusion extraction unit, and a material generation unit. The input information acquisition unit acquires voice and moving image data of a conference. The problem extraction unit extracts a problem discussed in the conference from the input information acquired by the input information acquisition unit. The examination history extraction unit extracts an examination history on the basis of the issue extracted by the issue extraction unit. The conclusion extraction unit extracts a conclusion on the basis of the examination history extracted by the examination history extraction unit. The material generation unit generates a ppt or PDF material based on the conclusion extracted by the conclusion extraction 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 techniques have made it difficult and time-consuming to efficiently create meeting minutes.

[0005] The system according to the embodiment aims to efficiently create minutes of a meeting. [Means for solving the problem]

[0006] The system according to the embodiment includes an input information acquisition unit, an issue extraction unit, a study history extraction unit, a conclusion extraction unit, and a material generation unit. The input information acquisition unit acquires audio and video data from the meeting. The issue extraction unit extracts issues discussed in the meeting from the input information acquired by the input information acquisition unit. The study history extraction unit extracts a study history based on the issues extracted by the issue extraction unit. The conclusion extraction unit extracts a conclusion based on the study history extracted by the study history extraction unit. The material generation unit generates ppt or PDF materials based on the conclusion extracted by the conclusion extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently create minutes of a meeting. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. 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) The AI ​​system according to the embodiment of the present invention efficiently reads meeting minutes, and the generation AI automatically extracts the meeting's "issues," "debate history," and "conclusions," and generates them as PPT or PDF documents. This allows the AI ​​system to quickly grasp important meeting information and enable efficient information sharing.

[0029] The AI ​​system according to the embodiment includes an input information acquisition unit, an issue extraction unit, a study history extraction unit, a conclusion extraction unit, and a document generation unit. The input information acquisition unit acquires audio and video data from a meeting. For example, it collects audio data from a meeting using a microphone and stores it digitally. It can also capture video data from a meeting using a camera and store it as video data. Furthermore, the input information acquisition unit can scan images of a whiteboard or handwritten notes used during a meeting and convert them into digital data. For example, it can capture an image of a whiteboard using a high-resolution camera and convert it into text data using image recognition technology. Handwritten notes can be converted into character data using OCR technology. The issue extraction unit extracts issues discussed in a meeting from the input information acquired by the input information acquisition unit. For example, the generation AI converts audio data from a meeting into text using speech recognition technology and extracts issues using natural language processing technology. The study history extraction unit extracts a study history based on the issues extracted by the issue extraction unit. For example, the generation AI analyzes the flow of discussion and the order of statements from text data to extract the discussion history. The conclusion extraction unit extracts a conclusion based on the discussion history extracted by the discussion history extraction unit. For example, the generation AI analyzes final decisions and agreements from text data to extract a conclusion. The document generation unit generates PowerPoint or PDF documents based on the conclusion extracted by the conclusion extraction unit. For example, the generation AI automatically generates PowerPoint slides based on the extracted information, describing the issues, discussion history, and conclusions on each slide. PDF documents are also output in a format that clearly organizes each item. This allows the AI ​​system according to the embodiment to quickly grasp important meeting information and enable efficient information sharing. For example, there is no need to read the entire meeting minutes; participants can review only the important points in PowerPoint or PDF. It also enables members who were unable to attend the meeting to receive concise and easy-to-understand documents.

[0030] The input information acquisition unit can analyze images of whiteboards and handwritten notes used during meetings, as well as audio and video data of meetings, and convert them into text data. For example, the input information acquisition unit captures images of whiteboards used during meetings and converts handwritten characters and drawings into text data using image recognition technology. For example, it automatically extracts agendas and notes written on whiteboards. The input information acquisition unit also scans handwritten notes written by meeting participants and converts them into text data using character recognition technology. For example, it extracts important keywords and phrases from handwritten notes. The input information acquisition unit also analyzes images of whiteboards and handwritten notes used during meetings in real time and generates text data in line with the progress of the meeting. For example, it instantly reflects content added during the meeting. This allows analysis to include handwritten information during meetings.

[0031] The input information acquisition unit analyzes not only the content of speech made by conference participants but also the speaker's facial expressions and gestures, enabling a more accurate understanding of the nuances of speech. For example, the input information acquisition unit captures the facial expressions of speakers during a conference with a camera and analyzes the emotions and nuances of speech using facial expression recognition technology. For example, if a speaker is smiling while speaking, it indicates that the speech is positive. The input information acquisition unit also captures the speaker's gestures using video analysis technology to identify the emphasis and important parts of the speech. For example, a gesture of raising one's hand indicates an emphasized speech. The input information acquisition unit also comprehensively analyzes the speech content and the speaker's facial expressions and gestures, building a system that more accurately grasps the nuances of speech. For example, if a speaker is speaking with a serious expression, it indicates that the speech is important. This allows a more accurate understanding of the nuances of speech.

[0032] The input information acquisition unit can automatically acquire documents and slides shared during a meeting, in addition to audio and video data from the meeting, and use them for analysis. For example, the input information acquisition unit automatically acquires documents and slides shared during a meeting and analyzes their contents using text analysis technology. For example, it extracts important points from shared presentation materials. The input information acquisition unit also acquires documents and slides used during a meeting in real time and analyzes them as the meeting progresses. For example, it instantly analyzes materials added during the meeting. The input information acquisition unit also automatically acquires shared documents and slides and builds a system that analyzes them in an integrated manner with the audio and video data from the meeting. For example, it associates the content of comments with the content of the materials and analyzes them. This makes it possible to analyze materials shared during a meeting as well.

[0033] The input information acquisition unit can automatically translate audio and video data of meetings held in different languages ​​and use it for analysis. For example, the input information acquisition unit automatically translates audio data of meetings held in different languages ​​and converts it into text data. For example, the content of a meeting held in English is translated into Japanese. The input information acquisition unit also automatically translates video data of meetings held in different languages ​​and displays it as subtitles. For example, the content of a meeting held in French is displayed with English subtitles. The input information acquisition unit also analyzes the automatically translated audio and video data and builds a system that makes it possible to understand the content of a meeting in multiple languages. For example, the content of a meeting in different languages ​​is analyzed in an integrated manner. This makes it possible to analyze meetings in different languages.

[0034] The issue extraction unit can automatically search past meeting records and documents related to an issue extracted from meeting audio data and provide supplemental information. For example, the issue extraction unit automatically searches past meeting records for an issue extracted from meeting audio data and provides related information. For example, it searches for records in which the same issue was previously discussed. The issue extraction unit also automatically searches for documents related to the extracted issue and provides them as supplemental information. For example, it searches for past project reports and technical documents. The issue extraction unit also builds a system that automatically searches for related past meeting records and documents based on the issue extraction results and provides them to meeting participants. For example, it provides related materials as links. This makes it possible to provide supplemental information based on past meeting records and documents.

[0035] The issue extraction unit can prioritize extracting issues of high importance by taking into account the speaker's expertise and position. The issue extraction unit, for example, registers the speaker's expertise and position in a database and evaluates the importance of an issue based on that information. For example, it prioritizes extracting issues from speakers who have specialized knowledge. The issue extraction unit also builds a system that evaluates the importance of an issue based on the speaker's position. For example, it extracts comments from senior managers as important issues. The issue extraction unit also develops an algorithm that prioritizes extracting issues of high importance by taking into account the speaker's expertise and position. For example, it weights both expertise and position for evaluation. This makes it possible to extract issues of high importance by taking into account the speaker's expertise and position.

[0036] The issue extraction unit can automatically associate similar issues discussed in different meetings and generate a comprehensive issue list. For example, the issue extraction unit develops an algorithm that automatically associates issues discussed in different meetings and generates a comprehensive issue list. For example, it associates issues that include the same keywords. The issue extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar issues. For example, it uses natural language processing technology to extract similar issues. The issue extraction unit also develops a system that generates a comprehensive issue list based on the automatically associated issues and provides it to meeting participants. For example, it combines related issues into a single list. This makes it possible to associate similar issues discussed in different meetings and generate a comprehensive issue list.

[0037] The issue extraction unit can compare the issue extraction results with issues in different industries or fields to identify similarities and differences. For example, the issue extraction unit builds a system that compares extracted issues with issues in different industries or fields. For example, it compares issues in the technical field with issues in the marketing field. The issue extraction unit also develops an algorithm that registers issues in different industries or fields in a database and compares them with the extracted issues. For example, it automatically analyzes similarities and differences. The issue extraction unit also builds a system that compares the issue extraction results with issues in different industries or fields to identify similarities and differences. For example, it visually compares issues in different industries. This makes it possible to compare issues in different industries or fields and identify similarities and differences.

[0038] When extracting the consideration history, the consideration history extraction unit analyzes the context and order of comments to grasp the details of the consideration history. For example, the consideration history extraction unit analyzes the context and order of comments to develop an algorithm to grasp the consideration history in detail. For example, it analyzes the order and relevance of comments. The consideration history extraction unit also analyzes the context of comments to build a system to grasp the consideration history in detail. For example, it analyzes the background and intention of comments. The consideration history extraction unit also comprehensively analyzes the context and order of comments to develop a system to grasp the consideration history in detail. For example, it visualizes the flow of comments. This makes it possible to analyze the context and order of comments to grasp the details of the consideration history.

[0039] The study history extraction unit can automatically search for related technical literature and patent information based on the study history extraction results and provide supplemental information. The study history extraction unit, for example, builds a system that automatically searches for related technical literature based on the study history extraction results and provides it as supplemental information. For example, it searches a technical paper database. The study history extraction unit also develops an algorithm that automatically searches for patent information related to the extracted study history and provides it as supplemental information. For example, it searches a patent database. The study history extraction unit also builds a system that automatically searches for related technical literature and patent information based on the study history extraction results and provides it to meeting participants. For example, it provides related literature and patents as links. This makes it possible to provide supplemental information based on related technical literature and patent information.

[0040] The consideration history extraction unit can automatically associate the consideration histories discussed in different meetings and generate a comprehensive consideration history list. The consideration history extraction unit, for example, develops an algorithm that automatically associates the consideration histories discussed in different meetings and generates a comprehensive consideration history list. For example, it associates consideration histories on the same topic. The consideration history extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar consideration histories. For example, it uses natural language processing technology to extract similar consideration histories. The consideration history extraction unit also develops a system that generates a comprehensive consideration history list based on the automatically associated consideration histories and provides it to meeting participants. For example, it consolidates related consideration histories into a single list. This makes it possible to associate the consideration histories discussed in different meetings and generate a comprehensive consideration history list.

[0041] The consideration history extraction unit can compare the extracted results of the consideration history with the consideration history of different industries or fields to clarify similarities and differences. For example, the consideration history extraction unit builds a system that compares the extracted consideration history with the consideration history of different industries or fields. For example, it compares the consideration history of the technical field with the consideration history of the marketing field. The consideration history extraction unit also registers the consideration history of different industries or fields in a database and develops an algorithm that compares the extracted consideration history. For example, it automatically analyzes the similarities and differences. The consideration history extraction unit also builds a system that compares the extracted results of the consideration history with the consideration history of different industries or fields to clarify similarities and differences. For example, it visually compares the consideration history of different industries. This makes it possible to compare the consideration history of different industries or fields to clarify similarities and differences.

[0042] When extracting a conclusion, the conclusion extraction unit analyzes the context and order of statements to grasp a more detailed conclusion. The conclusion extraction unit, for example, analyzes the context and order of statements to develop an algorithm to grasp a conclusion in detail. For example, it analyzes the order and relevance of statements. The conclusion extraction unit also analyzes the context of statements to build a system to grasp a conclusion in detail. For example, it analyzes the background and intention of statements. The conclusion extraction unit also develops a system to comprehensively analyze the context and order of statements to grasp a conclusion in detail. For example, it visualizes the flow of statements. This makes it possible to analyze the context and order of statements to grasp a detailed conclusion.

[0043] The conclusion extraction unit can automatically search for related technical literature and patent information based on the conclusion extraction results and provide supplementary information. The conclusion extraction unit, for example, builds a system that automatically searches for related technical literature based on the conclusion extraction results and provides it as supplementary information. For example, it searches a technical paper database. The conclusion extraction unit also develops an algorithm that automatically searches for patent information related to the extracted conclusion and provides it as supplementary information. For example, it searches a patent database. The conclusion extraction unit also builds a system that automatically searches for related technical literature and patent information based on the conclusion extraction results and provides it to conference participants. For example, it provides related literature and patents as links. This makes it possible to provide supplementary information based on related technical literature and patent information.

[0044] The conclusion extraction unit can automatically associate conclusions discussed in different meetings and generate a comprehensive list of conclusions. For example, the conclusion extraction unit develops an algorithm that automatically associates conclusions discussed in different meetings and generates a comprehensive list of conclusions. For example, it associates conclusions on the same topic. The conclusion extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar conclusions. For example, it extracts similar conclusions using natural language processing technology. The conclusion extraction unit also develops a system that generates a comprehensive list of conclusions based on the automatically associated conclusions and provides it to meeting participants. For example, it combines related conclusions into a single list. This makes it possible to associate conclusions discussed in different meetings and generate a comprehensive list of conclusions.

[0045] The conclusion extraction unit can compare the conclusion extraction results with conclusions from different industries or fields to clarify similarities and differences. For example, the conclusion extraction unit builds a system that compares extracted conclusions with conclusions from different industries or fields. For example, it compares conclusions from the technical field with those from the marketing field. The conclusion extraction unit also registers conclusions from different industries or fields in a database and develops an algorithm that compares them with the extracted conclusion. For example, it automatically analyzes similarities and differences. The conclusion extraction unit also builds a system that compares the conclusion extraction results with conclusions from different industries or fields to clarify similarities and differences. For example, it visually compares conclusions from different industries. This makes it possible to compare conclusions from different industries or fields to clarify similarities and differences.

[0046] The document generation unit can automatically generate visually appealing and easy-to-understand PPT and PDF documents based on the extracted information. The document generation unit, for example, builds a system that automatically generates visually appealing PPT slides based on the extracted information. For example, it automatically adjusts the graphic design and layout. The document generation unit also develops an algorithm that automatically generates easy-to-understand PDF documents based on the extracted information. For example, it automatically adjusts the text format and the placement of figures and tables. The document generation unit also builds a system that automatically generates visually appealing and easy-to-understand PPT and PDF documents. For example, it uses templates to provide a consistent design. This makes it possible to automatically generate visually appealing and easy-to-understand documents.

[0047] The data generation unit can automatically create related graphs and charts to provide visual supplementary information when generating data. The data generation unit, for example, builds a system that automatically creates related graphs and charts based on extracted information. For example, it generates bar graphs and pie charts based on data. The data generation unit also develops an algorithm that automatically adds graphs and charts as visual supplementary information when generating data. For example, it generates a line graph that shows data trends. The data generation unit also builds a system that automatically creates related graphs and charts to provide visual supplementary information. For example, it generates a heat map that shows a comparison of data. This makes it possible to automatically create related graphs and charts to provide visual supplementary information.

[0048] The material generation unit can integrate materials from different meetings and automatically generate a comprehensive report. For example, the material generation unit builds a system that integrates materials from different meetings and automatically generates a comprehensive report. For example, it compiles minutes from multiple meetings into a single PDF. The material generation unit also develops an algorithm that automatically integrates materials from different meetings and generates a visually organized report. For example, it creates slides that summarize the important points of each meeting. The material generation unit also builds a system that integrates materials from different meetings and automatically generates a comprehensive report. For example, it adds a section that summarizes the conclusions of each meeting. This makes it possible to integrate materials from different meetings and automatically generate a comprehensive report.

[0049] The document generation unit can support output in different languages ​​when generating documents, enabling information sharing from an international perspective. The document generation unit, for example, builds a system that supports output in different languages ​​when generating documents. For example, it generates documents in multiple languages, such as English, Japanese, and French. The document generation unit also develops algorithms that support output in different languages ​​and enable information sharing from an international perspective. For example, it builds a document generation system that incorporates an automatic translation function. The document generation unit also builds a system that supports output in different languages ​​when generating documents, enabling information sharing from an international perspective. For example, it performs translation that takes into account the technical terms of each language. This makes it possible to support output in different languages ​​and enable information sharing from an international perspective.

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

[0051] The input information acquisition unit can acquire data from digital whiteboards used during meetings in real time and use it for analysis. For example, it can instantly convert what is written on the digital whiteboard into text data and analyze it as the meeting progresses. The input information acquisition unit can also analyze the digital whiteboard data in an integrated manner with other meeting materials to extract related information. This allows analysis to include information from the digital whiteboard during the meeting.

[0052] The input information acquisition unit can analyze not only the content of speech by conference participants, but also the tone and speed of the speaker's voice to evaluate the importance of the speech. For example, speech with a high tone and fast speed is likely to be important. The input information acquisition unit can also build a system that analyzes changes in the speaker's voice in real time to identify important speech. This allows for a more accurate understanding of the nuances of speech.

[0053] The input information acquisition unit can automatically acquire chat messages and emails used during a meeting and use them for analysis. For example, it can analyze chat messages sent during a meeting in real time and extract important information. The input information acquisition unit can also automatically acquire emails sent during a meeting, convert them into text data, and analyze them. This allows analysis of digital communications during a meeting as well.

[0054] The input information acquisition unit can automatically acquire documents and slides used during a meeting, in addition to audio and video data from the meeting, and use them for analysis. For example, it can automatically acquire documents and slides shared during a meeting and analyze their contents using text analysis technology. The input information acquisition unit can also acquire documents and slides used during a meeting in real time and analyze them as the meeting progresses. This allows analysis to include materials shared during the meeting.

[0055] The input information acquisition unit can automatically translate audio and video data from conferences held in different languages ​​and use it for analysis. For example, audio data from conferences held in different languages ​​can be automatically translated and converted into text data. The input information acquisition unit can also automatically translate video data from conferences held in different languages ​​and display it as subtitles. This allows conferences held in different languages ​​to be analyzed.

[0056] The issue extraction unit can automatically search past meeting records and documents related to an issue extracted from the meeting audio data and provide supplementary information. For example, past meeting records can be automatically searched for an issue extracted from the meeting audio data and related information can be provided. The issue extraction unit can also automatically search for documents related to the extracted issue and provide them as supplementary information. This makes it possible to provide supplementary information based on past meeting records and documents.

[0057] The issue extraction unit can prioritize the extraction of issues with high importance, taking into account the speaker's expertise and position. For example, the speaker's expertise and position can be registered in a database, and the importance of an issue can be evaluated based on that information. The issue extraction unit can also build a system that evaluates the importance of an issue based on the speaker's position. This makes it possible to extract issues with high importance, taking into account the speaker's expertise and position.

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

[0059] Step 1: The input information acquisition unit acquires audio and video data from the meeting. For example, recordings of the meeting can be collected using a microphone and saved in digital format. Recorded meeting data can also be captured using a camera and saved as video data. The input information acquisition unit can also scan images of the whiteboard and handwritten notes used during the meeting and convert them into digital data. For example, an image of the whiteboard can be captured using a high-resolution camera and converted into text data using image recognition technology. Handwritten notes can be converted into character data using OCR technology. Step 2: The issue extraction unit extracts the issues discussed in the meeting from the input information acquired by the input information acquisition unit. For example, the generation AI converts the audio data of the meeting into text using speech recognition technology and extracts the issues using natural language processing technology. Step 3: The consideration history extraction unit extracts the consideration history based on the issues extracted by the issue extraction unit. For example, the generation AI analyzes the flow of discussion and the order of comments from text data to extract the consideration history. Step 4: The conclusion extraction unit extracts a conclusion based on the deliberation process extracted by the deliberation process extraction unit. For example, the generation AI analyzes the final decisions and agreements from the text data and extracts a conclusion. Step 5: The document generation unit generates PowerPoint or PDF documents based on the conclusions extracted by the conclusion extraction unit. For example, the generation AI automatically generates PowerPoint slides based on the extracted information, describing the issues, the process of consideration, and the conclusions on each slide. PDF documents are also output in a similar format, with each item clearly organized.

[0060] (Example 2) The AI ​​system according to the embodiment of the present invention efficiently reads meeting minutes, and the generation AI automatically extracts the meeting's "issues," "debate history," and "conclusions," and generates them as PPT or PDF documents. This allows the AI ​​system to quickly grasp important meeting information and enable efficient information sharing.

[0061] The AI ​​system according to the embodiment includes an input information acquisition unit, an issue extraction unit, a study history extraction unit, a conclusion extraction unit, and a document generation unit. The input information acquisition unit acquires audio and video data from a meeting. For example, it collects audio data from a meeting using a microphone and stores it digitally. It can also capture video data from a meeting using a camera and store it as video data. Furthermore, the input information acquisition unit can scan images of a whiteboard or handwritten notes used during a meeting and convert them into digital data. For example, it can capture an image of a whiteboard using a high-resolution camera and convert it into text data using image recognition technology. Handwritten notes can be converted into character data using OCR technology. The issue extraction unit extracts issues discussed in a meeting from the input information acquired by the input information acquisition unit. For example, the generation AI converts audio data from a meeting into text using speech recognition technology and extracts issues using natural language processing technology. The study history extraction unit extracts a study history based on the issues extracted by the issue extraction unit. For example, the generation AI analyzes the flow of discussion and the order of statements from text data to extract the discussion history. The conclusion extraction unit extracts a conclusion based on the discussion history extracted by the discussion history extraction unit. For example, the generation AI analyzes final decisions and agreements from text data to extract a conclusion. The document generation unit generates PowerPoint or PDF documents based on the conclusion extracted by the conclusion extraction unit. For example, the generation AI automatically generates PowerPoint slides based on the extracted information, describing the issues, discussion history, and conclusions on each slide. PDF documents are also output in a format that clearly organizes each item. This allows the AI ​​system according to the embodiment to quickly grasp important meeting information and enable efficient information sharing. For example, there is no need to read the entire meeting minutes; participants can review only the important points in PowerPoint or PDF. It also enables members who were unable to attend the meeting to receive concise and easy-to-understand documents.

[0062] The input information acquisition unit can analyze images of whiteboards and handwritten notes used during meetings, as well as audio and video data of meetings, and convert them into text data. For example, the input information acquisition unit captures images of whiteboards used during meetings and converts handwritten characters and drawings into text data using image recognition technology. For example, it automatically extracts agendas and notes written on whiteboards. The input information acquisition unit also scans handwritten notes written by meeting participants and converts them into text data using character recognition technology. For example, it extracts important keywords and phrases from handwritten notes. The input information acquisition unit also analyzes images of whiteboards and handwritten notes used during meetings in real time and generates text data in line with the progress of the meeting. For example, it instantly reflects content added during the meeting. This allows analysis to include handwritten information during meetings.

[0063] The input information acquisition unit analyzes not only the content of speech made by conference participants but also the speaker's facial expressions and gestures, enabling a more accurate understanding of the nuances of speech. For example, the input information acquisition unit captures the facial expressions of speakers during a conference with a camera and analyzes the emotions and nuances of speech using facial expression recognition technology. For example, if a speaker is smiling while speaking, it indicates that the speech is positive. The input information acquisition unit also captures the speaker's gestures using video analysis technology to identify the emphasis and important parts of the speech. For example, a gesture of raising one's hand indicates an emphasized speech. The input information acquisition unit also comprehensively analyzes the speech content and the speaker's facial expressions and gestures, building a system that more accurately grasps the nuances of speech. For example, if a speaker is speaking with a serious expression, it indicates that the speech is important. This allows a more accurate understanding of the nuances of speech.

[0064] The input information acquisition unit can use the emotion estimation function to analyze the emotions of speakers during a meeting in real time and record changes in emotions. The input information acquisition unit, for example, analyzes the voice of the speaker during a meeting and estimates emotions from the tone and pitch of the voice. For example, a higher voice indicates excitement. The input information acquisition unit also captures the speaker's facial expression with a camera and analyzes emotions in real time using facial expression recognition technology. For example, a frown indicates dissatisfaction. The input information acquisition unit also records changes in the speaker's emotions in real time and builds a system that visualizes changes in emotions as the meeting progresses. For example, the changes in emotions are displayed in a graph. This makes it possible to record changes in emotions during a meeting in real time.

[0065] The input information acquisition unit can automatically acquire documents and slides shared during a meeting, in addition to audio and video data from the meeting, and use them for analysis. For example, the input information acquisition unit automatically acquires documents and slides shared during a meeting and analyzes their contents using text analysis technology. For example, it extracts important points from shared presentation materials. The input information acquisition unit also acquires documents and slides used during a meeting in real time and analyzes them as the meeting progresses. For example, it instantly analyzes materials added during the meeting. The input information acquisition unit also automatically acquires shared documents and slides and builds a system that analyzes them in an integrated manner with the audio and video data from the meeting. For example, it associates the content of comments with the content of the materials and analyzes them. This makes it possible to analyze materials shared during a meeting as well.

[0066] The input information acquisition unit can automatically translate audio and video data of meetings held in different languages ​​and use it for analysis. For example, the input information acquisition unit automatically translates audio data of meetings held in different languages ​​and converts it into text data. For example, the content of a meeting held in English is translated into Japanese. The input information acquisition unit also automatically translates video data of meetings held in different languages ​​and displays it as subtitles. For example, the content of a meeting held in French is displayed with English subtitles. The input information acquisition unit also analyzes the automatically translated audio and video data and builds a system that makes it possible to understand the content of a meeting in multiple languages. For example, the content of a meeting in different languages ​​is analyzed in an integrated manner. This makes it possible to analyze meetings in different languages.

[0067] The input information acquisition unit uses an emotion estimation function to analyze the emotions of conference participants in real time, and can evaluate the progress of the conference based on changes in emotion. The input information acquisition unit, for example, analyzes the voices of conference participants and estimates changes in emotion in real time. For example, it detects changes in emotion from the tone and pitch of their voices. The input information acquisition unit also captures the facial expressions of conference participants with a camera and analyzes changes in emotion in real time using facial expression recognition technology. For example, it detects changes in emotion from smiles and furrowed brows. The input information acquisition unit also evaluates the progress of the conference based on the emotion estimation data and builds a system that focuses on analyzing parts with large changes in emotion. For example, it marks statements with large changes in emotion as important statements. This makes it possible to evaluate the progress of the conference based on changes in emotion.

[0068] The issue extraction unit can automatically search past meeting records and documents related to an issue extracted from meeting audio data and provide supplemental information. For example, the issue extraction unit automatically searches past meeting records for an issue extracted from meeting audio data and provides related information. For example, it searches for records in which the same issue was previously discussed. The issue extraction unit also automatically searches for documents related to the extracted issue and provides them as supplemental information. For example, it searches for past project reports and technical documents. The issue extraction unit also builds a system that automatically searches for related past meeting records and documents based on the issue extraction results and provides them to meeting participants. For example, it provides related materials as links. This makes it possible to provide supplemental information based on past meeting records and documents.

[0069] The issue extraction unit can prioritize extracting issues of high importance by taking into account the speaker's expertise and position. The issue extraction unit, for example, registers the speaker's expertise and position in a database and evaluates the importance of an issue based on that information. For example, it prioritizes extracting issues from speakers who have specialized knowledge. The issue extraction unit also builds a system that evaluates the importance of an issue based on the speaker's position. For example, it extracts comments from senior managers as important issues. The issue extraction unit also develops an algorithm that prioritizes extracting issues of high importance by taking into account the speaker's expertise and position. For example, it weights both expertise and position for evaluation. This makes it possible to extract issues of high importance by taking into account the speaker's expertise and position.

[0070] The issue extraction unit can use the emotion estimation function to analyze the speaker's emotions and prioritize extract emotionally emphasized issues. The issue extraction unit, for example, analyzes the speaker's voice and estimates the intensity of the emotion. For example, it measures the intensity of the emotion from the tone and pitch of the voice and extracts emphasized issues. The issue extraction unit also captures the speaker's facial expression with a camera and analyzes the intensity of the emotion using facial expression recognition technology. For example, it measures the intensity of the emotion from a smile or wrinkles between the eyebrows and extracts emphasized issues. The issue extraction unit also builds a system that prioritizes extracting emotionally emphasized issues based on the emotion estimation data. For example, it marks statements with high emotional intensity as important issues. This makes it possible to prioritize extract emotionally emphasized issues.

[0071] The issue extraction unit can automatically associate similar issues discussed in different meetings and generate a comprehensive issue list. For example, the issue extraction unit develops an algorithm that automatically associates issues discussed in different meetings and generates a comprehensive issue list. For example, it associates issues that include the same keywords. The issue extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar issues. For example, it uses natural language processing technology to extract similar issues. The issue extraction unit also develops a system that generates a comprehensive issue list based on the automatically associated issues and provides it to meeting participants. For example, it combines related issues into a single list. This makes it possible to associate similar issues discussed in different meetings and generate a comprehensive issue list.

[0072] The issue extraction unit can compare the issue extraction results with issues in different industries or fields to identify similarities and differences. For example, the issue extraction unit builds a system that compares extracted issues with issues in different industries or fields. For example, it compares issues in the technical field with issues in the marketing field. The issue extraction unit also develops an algorithm that registers issues in different industries or fields in a database and compares them with the extracted issues. For example, it automatically analyzes similarities and differences. The issue extraction unit also builds a system that compares the issue extraction results with issues in different industries or fields to identify similarities and differences. For example, it visually compares issues in different industries. This makes it possible to compare issues in different industries or fields and identify similarities and differences.

[0073] The issue extraction unit can use the emotion estimation function to evaluate the importance of issues and assign priorities based on the emotions of the meeting participants. The issue extraction unit, for example, analyzes the voices of the meeting participants and evaluates the importance of issues based on the intensity of their emotions. For example, it prioritizes extracting issues with a high emotional intensity. The issue extraction unit also captures the facial expressions of the meeting participants with a camera, analyzes the intensity of their emotions using facial expression recognition technology, and evaluates the importance of issues. For example, it prioritizes extracting issues with a high emotional intensity. The issue extraction unit also builds a system that evaluates the importance of issues and assigns priorities based on the emotion estimation data. For example, it marks issues with a high emotional intensity as important issues. This makes it possible to evaluate the importance of issues and assign priorities based on emotions.

[0074] When extracting the consideration history, the consideration history extraction unit analyzes the context and order of comments to grasp the details of the consideration history. For example, the consideration history extraction unit analyzes the context and order of comments to develop an algorithm to grasp the consideration history in detail. For example, it analyzes the order and relevance of comments. The consideration history extraction unit also analyzes the context of comments to build a system to grasp the consideration history in detail. For example, it analyzes the background and intention of comments. The consideration history extraction unit also comprehensively analyzes the context and order of comments to develop a system to grasp the consideration history in detail. For example, it visualizes the flow of comments. This makes it possible to analyze the context and order of comments to grasp the details of the consideration history.

[0075] The study history extraction unit can automatically search for related technical literature and patent information based on the study history extraction results and provide supplemental information. The study history extraction unit, for example, builds a system that automatically searches for related technical literature based on the study history extraction results and provides it as supplemental information. For example, it searches a technical paper database. The study history extraction unit also develops an algorithm that automatically searches for patent information related to the extracted study history and provides it as supplemental information. For example, it searches a patent database. The study history extraction unit also builds a system that automatically searches for related technical literature and patent information based on the study history extraction results and provides it to meeting participants. For example, it provides related literature and patents as links. This makes it possible to provide supplemental information based on related technical literature and patent information.

[0076] The consideration history extraction unit can analyze the speaker's emotions using an emotion estimation function and preferentially extract emotionally important consideration history. The consideration history extraction unit, for example, analyzes the speaker's voice and estimates the intensity of the emotion. For example, the intensity of the emotion is measured from the tone and pitch of the voice, and important consideration history is extracted. The consideration history extraction unit also captures the speaker's facial expression with a camera and analyzes the intensity of the emotion using facial expression recognition technology. For example, the intensity of the emotion is measured from a smile or wrinkles between the eyebrows, and important consideration history is extracted. The consideration history extraction unit also builds a system that preferentially extracts emotionally important consideration history based on the emotion estimation data. For example, it marks statements with high emotional intensity as important consideration history. This allows emotionally important consideration history to be preferentially extracted.

[0077] The consideration history extraction unit can automatically associate the consideration histories discussed in different meetings and generate a comprehensive consideration history list. The consideration history extraction unit, for example, develops an algorithm that automatically associates the consideration histories discussed in different meetings and generates a comprehensive consideration history list. For example, it associates consideration histories on the same topic. The consideration history extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar consideration histories. For example, it uses natural language processing technology to extract similar consideration histories. The consideration history extraction unit also develops a system that generates a comprehensive consideration history list based on the automatically associated consideration histories and provides it to meeting participants. For example, it consolidates related consideration histories into a single list. This makes it possible to associate the consideration histories discussed in different meetings and generate a comprehensive consideration history list.

[0078] The consideration history extraction unit can compare the extracted results of the consideration history with the consideration history of different industries or fields to clarify similarities and differences. For example, the consideration history extraction unit builds a system that compares the extracted consideration history with the consideration history of different industries or fields. For example, it compares the consideration history of the technical field with the consideration history of the marketing field. The consideration history extraction unit also registers the consideration history of different industries or fields in a database and develops an algorithm that compares the extracted consideration history. For example, it automatically analyzes the similarities and differences. The consideration history extraction unit also builds a system that compares the extracted results of the consideration history with the consideration history of different industries or fields to clarify similarities and differences. For example, it visually compares the consideration history of different industries. This makes it possible to compare the consideration history of different industries or fields to clarify similarities and differences.

[0079] The consideration history extraction unit can use the emotion estimation function to evaluate the importance of the consideration history and assign priorities based on the emotions of the conference participants. The consideration history extraction unit, for example, analyzes the voices of the conference participants and evaluates the importance of the consideration history based on the intensity of their emotions. For example, it preferentially extracts consideration history with a high intensity of emotion. The consideration history extraction unit also captures the facial expressions of the conference participants with a camera, analyzes the intensity of their emotions using facial expression recognition technology, and evaluates the importance of the consideration history. For example, it preferentially extracts consideration history with a high intensity of emotion. The consideration history extraction unit also builds a system that evaluates the importance of the consideration history and assigns priorities based on the emotion estimation data. For example, it marks consideration history with a high intensity of emotion as important consideration history. This makes it possible to evaluate the importance of the consideration history and assign priorities based on emotions.

[0080] When extracting a conclusion, the conclusion extraction unit analyzes the context and order of statements to grasp a more detailed conclusion. The conclusion extraction unit, for example, analyzes the context and order of statements to develop an algorithm to grasp a conclusion in detail. For example, it analyzes the order and relevance of statements. The conclusion extraction unit also analyzes the context of statements to build a system to grasp a conclusion in detail. For example, it analyzes the background and intention of statements. The conclusion extraction unit also develops a system to comprehensively analyze the context and order of statements to grasp a conclusion in detail. For example, it visualizes the flow of statements. This makes it possible to analyze the context and order of statements to grasp a detailed conclusion.

[0081] The conclusion extraction unit can automatically search for related technical literature and patent information based on the conclusion extraction results and provide supplementary information. The conclusion extraction unit, for example, builds a system that automatically searches for related technical literature based on the conclusion extraction results and provides it as supplementary information. For example, it searches a technical paper database. The conclusion extraction unit also develops an algorithm that automatically searches for patent information related to the extracted conclusion and provides it as supplementary information. For example, it searches a patent database. The conclusion extraction unit also builds a system that automatically searches for related technical literature and patent information based on the conclusion extraction results and provides it to conference participants. For example, it provides related literature and patents as links. This makes it possible to provide supplementary information based on related technical literature and patent information.

[0082] The conclusion extraction unit can analyze the speaker's emotions using the emotion estimation function and preferentially extract emotionally important conclusions. The conclusion extraction unit, for example, analyzes the speaker's voice and estimates the intensity of the emotion. For example, the intensity of the emotion is measured from the tone and pitch of the voice, and important conclusions are extracted. The conclusion extraction unit also captures the speaker's facial expression with a camera and analyzes the intensity of the emotion using facial expression recognition technology. For example, the intensity of the emotion is measured from a smile or wrinkles between the eyebrows, and important conclusions are extracted. The conclusion extraction unit also builds a system that preferentially extracts emotionally important conclusions based on the emotion estimation data. For example, it marks statements with high emotional intensity as important conclusions. This allows emotionally important conclusions to be preferentially extracted.

[0083] The conclusion extraction unit can automatically associate conclusions discussed in different meetings and generate a comprehensive list of conclusions. For example, the conclusion extraction unit develops an algorithm that automatically associates conclusions discussed in different meetings and generates a comprehensive list of conclusions. For example, it associates conclusions on the same topic. The conclusion extraction unit also analyzes the minutes of different meetings and builds a system that automatically associates similar conclusions. For example, it extracts similar conclusions using natural language processing technology. The conclusion extraction unit also develops a system that generates a comprehensive list of conclusions based on the automatically associated conclusions and provides it to meeting participants. For example, it combines related conclusions into a single list. This makes it possible to associate conclusions discussed in different meetings and generate a comprehensive list of conclusions.

[0084] The conclusion extraction unit can compare the conclusion extraction results with conclusions from different industries or fields to clarify similarities and differences. For example, the conclusion extraction unit builds a system that compares extracted conclusions with conclusions from different industries or fields. For example, it compares conclusions from the technical field with those from the marketing field. The conclusion extraction unit also registers conclusions from different industries or fields in a database and develops an algorithm that compares them with the extracted conclusion. For example, it automatically analyzes similarities and differences. The conclusion extraction unit also builds a system that compares the conclusion extraction results with conclusions from different industries or fields to clarify similarities and differences. For example, it visually compares conclusions from different industries. This makes it possible to compare conclusions from different industries or fields to clarify similarities and differences.

[0085] The conclusion extraction unit can use the emotion estimation function to evaluate the importance of conclusions and prioritize them based on the emotions of the conference participants. The conclusion extraction unit, for example, analyzes the voices of the conference participants and evaluates the importance of conclusions based on the intensity of their emotions. For example, it preferentially extracts conclusions with a high emotional intensity. The conclusion extraction unit also captures the facial expressions of the conference participants with a camera, analyzes the intensity of their emotions using facial expression recognition technology, and evaluates the importance of conclusions. For example, it preferentially extracts conclusions with a high emotional intensity. The conclusion extraction unit also builds a system that evaluates the importance of conclusions and prioritizes them based on emotion estimation data. For example, it marks conclusions with a high emotional intensity as important conclusions. This makes it possible to evaluate the importance of conclusions and prioritize them based on emotions.

[0086] The document generation unit can automatically generate visually appealing and easy-to-understand PPT and PDF documents based on the extracted information. The document generation unit, for example, builds a system that automatically generates visually appealing PPT slides based on the extracted information. For example, it automatically adjusts the graphic design and layout. The document generation unit also develops an algorithm that automatically generates easy-to-understand PDF documents based on the extracted information. For example, it automatically adjusts the text format and the placement of figures and tables. The document generation unit also builds a system that automatically generates visually appealing and easy-to-understand PPT and PDF documents. For example, it uses templates to provide a consistent design. This makes it possible to automatically generate visually appealing and easy-to-understand documents.

[0087] The data generation unit can automatically create related graphs and charts to provide visual supplementary information when generating data. The data generation unit, for example, builds a system that automatically creates related graphs and charts based on extracted information. For example, it generates bar graphs and pie charts based on data. The data generation unit also develops an algorithm that automatically adds graphs and charts as visual supplementary information when generating data. For example, it generates a line graph that shows data trends. The data generation unit also builds a system that automatically creates related graphs and charts to provide visual supplementary information. For example, it generates a heat map that shows a comparison of data. This makes it possible to automatically create related graphs and charts to provide visual supplementary information.

[0088] The material generation unit uses the emotion estimation function to generate materials that reflect the emotions of meeting participants, making the content more likely to resonate emotionally. The material generation unit, for example, uses the emotion estimation function to build a system that automatically generates PowerPoint slides that reflect the emotions of meeting participants. For example, it adopts a design that emphasizes statements that express strong positive emotions. The material generation unit also develops an algorithm that automatically generates PDF materials with content that is more likely to resonate emotionally based on the emotion estimation data. For example, it adjusts the color and font of text according to the intensity of the emotion. The material generation unit also builds a system that generates materials that reflect the emotions of meeting participants, making the content more likely to resonate emotionally. For example, it adds graphs and icons that show changes in emotion. This allows the generation of materials that reflect the emotions of meeting participants, making the content more likely to resonate emotionally.

[0089] The material generation unit can integrate materials from different meetings and automatically generate a comprehensive report. For example, the material generation unit builds a system that integrates materials from different meetings and automatically generates a comprehensive report. For example, it compiles minutes from multiple meetings into a single PDF. The material generation unit also develops an algorithm that automatically integrates materials from different meetings and generates a visually organized report. For example, it creates slides that summarize the important points of each meeting. The material generation unit also builds a system that integrates materials from different meetings and automatically generates a comprehensive report. For example, it adds a section that summarizes the conclusions of each meeting. This makes it possible to integrate materials from different meetings and automatically generate a comprehensive report.

[0090] The document generation unit can support output in different languages ​​when generating documents, enabling information sharing from an international perspective. The document generation unit, for example, builds a system that supports output in different languages ​​when generating documents. For example, it generates documents in multiple languages, such as English, Japanese, and French. The document generation unit also develops algorithms that support output in different languages ​​and enable information sharing from an international perspective. For example, it builds a document generation system that incorporates an automatic translation function. The document generation unit also builds a system that supports output in different languages ​​when generating documents, enabling information sharing from an international perspective. For example, it performs translation that takes into account the technical terms of each language. This makes it possible to support output in different languages ​​and enable information sharing from an international perspective.

[0091] The material generation unit uses the emotion estimation function to monitor the user's emotional response to the content of the material in real time, and can continuously improve the optimal material. The material generation unit, for example, develops a system that uses the emotion estimation function to monitor the user's emotional response to the content of the material in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The material generation unit also builds a system that continuously improves the content of the material based on the user's emotional response data. For example, it adopts a design that emphasizes parts that have a high number of positive emotional responses. The material generation unit also collects emotion estimation data in real time and develops a system that dynamically adjusts the content of the material. For example, it modifies the content of the material according to changes in the user's emotions. This makes it possible to monitor the user's emotional response in real time and continuously improve the optimal material.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The input information acquisition unit can acquire data from digital whiteboards used during meetings in real time and use it for analysis. For example, it can instantly convert what is written on the digital whiteboard into text data and analyze it as the meeting progresses. The input information acquisition unit can also analyze the digital whiteboard data in an integrated manner with other meeting materials to extract related information. This allows analysis to include information from the digital whiteboard during the meeting.

[0094] The input information acquisition unit can analyze not only the content of speech by conference participants, but also the tone and speed of the speaker's voice to evaluate the importance of the speech. For example, speech with a high tone and fast speed is likely to be important. The input information acquisition unit can also build a system that analyzes changes in the speaker's voice in real time to identify important speech. This allows for a more accurate understanding of the nuances of speech.

[0095] The input information acquisition unit can automatically acquire chat messages and emails used during a meeting and use them for analysis. For example, it can analyze chat messages sent during a meeting in real time and extract important information. The input information acquisition unit can also automatically acquire emails sent during a meeting, convert them into text data, and analyze them. This allows analysis of digital communications during a meeting as well.

[0096] The input information acquisition unit uses an emotion estimation function to analyze the emotions of conference participants in real time and can evaluate the progress of the conference based on changes in emotion. For example, it analyzes the voices of conference participants and estimates changes in emotion in real time. The input information acquisition unit can also capture the facial expressions of conference participants with a camera and analyze changes in emotion in real time using facial expression recognition technology. This makes it possible to evaluate the progress of the conference based on changes in emotion.

[0097] The input information acquisition unit can automatically acquire documents and slides used during a meeting, in addition to audio and video data from the meeting, and use them for analysis. For example, it can automatically acquire documents and slides shared during a meeting and analyze their contents using text analysis technology. The input information acquisition unit can also acquire documents and slides used during a meeting in real time and analyze them as the meeting progresses. This allows analysis to include materials shared during the meeting.

[0098] The input information acquisition unit can automatically translate audio and video data from conferences held in different languages ​​and use it for analysis. For example, audio data from conferences held in different languages ​​can be automatically translated and converted into text data. The input information acquisition unit can also automatically translate video data from conferences held in different languages ​​and display it as subtitles. This allows conferences held in different languages ​​to be analyzed.

[0099] The input information acquisition unit uses an emotion estimation function to analyze the emotions of conference participants in real time and can evaluate the progress of the conference based on changes in emotion. For example, it analyzes the voices of conference participants and estimates changes in emotion in real time. The input information acquisition unit can also capture the facial expressions of conference participants with a camera and analyze changes in emotion in real time using facial expression recognition technology. This makes it possible to evaluate the progress of the conference based on changes in emotion.

[0100] The issue extraction unit can automatically search past meeting records and documents related to an issue extracted from the meeting audio data and provide supplementary information. For example, past meeting records can be automatically searched for an issue extracted from the meeting audio data and related information can be provided. The issue extraction unit can also automatically search for documents related to the extracted issue and provide them as supplementary information. This makes it possible to provide supplementary information based on past meeting records and documents.

[0101] The issue extraction unit can prioritize the extraction of issues with high importance, taking into account the speaker's expertise and position. For example, the speaker's expertise and position can be registered in a database, and the importance of an issue can be evaluated based on that information. The issue extraction unit can also build a system that evaluates the importance of an issue based on the speaker's position. This makes it possible to extract issues with high importance, taking into account the speaker's expertise and position.

[0102] The issue extraction unit can use an emotion estimation function to analyze the speaker's emotions and prioritize extraction of emotionally emphasized issues. For example, it can analyze the speaker's voice and estimate the intensity of the emotion. The issue extraction unit can also capture the speaker's facial expression with a camera and analyze the intensity of the emotion using facial expression recognition technology. This allows it to prioritize extraction of emotionally emphasized issues.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The input information acquisition unit acquires audio and video data from the meeting. For example, recordings of the meeting can be collected using a microphone and saved in digital format. Recorded meeting data can also be captured using a camera and saved as video data. The input information acquisition unit can also scan images of the whiteboard and handwritten notes used during the meeting and convert them into digital data. For example, an image of the whiteboard can be captured using a high-resolution camera and converted into text data using image recognition technology. Handwritten notes can be converted into character data using OCR technology. Step 2: The issue extraction unit extracts the issues discussed in the meeting from the input information acquired by the input information acquisition unit. For example, the generation AI converts the audio data of the meeting into text using speech recognition technology and extracts the issues using natural language processing technology. Step 3: The consideration history extraction unit extracts the consideration history based on the issues extracted by the issue extraction unit. For example, the generation AI analyzes the flow of discussion and the order of comments from text data to extract the consideration history. Step 4: The conclusion extraction unit extracts a conclusion based on the deliberation process extracted by the deliberation process extraction unit. For example, the generation AI analyzes the final decisions and agreements from the text data and extracts a conclusion. Step 5: The document generation unit generates PowerPoint or PDF documents based on the conclusions extracted by the conclusion extraction unit. For example, the generation AI automatically generates PowerPoint slides based on the extracted information, describing the issues, the process of consideration, and the conclusions on each slide. PDF documents are also output in a similar format, with each item clearly organized.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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]

[0172] 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. an input information acquisition unit that acquires audio and video data of the conference; a problem extraction unit that extracts problems discussed in the meeting from the input information acquired by the input information acquisition unit; a study history extraction unit that extracts a study history based on the problem extracted by the problem extraction unit; a conclusion extraction unit that extracts a conclusion based on the study history extracted by the study history extraction unit; a material generation unit that generates a material such as a ppt or PDF based on the conclusion extracted by the conclusion extraction unit. A system characterized by:

2. The input information acquisition unit In addition to the audio and video data of the meeting, images of the whiteboard used during the meeting and handwritten notes are analyzed and converted into text data.

2. The system of claim 1.

3. The input information acquisition unit Analyze not only the content of what meeting participants say, but also their facial expressions and gestures to more accurately grasp the nuances of what is being said 2. The system of claim 1.

4. The input information acquisition unit The emotions of the speakers during the meeting are analyzed in real time, and changes in the emotions are recorded.

2. The system of claim 1.

5. The input information acquisition unit In addition to the audio and video data of the meeting, documents and slides shared during the meeting are automatically captured and used for analysis.

2. The system of claim 1.

6. The input information acquisition unit The audio and video data of the meetings held in different languages ​​are automatically translated and used for analysis.

2. The system of claim 1.

7. The input information acquisition unit Analyzing the emotions of meeting participants in real time and evaluating the progress of the meeting based on changes in the emotions 2. The system of claim 1.

8. The problem extraction unit Automatically search for relevant past meeting records and documents for the issues extracted from the audio data of the meeting, and provide supplementary information 2. The system of claim 1.

Images