system

Abstract

The system according to this embodiment aims to share documents that are discussed during a meeting and to capture and answer participants' questions in real time. [Solution] The system according to the embodiment comprises a document sharing unit, a question receiving unit, a meeting minutes generation unit, and an emotion analysis unit. The document sharing unit shares documents that were discussed during the meeting. The question receiving unit identifies points of confusion for each participant based on the documents shared by the document sharing unit and provides answers in real time. The meeting minutes generation unit automatically generates meeting minutes after the meeting based on the points of confusion identified by the question receiving unit. The emotion analysis unit analyzes the sentiments of stakeholders regarding the meeting minutes generated by the meeting minutes generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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] [[ID=二十一]] [[ID=二十二]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, sharing of documents that have come up in a meeting and capturing of unclear points of participants are not sufficiently performed, and there is room for improvement.

[0005] The system according to the embodiment aims to share documents that have come up in a meeting and capture and answer unclear points of participants in real time.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a document sharing unit, a question receiving unit, a meeting minutes generation unit, and a sentiment analysis unit. The document sharing unit shares documents that were discussed during the meeting. The question receiving unit identifies points of confusion for each participant based on the documents shared by the document sharing unit and provides answers in real time. The meeting minutes generation unit automatically generates meeting minutes after the meeting based on the points of confusion identified by the question receiving unit. The sentiment analysis unit analyzes the sentiments of stakeholders regarding the meeting minutes generated by the meeting minutes generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can share documents that are discussed during a meeting and can capture and answer participants' questions in real time. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The MTG Agent System according to an embodiment of the present invention is a system that shares documents discussed in real time during a meeting and identifies points of confusion for each participant to enhance their understanding. The MTG Agent System shares documents discussed during the meeting in real time, identifies points of confusion for each participant, and provides answers in real time. Furthermore, the MTG Agent System automatically generates meeting minutes after the meeting and provides clear information including stakeholders' sentiments (positive or negative) regarding the minutes. For example, the MTG Agent System has a function to share documents such as presentation materials and reports discussed during the meeting in real time. Next, the MTG Agent System has a function to identify points of confusion for each participant and provide answers in real time. In addition, the MTG Agent System has a function to automatically generate meeting minutes after the meeting, and the minutes include stakeholders' sentiments. In this way, by utilizing the MTG Agent System, it becomes possible to share documents during meetings, resolve points of confusion, automatically generate meeting minutes, and analyze sentiment, thereby improving the efficiency of meetings and enhancing understanding. This enables the MTG agent system to share documents during meetings, resolve questions, automatically generate meeting minutes, and perform sentiment analysis, thereby improving meeting efficiency and comprehension.

[0029] The MTG agent system according to this embodiment comprises a document sharing unit, a question receiving unit, a meeting minutes generation unit, and a sentiment analysis unit. The document sharing unit shares documents that were discussed during the meeting. The document sharing unit shares documents such as presentation materials and reports that were discussed during the meeting in real time. For example, the document sharing unit can share presentation materials in slide format. The document sharing unit can also share reports in PDF format. Furthermore, the document sharing unit can also share notes in text format. The question receiving unit captures any unclear points for each participant and provides answers in real time. For example, the question receiving unit accepts questions from participants when they have unclear points during the meeting. For example, the question receiving unit provides answers to participants' questions in real time using a generating AI. For example, the question receiving unit can accept questions from participants in text format and generate answers using a generating AI. For example, the question receiving unit can accept questions from participants using voice input and generate answers using a generating AI. The meeting minutes generation unit automatically generates meeting minutes after the meeting. The minutes generation unit automatically generates meeting minutes based on, for example, the content of statements made during the meeting and shared documents. The minutes generation unit can, for example, use speech recognition technology to convert the content of statements made during the meeting into text and generate the minutes. The minutes generation unit can also, for example, summarize the content of shared documents and reflect them in the minutes. The minutes generation unit can also, for example, summarize the content of statements made during the meeting and reflect them in the minutes. The sentiment analysis unit analyzes the emotions of stakeholders regarding the minutes. The sentiment analysis unit can, for example, analyze the emotions of stakeholders from the content of statements and reactions and reflect them in the minutes. The sentiment analysis unit can, for example, use natural language processing technology to analyze the content of statements and estimate emotions. The sentiment analysis unit can also, for example, use facial recognition technology to analyze the emotions of stakeholders. The sentiment analysis unit can also, for example, use speech analysis technology to analyze the emotions of stakeholders. As a result, the MTG agent system according to this embodiment enables document sharing during meetings, clarification of unclear points, automatic generation of meeting minutes, and sentiment analysis, thereby improving meeting efficiency and comprehension.

[0030] The document sharing function allows users to share documents that come up in discussion during a meeting. Specifically, it has the functionality to share documents such as presentation materials and reports in real time during a meeting. For example, presentation materials can be shared in slide format, allowing participants to view the slides on their own devices while participating in the meeting. Reports can also be shared in PDF format, enabling participants to discuss while reviewing detailed data and graphs. Furthermore, notes can be shared in text format, allowing important points and action items to be recorded in real time during the meeting, ensuring everyone shares the same information. The document sharing function is integrated with cloud storage, making it easy to share documents uploaded before the meeting. Newly created documents and notes during the meeting are also instantly shared, allowing all participants to discuss based on the latest information. As a result, the document sharing function can significantly improve meeting efficiency and promote information sharing and understanding.

[0031] The question reception system captures any points of confusion for each participant and provides answers in real time. Specifically, it has a function to accept questions from participants when they have questions during the meeting. For example, if a participant enters a question in text format, a generative AI will generate an answer in real time. The generative AI can provide appropriate answers based on the meeting content and shared documents. It is also possible to accept questions from participants using voice input, and the generative AI will use speech recognition technology to convert the question into text and generate an answer. The question reception system can analyze the intent of questions using natural language processing technology and provide the most appropriate answer. Furthermore, the question reception system can refer to past meeting data and FAQ databases to provide quick and accurate answers. As a result, the question reception system can immediately resolve participants' doubts and ensure the smooth progress of the meeting. In addition, the question reception system can record the question history of participants and refer to it later, which is useful for post-meeting follow-up and the creation of meeting minutes.

[0032] The meeting minutes generation unit automatically generates meeting minutes after the meeting. Specifically, it has the function to automatically generate meeting minutes based on the content of the discussions during the meeting and the documents shared. For example, it uses speech recognition technology to convert the content of the discussions during the meeting into text and generate the meeting minutes. Speech recognition technology performs highly accurate speech analysis and can accurately record the content of each speaker's remarks. It can also summarize the content of shared documents and reflect it in the meeting minutes. As a result, the meeting minutes generation unit can record all important points and decisions made during the meeting without omission and share them with all participants. Furthermore, the meeting minutes generation unit can also summarize the content of the discussions during the meeting and reflect it in the meeting minutes. Using summarization technology, it can concisely summarize long remarks and complex discussions, improving the readability of the meeting minutes. The meeting minutes generation unit saves the generated meeting minutes to cloud storage, making them accessible to all participants. It also makes the content of the meeting minutes searchable, making it easy to find specific topics and remarks. As a result, the meeting minutes generation unit can streamline post-meeting follow-up and information sharing, maximizing the effectiveness of the meeting.

[0033] The emotion analysis unit analyzes stakeholders' emotions regarding meeting minutes. Specifically, it analyzes stakeholders' emotions from their statements and reactions and reflects them in the minutes. For example, it uses natural language processing technology to analyze statements and estimate emotions. Natural language processing technology can analyze the tone and wording of statements and classify emotions as positive, negative, neutral, etc. It can also analyze stakeholders' emotions using facial recognition technology. Facial recognition technology analyzes camera footage and estimates emotions from stakeholders' facial expressions. Furthermore, it can also analyze stakeholders' emotions using voice analysis technology. Voice analysis technology analyzes the tone, pitch, and speed of voices to estimate emotions. The emotion analysis unit can combine these technologies to perform more accurate emotion analysis. The analyzed emotions are reflected in the meeting minutes and used as reference information to understand the atmosphere of the meeting and the reactions of stakeholders. In this way, the emotion analysis unit can improve the understanding of meetings and participant satisfaction, and support more effective communication.

[0034] The document sharing section allows for the real-time sharing of documents such as presentation materials and reports that were discussed during a meeting. For example, the document sharing section can share presentation materials discussed during the meeting in slide format. It can also share reports in PDF format, for example. It can also share notes in text format, for example. This improves participants' understanding by sharing documents discussed during the meeting in real time. Presentation materials include, but are not limited to, slides, videos, and audio. Reports include, but are not limited to, PDFs, Word documents, and Excel spreadsheets.

[0035] The question reception desk can receive questions from participants during the meeting if they have any questions, and provide answers in real time. For example, the question reception desk can receive questions from participants if they have any questions during the meeting. For example, the question reception desk can use generative AI to provide answers to participants' questions in real time. For example, the question reception desk can receive questions from participants in text format, and generative AI can generate answers to those questions. For example, the question reception desk can receive questions from participants using voice input, and generative AI can generate answers to those questions. This improves participants' understanding by providing answers in real time when they have any questions during the meeting. Questions include, but are not limited to, the format of the question or ambiguity of its content. Real time includes, but is not limited to, a few seconds or a few minutes.

[0036] The minutes generation unit can automatically generate meeting minutes based on the content of discussions during the meeting and shared documents. For example, the minutes generation unit can automatically generate meeting minutes based on the content of discussions during the meeting and shared documents. For example, the minutes generation unit can use speech recognition technology to convert the content of discussions during the meeting into text and generate the minutes. The minutes generation unit can also summarize the content of shared documents and reflect it in the minutes. This streamlines the creation of meeting minutes after the meeting by automatically generating minutes based on the content of discussions during the meeting and shared documents. The content of discussions includes, but is not limited to, speech recognition and manual input. The documents include, but are not limited to, presentation materials, reports, and memos.

[0037] The emotion analysis unit can analyze stakeholders' emotions from their statements and reactions and reflect them in the meeting minutes. For example, the emotion analysis unit can analyze stakeholders' emotions from their statements and reactions and reflect them in the meeting minutes. For example, the emotion analysis unit can analyze statements using natural language processing technology and estimate emotions. For example, the emotion analysis unit can analyze stakeholders' emotions using facial recognition technology. For example, the emotion analysis unit can analyze stakeholders' emotions using voice analysis technology. As a result, by analyzing stakeholders' emotions from their statements and reactions and reflecting them in the meeting minutes, the content of the meeting minutes can be enriched. Emotions include, for example, positive, negative, neutral, etc., but are not limited to these examples. Reactions include, for example, facial expressions, tone of voice, gestures, etc., but are not limited to these examples.

[0038] The document sharing department can prioritize sharing documents based on their importance during the meeting. For example, it might immediately share important presentation materials, share supplementary reports as the discussion progresses, or share reference materials all at once at the end of the meeting. This ensures that important information is shared preferentially by prioritizing sharing based on the importance of the documents discussed during the meeting. Importance may include, but is not limited to, the speaker's title or the relevance of the content.

[0039] The document sharing function can provide customized documents to participants based on their roles and areas of expertise when sharing documents. For example, the document sharing function can provide executives with concise documents, engineers with detailed technical materials, and marketing personnel with market analysis reports. By providing customized documents based on participants' roles and areas of expertise, the function improves participants' understanding. Roles include, but are not limited to, managers, engineers, and assistants. Areas of expertise include, but are not limited to, technology, marketing, and finance.

[0040] The document sharing function can prioritize sharing highly relevant documents by considering the geographical location of participants when sharing documents. For example, if participants are in different regions, the document sharing function will prioritize sharing documents relevant to each region. For example, if participants are in the same office, the document sharing function will share common documents. For example, if participants are working remotely, the document sharing function will share documents that are accessible online. This improves participants' understanding by prioritizing the sharing of highly relevant documents by considering their geographical location. Geographical location information includes, but is not limited to, GPS data and IP addresses. Highly relevant documents include, but are not limited to, documents with similar content and past usage history.

[0041] The document sharing function can analyze participants' past meeting attendance history and provide relevant documents when sharing documents. For example, the document sharing function can provide relevant documents based on meeting minutes from meetings the participant has previously attended. For example, the document sharing function can provide relevant documents based on reports submitted by the participant in the past. For example, the document sharing function can provide relevant documents based on feedback the participant has previously received. This improves participants' understanding by analyzing their past meeting attendance history and providing relevant documents. Past meeting attendance history includes, but is not limited to, attendance records and statements made. Relevant documents include, but are not limited to, content consistency and past usage history.

[0042] The question reception department can provide the most appropriate answer by referring to the participant's past question history when a question is received. For example, the question reception department can provide relevant answers based on the content of questions the participant has asked in the past. For example, the question reception department can provide answers to common questions from the participant's past question history. For example, the question reception department can analyze the participant's past question history and provide the most appropriate answer. This improves the participant's understanding by providing the most appropriate answer by referring to the participant's past question history. Past question history includes, but is not limited to, the content of the question and the content of the answer. The most appropriate answer includes, but is not limited to, the accuracy and relevance of the content.

[0043] The question reception desk can prioritize questions based on the progress of the meeting. For example, the question reception desk may prioritize questions related to important agenda items of the meeting. For example, the question reception desk may prioritize questions that affect the progress of the meeting. For example, the question reception desk may postpone questions raised near the end of the meeting. In this way, by prioritizing questions based on the progress of the meeting, important questions are handled preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers have spoken. The priority of questions includes, but is not limited to, the importance and urgency of the questions.

[0044] The question reception desk can provide customized answers to participants based on their area of ​​expertise and position. For example, the question reception desk can provide answers including technical details to engineers, concise answers to management, and market analysis to marketing personnel. This improves participants' understanding by providing customized answers based on their area of ​​expertise and position. Areas of expertise include, but are not limited to, technology, marketing, and finance. Positions include, but are not limited to, managers, engineers, and assistants.

[0045] The question reception desk can analyze participants' social media activity and provide relevant information when questions are received. For example, the question reception desk can provide relevant information based on what participants have posted on social media. For example, the question reception desk can provide influential information considering the number of followers a participant has on social media. For example, the question reception desk can analyze a participant's social media activity history and provide the most relevant information. This improves participants' understanding by analyzing their social media activity and providing relevant information. Social media activity includes, but is not limited to, posts and follower counts. Relevant information includes, but is not limited to, content consistency and past usage history.

[0046] The minutes generation unit can adjust the level of detail in the minutes based on the importance of the statements made during the meeting. For example, the minutes generation unit will record important statements in detail. For example, the minutes generation unit will record supplementary statements concisely. For example, the minutes generation unit will record only the main points of statements that are only for reference. In this way, by adjusting the level of detail in the minutes based on the importance of the statements made during the meeting, important information is recorded preferentially. The importance of a statement includes, but is not limited to, the speaker's position and the relevance of the content. The level of detail in the minutes includes, but is not limited to, the degree of summarization and the scope of the recording.

[0047] The minutes generation unit can apply different minutes generation algorithms depending on the category of the meeting when generating minutes. For example, the minutes generation unit applies a minutes generation algorithm that emphasizes technical details to a technical meeting. For example, the minutes generation unit applies a minutes generation algorithm that summarizes key points to a management meeting. For example, the minutes generation unit applies a minutes generation algorithm that includes market analysis to a marketing meeting. This improves the accuracy of the minutes by applying the most suitable minutes generation algorithm according to the category of the meeting. Meeting categories include, but are not limited to, technical meetings, sales meetings, and strategy meetings. Minutes generation algorithms include, but are not limited to, natural language processing and machine learning.

[0048] The minutes generation unit can determine the priority of meeting minutes based on the progress of the meeting. For example, the minutes generation unit can prioritize the generation of minutes related to important agenda items of the meeting. For example, the minutes generation unit can prioritize the generation of minutes that affect the progress of the meeting. For example, the minutes generation unit can postpone the generation of minutes issued near the end of the meeting. In this way, by determining the priority of minutes based on the progress of the meeting, important information is recorded preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers spoke. The priority of meeting minutes includes, but is not limited to, the importance and urgency of the content.

[0049] The minutes generation unit can improve the accuracy of the minutes by referring to relevant literature during the generation process. For example, the minutes generation unit can supplement the content of the minutes based on literature referenced during the meeting. For example, the minutes generation unit can improve the accuracy of the minutes by referring to literature related to the meeting agenda. For example, the minutes generation unit can supplement the content of the minutes by referring to literature that influences the progress of the meeting. As a result, the content of the minutes is enriched by improving their accuracy by referring to relevant literature. Relevant literature includes, but is not limited to, past minutes and research papers. The accuracy of the minutes includes, but is not limited to, accuracy and comprehensiveness of content.

[0050] The sentiment analysis unit can adjust the level of detail in its sentiment analysis based on the importance of the statements made during the meeting. For example, the sentiment analysis unit can perform a detailed sentiment analysis on important statements. For example, it can perform a simplified sentiment analysis on supplementary statements. For example, it can perform a summary sentiment analysis on statements that are only for reference. By adjusting the level of detail in the sentiment analysis based on the importance of the statements made during the meeting, important information is prioritized for analysis. The importance of statements includes, but is not limited to, the speaker's position and the relevance of the content. The level of detail in the sentiment analysis includes, but is not limited to, the depth and scope of the analysis.

[0051] The sentiment analysis unit can apply different sentiment analysis algorithms depending on the category of the meeting during sentiment analysis. For example, in a technical meeting, the sentiment analysis unit applies a sentiment analysis algorithm for technical statements. For example, in a management meeting, the sentiment analysis unit applies a sentiment analysis algorithm for management statements. For example, in a marketing meeting, the sentiment analysis unit applies a sentiment analysis algorithm for market analysis. This improves the accuracy of sentiment analysis by applying the most appropriate sentiment analysis algorithm according to the category of the meeting. Meeting categories include, but are not limited to, technical meetings, sales meetings, and strategy meetings. Sentiment analysis algorithms include, but are not limited to, natural language processing and machine learning.

[0052] The sentiment analysis unit can prioritize sentiment analysis based on the progress of the meeting. For example, the sentiment analysis unit may prioritize sentiment analysis related to important agenda items of the meeting. For example, the sentiment analysis unit may prioritize sentiment analysis that affects the progress of the meeting. For example, the sentiment analysis unit may postpone sentiment analysis submitted near the end of the meeting. By prioritizing sentiment analysis based on the progress of the meeting, important information is analyzed preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers take their place. The priority of sentiment analysis includes, but is not limited to, the importance and urgency of the content.

[0053] The sentiment analysis unit can improve the accuracy of its sentiment analysis by referring to relevant literature for the meeting during the analysis. For example, the sentiment analysis unit can supplement the content of the sentiment analysis based on literature referenced during the meeting. For example, the sentiment analysis unit can improve the accuracy of its sentiment analysis by referring to literature related to the meeting agenda. For example, the sentiment analysis unit can supplement the content of its sentiment analysis by referring to literature that influences the progress of the meeting. In this way, the content of the sentiment analysis is enriched by improving the accuracy of the sentiment analysis by referring to relevant literature for the meeting. Relevant literature includes, but is not limited to, past meeting minutes and research papers. The accuracy of the sentiment analysis includes, but is not limited to, the accuracy and comprehensiveness of the content.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The MTG Agent System can further analyze participants' contributions and generate rankings of speakers based on the frequency and importance of their statements. For example, by analyzing the content of their statements, it can identify the participant who spoke the most during the meeting and display their ranking. It can also evaluate the importance of each participant's contribution and place those who made important statements higher in the rankings. Furthermore, by combining frequency and importance of contributions, it can generate a comprehensive ranking that visualizes each participant's contribution to the meeting's progress. In this way, by analyzing participants' contributions and generating rankings of speakers based on frequency and importance, the progress of the meeting can be understood more clearly.

[0056] The MTG Agent system can also translate meeting content in real time and provide the translation results immediately to participants who speak different languages. For example, it can translate a statement made in English into Japanese and display it to Japanese-speaking participants. It can also translate a statement made in French into English and display it to English-speaking participants. Furthermore, by supporting multiple languages, it enables smooth communication even in international meetings. This allows for real-time translation of meeting content and immediate provision of translation results to participants who speak different languages, thereby facilitating smooth communication that transcends language barriers.

[0057] The MTG Agent System can further analyze the content of discussions during meetings, classify them by topic, and display them visually. For example, it can automatically classify the topics discussed during a meeting and organize and display the content of discussions for each topic. It can also visually display the frequency and importance of discussions for each topic using graphs and charts. Furthermore, by summarizing the content of discussions for each topic and providing it to participants, the progress of the meeting can be grasped more clearly. In this way, by analyzing the content of discussions during meetings, classifying them by topic, and displaying them visually, the content of the meeting can be organized in a more understandable way.

[0058] The MTG Agent System can further analyze the content of statements made during meetings, evaluate their reliability, and display it visually. For example, it can classify the reliability of statements into high, medium, and low, and display the reliability of each statement using different colors. It can also visually display the overall trend of statement reliability in the meeting using graphs and charts. Furthermore, it can track changes in the reliability of specific speakers, allowing for an understanding of changes in reliability as the meeting progresses. In this way, by analyzing the content of statements made during meetings, evaluating their reliability, and displaying it visually, the reliability of the meeting content can be understood more clearly.

[0059] The MTG Agent System can further analyze the content of discussions during meetings, evaluate the impact of those discussions, and display it visually. For example, it can classify the impact of discussions into high, medium, and low categories and display the impact of each discussion using different colors. It can also visually display the overall trend of influence of discussions in the meeting using graphs and charts. Furthermore, it can track changes in the influence of specific speakers and understand how their influence changes in the progress of the meeting. In this way, by analyzing the content of discussions during meetings, evaluating the impact of those discussions, and displaying it visually, the impact of the content of the meeting can be understood more clearly.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The document sharing section allows users to share documents that were discussed during the meeting. For example, presentation materials and reports can be shared in real time. The document sharing section allows users to share presentation materials in slide format, reports in PDF format, and notes in text format. Step 2: The question reception team identifies any points of confusion for each participant and provides answers in real time. For example, if a participant has any questions during the meeting, the team will accept them and provide answers in real time using a generative AI. Questions can be submitted in text format or via voice input, and the generative AI will generate answers to those questions. Step 3: The minutes generation unit automatically generates meeting minutes after the meeting. For example, it can automatically generate minutes based on the content of discussions during the meeting and shared documents. It can also use speech recognition technology to convert the content of discussions during the meeting into text and generate the minutes. Furthermore, it can summarize the content of shared documents and discussions and reflect them in the minutes. Step 4: The emotion analysis unit analyzes stakeholders' emotions regarding the meeting minutes. For example, it analyzes stakeholders' emotions from their statements and reactions and reflects them in the minutes. Natural language processing technology can be used to analyze statements and estimate emotions. It can also analyze stakeholders' emotions using facial recognition technology and voice analysis technology.

[0062] (Example of form 2) The MTG Agent System according to an embodiment of the present invention is a system that shares documents discussed in real time during a meeting and identifies points of confusion for each participant to enhance their understanding. The MTG Agent System shares documents discussed during the meeting in real time, identifies points of confusion for each participant, and provides answers in real time. Furthermore, the MTG Agent System automatically generates meeting minutes after the meeting and provides clear information including stakeholders' sentiments (positive or negative) regarding the minutes. For example, the MTG Agent System has a function to share documents such as presentation materials and reports discussed during the meeting in real time. Next, the MTG Agent System has a function to identify points of confusion for each participant and provide answers in real time. In addition, the MTG Agent System has a function to automatically generate meeting minutes after the meeting, and the minutes include stakeholders' sentiments. In this way, by utilizing the MTG Agent System, it becomes possible to share documents during meetings, resolve points of confusion, automatically generate meeting minutes, and analyze sentiment, thereby improving the efficiency of meetings and enhancing understanding. This enables the MTG agent system to share documents during meetings, resolve questions, automatically generate meeting minutes, and perform sentiment analysis, thereby improving meeting efficiency and comprehension.

[0063] The MTG agent system according to this embodiment comprises a document sharing unit, a question receiving unit, a meeting minutes generation unit, and a sentiment analysis unit. The document sharing unit shares documents that were discussed during the meeting. The document sharing unit shares documents such as presentation materials and reports that were discussed during the meeting in real time. For example, the document sharing unit can share presentation materials in slide format. The document sharing unit can also share reports in PDF format. Furthermore, the document sharing unit can also share notes in text format. The question receiving unit captures any unclear points for each participant and provides answers in real time. For example, the question receiving unit accepts questions from participants when they have unclear points during the meeting. For example, the question receiving unit provides answers to participants' questions in real time using a generating AI. For example, the question receiving unit can accept questions from participants in text format and generate answers using a generating AI. For example, the question receiving unit can accept questions from participants using voice input and generate answers using a generating AI. The meeting minutes generation unit automatically generates meeting minutes after the meeting. The minutes generation unit automatically generates meeting minutes based on, for example, the content of statements made during the meeting and shared documents. The minutes generation unit can, for example, use speech recognition technology to convert the content of statements made during the meeting into text and generate the minutes. The minutes generation unit can also, for example, summarize the content of shared documents and reflect them in the minutes. The minutes generation unit can also, for example, summarize the content of statements made during the meeting and reflect them in the minutes. The sentiment analysis unit analyzes the emotions of stakeholders regarding the minutes. The sentiment analysis unit can, for example, analyze the emotions of stakeholders from the content of statements and reactions and reflect them in the minutes. The sentiment analysis unit can, for example, use natural language processing technology to analyze the content of statements and estimate emotions. The sentiment analysis unit can also, for example, use facial recognition technology to analyze the emotions of stakeholders. The sentiment analysis unit can also, for example, use speech analysis technology to analyze the emotions of stakeholders. As a result, the MTG agent system according to this embodiment enables document sharing during meetings, clarification of unclear points, automatic generation of meeting minutes, and sentiment analysis, thereby improving meeting efficiency and comprehension.

[0064] The document sharing function allows users to share documents that come up in discussion during a meeting. Specifically, it has the functionality to share documents such as presentation materials and reports in real time during a meeting. For example, presentation materials can be shared in slide format, allowing participants to view the slides on their own devices while participating in the meeting. Reports can also be shared in PDF format, enabling participants to discuss while reviewing detailed data and graphs. Furthermore, notes can be shared in text format, allowing important points and action items to be recorded in real time during the meeting, ensuring everyone shares the same information. The document sharing function is integrated with cloud storage, making it easy to share documents uploaded before the meeting. Newly created documents and notes during the meeting are also instantly shared, allowing all participants to discuss based on the latest information. As a result, the document sharing function can significantly improve meeting efficiency and promote information sharing and understanding.

[0065] The question reception system captures any points of confusion for each participant and provides answers in real time. Specifically, it has a function to accept questions from participants when they have questions during the meeting. For example, if a participant enters a question in text format, a generative AI will generate an answer in real time. The generative AI can provide appropriate answers based on the meeting content and shared documents. It is also possible to accept questions from participants using voice input, and the generative AI will use speech recognition technology to convert the question into text and generate an answer. The question reception system can analyze the intent of questions using natural language processing technology and provide the most appropriate answer. Furthermore, the question reception system can refer to past meeting data and FAQ databases to provide quick and accurate answers. As a result, the question reception system can immediately resolve participants' doubts and ensure the smooth progress of the meeting. In addition, the question reception system can record the question history of participants and refer to it later, which is useful for post-meeting follow-up and the creation of meeting minutes.

[0066] The meeting minutes generation unit automatically generates meeting minutes after the meeting. Specifically, it has the function to automatically generate meeting minutes based on the content of the discussions during the meeting and the documents shared. For example, it uses speech recognition technology to convert the content of the discussions during the meeting into text and generate the meeting minutes. Speech recognition technology performs highly accurate speech analysis and can accurately record the content of each speaker's remarks. It can also summarize the content of shared documents and reflect it in the meeting minutes. As a result, the meeting minutes generation unit can record all important points and decisions made during the meeting without omission and share them with all participants. Furthermore, the meeting minutes generation unit can also summarize the content of the discussions during the meeting and reflect it in the meeting minutes. Using summarization technology, it can concisely summarize long remarks and complex discussions, improving the readability of the meeting minutes. The meeting minutes generation unit saves the generated meeting minutes to cloud storage, making them accessible to all participants. It also makes the content of the meeting minutes searchable, making it easy to find specific topics and remarks. As a result, the meeting minutes generation unit can streamline post-meeting follow-up and information sharing, maximizing the effectiveness of the meeting.

[0067] The emotion analysis unit analyzes stakeholders' emotions regarding meeting minutes. Specifically, it analyzes stakeholders' emotions from their statements and reactions and reflects them in the minutes. For example, it uses natural language processing technology to analyze statements and estimate emotions. Natural language processing technology can analyze the tone and wording of statements and classify emotions as positive, negative, neutral, etc. It can also analyze stakeholders' emotions using facial recognition technology. Facial recognition technology analyzes camera footage and estimates emotions from stakeholders' facial expressions. Furthermore, it can also analyze stakeholders' emotions using voice analysis technology. Voice analysis technology analyzes the tone, pitch, and speed of voices to estimate emotions. The emotion analysis unit can combine these technologies to perform more accurate emotion analysis. The analyzed emotions are reflected in the meeting minutes and used as reference information to understand the atmosphere of the meeting and the reactions of stakeholders. In this way, the emotion analysis unit can improve the understanding of meetings and participant satisfaction, and support more effective communication.

[0068] The document sharing section allows for the real-time sharing of documents such as presentation materials and reports that were discussed during a meeting. For example, the document sharing section can share presentation materials discussed during the meeting in slide format. It can also share reports in PDF format, for example. It can also share notes in text format, for example. This improves participants' understanding by sharing documents discussed during the meeting in real time. Presentation materials include, but are not limited to, slides, videos, and audio. Reports include, but are not limited to, PDFs, Word documents, and Excel spreadsheets.

[0069] The question reception desk can receive questions from participants during the meeting if they have any questions, and provide answers in real time. For example, the question reception desk can receive questions from participants if they have any questions during the meeting. For example, the question reception desk can use generative AI to provide answers to participants' questions in real time. For example, the question reception desk can receive questions from participants in text format, and generative AI can generate answers to those questions. For example, the question reception desk can receive questions from participants using voice input, and generative AI can generate answers to those questions. This improves participants' understanding by providing answers in real time when they have any questions during the meeting. Questions include, but are not limited to, the format of the question or ambiguity of its content. Real time includes, but is not limited to, a few seconds or a few minutes.

[0070] The minutes generation unit can automatically generate meeting minutes based on the content of discussions during the meeting and shared documents. For example, the minutes generation unit can automatically generate meeting minutes based on the content of discussions during the meeting and shared documents. For example, the minutes generation unit can use speech recognition technology to convert the content of discussions during the meeting into text and generate the minutes. The minutes generation unit can also summarize the content of shared documents and reflect it in the minutes. This streamlines the creation of meeting minutes after the meeting by automatically generating minutes based on the content of discussions during the meeting and shared documents. The content of discussions includes, but is not limited to, speech recognition and manual input. The documents include, but are not limited to, presentation materials, reports, and memos.

[0071] The emotion analysis unit can analyze stakeholders' emotions from their statements and reactions and reflect them in the meeting minutes. For example, the emotion analysis unit can analyze stakeholders' emotions from their statements and reactions and reflect them in the meeting minutes. For example, the emotion analysis unit can analyze statements using natural language processing technology and estimate emotions. For example, the emotion analysis unit can analyze stakeholders' emotions using facial recognition technology. For example, the emotion analysis unit can analyze stakeholders' emotions using voice analysis technology. As a result, by analyzing stakeholders' emotions from their statements and reactions and reflecting them in the meeting minutes, the content of the meeting minutes can be enriched. Emotions include, for example, positive, negative, neutral, etc., but are not limited to these examples. Reactions include, for example, facial expressions, tone of voice, gestures, etc., but are not limited to these examples.

[0072] The document sharing function can estimate participants' emotions and adjust the timing of document sharing based on those estimates. For example, if participants are excited, the document sharing function can immediately share the document to stimulate discussion. If participants are tired, the document sharing function can share the document after a break to deepen understanding. If participants are focused, the document sharing function can share the document at a time that does not disrupt the flow of discussion. This allows for smoother meeting progress by adjusting the timing of document sharing according to participants' emotions. Emotions include, but are not limited to, positive, negative, and neutral. Timing includes, but is not limited to, the progress of the meeting and participants' reactions.

[0073] The document sharing department can prioritize sharing documents based on their importance during the meeting. For example, it might immediately share important presentation materials, share supplementary reports as the discussion progresses, or share reference materials all at once at the end of the meeting. This ensures that important information is shared preferentially by prioritizing sharing based on the importance of the documents discussed during the meeting. Importance may include, but is not limited to, the speaker's title or the relevance of the content.

[0074] The document sharing function can provide customized documents to participants based on their roles and areas of expertise when sharing documents. For example, the document sharing function can provide executives with concise documents, engineers with detailed technical materials, and marketing personnel with market analysis reports. By providing customized documents based on participants' roles and areas of expertise, the function improves participants' understanding. Roles include, but are not limited to, managers, engineers, and assistants. Areas of expertise include, but are not limited to, technology, marketing, and finance.

[0075] The document sharing section can estimate participants' emotions and adjust how the document is displayed based on those estimated emotions. For example, if a participant is nervous, the document sharing section provides a simple display. If a participant is relaxed, the document sharing section provides a display that includes detailed information. If a participant is in a hurry, the document sharing section provides a display that highlights the key points. By adjusting how the document is displayed according to the participant's emotions, the participant's understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. Display methods include, but are not limited to, font size, color, and layout.

[0076] The document sharing function can prioritize sharing highly relevant documents by considering the geographical location of participants when sharing documents. For example, if participants are in different regions, the document sharing function will prioritize sharing documents relevant to each region. For example, if participants are in the same office, the document sharing function will share common documents. For example, if participants are working remotely, the document sharing function will share documents that are accessible online. This improves participants' understanding by prioritizing the sharing of highly relevant documents by considering their geographical location. Geographical location information includes, but is not limited to, GPS data and IP addresses. Highly relevant documents include, but are not limited to, documents with similar content and past usage history.

[0077] The document sharing function can analyze participants' past meeting attendance history and provide relevant documents when sharing documents. For example, the document sharing function can provide relevant documents based on meeting minutes from meetings the participant has previously attended. For example, the document sharing function can provide relevant documents based on reports submitted by the participant in the past. For example, the document sharing function can provide relevant documents based on feedback the participant has previously received. This improves participants' understanding by analyzing their past meeting attendance history and providing relevant documents. Past meeting attendance history includes, but is not limited to, attendance records and statements made. Relevant documents include, but are not limited to, content consistency and past usage history.

[0078] The question reception system can estimate the participant's emotions and adjust the question reception method based on the estimated emotions. For example, if a participant is nervous, the system can provide a simple question format. For example, if a participant is relaxed, the system can provide a detailed question format. For example, if a participant is in a hurry, the system can provide a question format that can be answered quickly. By adjusting the question reception method according to the participant's emotions, the participant's understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. Question reception methods include, but are not limited to, voice input and text input.

[0079] The question reception department can provide the most appropriate answer by referring to the participant's past question history when a question is received. For example, the question reception department can provide relevant answers based on the content of questions the participant has asked in the past. For example, the question reception department can provide answers to common questions from the participant's past question history. For example, the question reception department can analyze the participant's past question history and provide the most appropriate answer. This improves the participant's understanding by providing the most appropriate answer by referring to the participant's past question history. Past question history includes, but is not limited to, the content of the question and the content of the answer. The most appropriate answer includes, but is not limited to, the accuracy and relevance of the content.

[0080] The question reception desk can prioritize questions based on the progress of the meeting. For example, the question reception desk may prioritize questions related to important agenda items of the meeting. For example, the question reception desk may prioritize questions that affect the progress of the meeting. For example, the question reception desk may postpone questions raised near the end of the meeting. In this way, by prioritizing questions based on the progress of the meeting, important questions are handled preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers have spoken. The priority of questions includes, but is not limited to, the importance and urgency of the questions.

[0081] The question reception desk can estimate the participant's emotions and adjust the way the answer is phrased based on the estimated emotions. For example, if the participant is nervous, the question reception desk will provide an answer in a calm manner. For example, if the participant is relaxed, the question reception desk will provide an answer in detail. For example, if the participant is in a hurry, the question reception desk will provide an answer in a concise manner. By adjusting the way the answer is phrased according to the participant's emotions, the participant's understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. The way the answer is phrased includes, but are not limited to, word choice and format.

[0082] The question reception desk can provide customized answers to participants based on their area of ​​expertise and position. For example, the question reception desk can provide answers including technical details to engineers, concise answers to management, and market analysis to marketing personnel. This improves participants' understanding by providing customized answers based on their area of ​​expertise and position. Areas of expertise include, but are not limited to, technology, marketing, and finance. Positions include, but are not limited to, managers, engineers, and assistants.

[0083] The question reception desk can analyze participants' social media activity and provide relevant information when questions are received. For example, the question reception desk can provide relevant information based on what participants have posted on social media. For example, the question reception desk can provide influential information considering the number of followers a participant has on social media. For example, the question reception desk can analyze a participant's social media activity history and provide the most relevant information. This improves participants' understanding by analyzing their social media activity and providing relevant information. Social media activity includes, but is not limited to, posts and follower counts. Relevant information includes, but is not limited to, content consistency and past usage history.

[0084] The minutes generation unit can estimate the emotions of the participants and adjust the presentation of the minutes based on the estimated emotions. For example, if the participants are tense, the minutes generation unit will generate simple and easy-to-read minutes. For example, if the participants are relaxed, the minutes generation unit will generate minutes that include detailed information. For example, if the participants are in a hurry, the minutes generation unit will generate minutes that get straight to the point. By adjusting the presentation of the minutes according to the emotions of the participants, the participants' understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. Presentation of the minutes includes, but are not limited to, wording and formatting.

[0085] The minutes generation unit can adjust the level of detail in the minutes based on the importance of the statements made during the meeting. For example, the minutes generation unit will record important statements in detail. For example, the minutes generation unit will record supplementary statements concisely. For example, the minutes generation unit will record only the main points of statements that are only for reference. In this way, by adjusting the level of detail in the minutes based on the importance of the statements made during the meeting, important information is recorded preferentially. The importance of a statement includes, but is not limited to, the speaker's position and the relevance of the content. The level of detail in the minutes includes, but is not limited to, the degree of summarization and the scope of the recording.

[0086] The minutes generation unit can apply different minutes generation algorithms depending on the category of the meeting when generating minutes. For example, the minutes generation unit applies a minutes generation algorithm that emphasizes technical details to a technical meeting. For example, the minutes generation unit applies a minutes generation algorithm that summarizes key points to a management meeting. For example, the minutes generation unit applies a minutes generation algorithm that includes market analysis to a marketing meeting. This improves the accuracy of the minutes by applying the most suitable minutes generation algorithm according to the category of the meeting. Meeting categories include, but are not limited to, technical meetings, sales meetings, and strategy meetings. Minutes generation algorithms include, but are not limited to, natural language processing and machine learning.

[0087] The minutes generation unit can estimate the emotions of participants and adjust the length of the minutes based on the estimated emotions. For example, if participants are tense, the minutes generation unit will generate short, concise minutes. For example, if participants are relaxed, the minutes generation unit will generate longer minutes with detailed explanations. For example, if participants are in a hurry, the minutes generation unit will generate concise and easy-to-read minutes. By adjusting the length of the minutes according to the emotions of the participants, the participants' understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. The length of the minutes includes, but are not limited to, the number of pages, the number of characters, etc.

[0088] The minutes generation unit can determine the priority of meeting minutes based on the progress of the meeting. For example, the minutes generation unit can prioritize the generation of minutes related to important agenda items of the meeting. For example, the minutes generation unit can prioritize the generation of minutes that affect the progress of the meeting. For example, the minutes generation unit can postpone the generation of minutes issued near the end of the meeting. In this way, by determining the priority of minutes based on the progress of the meeting, important information is recorded preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers spoke. The priority of meeting minutes includes, but is not limited to, the importance and urgency of the content.

[0089] The minutes generation unit can improve the accuracy of the minutes by referring to relevant literature during the generation process. For example, the minutes generation unit can supplement the content of the minutes based on literature referenced during the meeting. For example, the minutes generation unit can improve the accuracy of the minutes by referring to literature related to the meeting agenda. For example, the minutes generation unit can supplement the content of the minutes by referring to literature that influences the progress of the meeting. As a result, the content of the minutes is enriched by improving their accuracy by referring to relevant literature. Relevant literature includes, but is not limited to, past minutes and research papers. The accuracy of the minutes includes, but is not limited to, accuracy and comprehensiveness of content.

[0090] The emotion analysis unit can estimate the participant's emotions and adjust the emotion analysis method based on the estimated emotions. For example, if the participant is nervous, the emotion analysis unit performs a detailed analysis to improve the accuracy of the emotion analysis. For example, if the participant is relaxed, the emotion analysis unit performs a simple emotion analysis. For example, if the participant is in a hurry, the emotion analysis unit performs a rapid emotion analysis. In this way, the accuracy of the emotion analysis is improved by adjusting the emotion analysis method according to the participant's emotions. Emotions include, but are not limited to, positive, negative, and neutral. Emotion analysis methods include, but are not limited to, text analysis and voice analysis.

[0091] The sentiment analysis unit can adjust the level of detail in its sentiment analysis based on the importance of the statements made during the meeting. For example, the sentiment analysis unit can perform a detailed sentiment analysis on important statements. For example, it can perform a simplified sentiment analysis on supplementary statements. For example, it can perform a summary sentiment analysis on statements that are only for reference. By adjusting the level of detail in the sentiment analysis based on the importance of the statements made during the meeting, important information is prioritized for analysis. The importance of statements includes, but is not limited to, the speaker's position and the relevance of the content. The level of detail in the sentiment analysis includes, but is not limited to, the depth and scope of the analysis.

[0092] The sentiment analysis unit can apply different sentiment analysis algorithms depending on the category of the meeting during sentiment analysis. For example, in a technical meeting, the sentiment analysis unit applies a sentiment analysis algorithm for technical statements. For example, in a management meeting, the sentiment analysis unit applies a sentiment analysis algorithm for management statements. For example, in a marketing meeting, the sentiment analysis unit applies a sentiment analysis algorithm for market analysis. This improves the accuracy of sentiment analysis by applying the most appropriate sentiment analysis algorithm according to the category of the meeting. Meeting categories include, but are not limited to, technical meetings, sales meetings, and strategy meetings. Sentiment analysis algorithms include, but are not limited to, natural language processing and machine learning.

[0093] The emotion analysis unit can estimate the participant's emotions and adjust the method of displaying the emotion analysis results based on the estimated emotions. For example, if the participant is nervous, the emotion analysis unit provides a simple and highly visible display method. For example, if the participant is relaxed, the emotion analysis unit provides a display method that includes detailed information. For example, if the participant is in a hurry, the emotion analysis unit provides a concise display method. By adjusting the method of displaying the emotion analysis results according to the participant's emotions, the participant's understanding is improved. Emotions include, but are not limited to, positive, negative, and neutral. Display methods include, but are not limited to, font size, color, and layout.

[0094] The sentiment analysis unit can prioritize sentiment analysis based on the progress of the meeting. For example, the sentiment analysis unit may prioritize sentiment analysis related to important agenda items of the meeting. For example, the sentiment analysis unit may prioritize sentiment analysis that affects the progress of the meeting. For example, the sentiment analysis unit may postpone sentiment analysis submitted near the end of the meeting. By prioritizing sentiment analysis based on the progress of the meeting, important information is analyzed preferentially. The progress of the meeting includes, but is not limited to, the progress of agenda items and the order in which speakers take their place. The priority of sentiment analysis includes, but is not limited to, the importance and urgency of the content.

[0095] The sentiment analysis unit can improve the accuracy of its sentiment analysis by referring to relevant literature for the meeting during the analysis. For example, the sentiment analysis unit can supplement the content of the sentiment analysis based on literature referenced during the meeting. For example, the sentiment analysis unit can improve the accuracy of its sentiment analysis by referring to literature related to the meeting agenda. For example, the sentiment analysis unit can supplement the content of its sentiment analysis by referring to literature that influences the progress of the meeting. In this way, the content of the sentiment analysis is enriched by improving the accuracy of the sentiment analysis by referring to relevant literature for the meeting. Relevant literature includes, but is not limited to, past meeting minutes and research papers. The accuracy of the sentiment analysis includes, but is not limited to, the accuracy and comprehensiveness of the content.

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

[0097] The MTG Agent System can further analyze participants' contributions and generate rankings of speakers based on the frequency and importance of their statements. For example, by analyzing the content of their statements, it can identify the participant who spoke the most during the meeting and display their ranking. It can also evaluate the importance of each participant's contribution and place those who made important statements higher in the rankings. Furthermore, by combining frequency and importance of contributions, it can generate a comprehensive ranking that visualizes each participant's contribution to the meeting's progress. In this way, by analyzing participants' contributions and generating rankings of speakers based on frequency and importance, the progress of the meeting can be understood more clearly.

[0098] The MTG Agent system can also translate meeting content in real time and provide the translation results immediately to participants who speak different languages. For example, it can translate a statement made in English into Japanese and display it to Japanese-speaking participants. It can also translate a statement made in French into English and display it to English-speaking participants. Furthermore, by supporting multiple languages, it enables smooth communication even in international meetings. This allows for real-time translation of meeting content and immediate provision of translation results to participants who speak different languages, thereby facilitating smooth communication that transcends language barriers.

[0099] The MTG Agent System can further analyze the content of discussions during meetings, classify them by topic, and display them visually. For example, it can automatically classify the topics discussed during a meeting and organize and display the content of discussions for each topic. It can also visually display the frequency and importance of discussions for each topic using graphs and charts. Furthermore, by summarizing the content of discussions for each topic and providing it to participants, the progress of the meeting can be grasped more clearly. In this way, by analyzing the content of discussions during meetings, classifying them by topic, and displaying them visually, the content of the meeting can be organized in a more understandable way.

[0100] The MTG Agent System can further analyze the content of statements made during a meeting, evaluate the emotional tone of those statements, and display it visually. For example, it can classify the emotional tone of statements into positive, negative, and neutral, and display each statement with a different color. It can also visually display the overall emotional tone trend of the meeting using graphs and charts. Furthermore, it can track changes in the emotional tone of specific speakers, allowing for an understanding of emotional shifts throughout the meeting. By analyzing the content of statements made during a meeting, evaluating the emotional tone of those statements, and visually displaying it, the system can provide a clearer understanding of the meeting's atmosphere and the emotional state of the participants.

[0101] The MTG Agent System can further analyze the content of statements made during meetings, evaluate their reliability, and display it visually. For example, it can classify the reliability of statements into high, medium, and low, and display the reliability of each statement using different colors. It can also visually display the overall trend of statement reliability in the meeting using graphs and charts. Furthermore, it can track changes in the reliability of specific speakers, allowing for an understanding of changes in reliability as the meeting progresses. In this way, by analyzing the content of statements made during meetings, evaluating their reliability, and displaying it visually, the reliability of the meeting content can be understood more clearly.

[0102] The MTG Agent System can further analyze the content of discussions during meetings, evaluate the impact of those discussions, and display it visually. For example, it can classify the impact of discussions into high, medium, and low categories and display the impact of each discussion using different colors. It can also visually display the overall trend of influence of discussions in the meeting using graphs and charts. Furthermore, it can track changes in the influence of specific speakers and understand how their influence changes in the progress of the meeting. In this way, by analyzing the content of discussions during meetings, evaluating the impact of those discussions, and displaying it visually, the impact of the content of the meeting can be understood more clearly.

[0103] The MTG Agent System can further analyze the content of comments made during a meeting and adjust the meeting's progress based on the emotional tone of those comments. For example, if the emotional tone of a comment is negative, the meeting can be temporarily suspended for a break. Conversely, if the emotional tone is positive, the meeting can be accelerated. Furthermore, if the emotional tone is neutral, the meeting can continue as is. In this way, by analyzing the content of comments made during a meeting and adjusting the meeting's progress based on the emotional tone, a more positive atmosphere can be maintained during the meeting.

[0104] The MTG Agent System can further analyze the content of comments made during meetings and provide feedback to speakers based on the emotional tone of their statements. For example, if the emotional tone of a comment is negative, it can provide feedback encouraging the speaker to express positive emotions. If the emotional tone of a comment is positive, it can provide feedback encouraging the speaker to maintain that tone. Furthermore, if the emotional tone of a comment is neutral, it can provide feedback encouraging the speaker to express specific emotions. By analyzing the content of comments made during meetings and providing feedback to speakers based on the emotional tone of their statements, the system can help maintain a more positive meeting atmosphere.

[0105] The MTG Agent System can further analyze the content of comments made during a meeting and adjust the meeting agenda based on the emotional tone of those comments. For example, if the emotional tone of a comment is negative, the agenda can be changed to a more positive topic. If the emotional tone is positive, the agenda can be continued as is. Furthermore, if the emotional tone is neutral, the agenda can be adjusted to capture the participants' interest. In this way, by analyzing the content of comments made during a meeting and adjusting the agenda based on the emotional tone of those comments, the meeting can proceed more smoothly.

[0106] The MTG Agent System can further analyze the content of comments made during a meeting and adjust the meeting's end time based on the emotional tone of those comments. For example, if the emotional tone of a comment is negative, the meeting can be ended earlier. Conversely, if the emotional tone is positive, the meeting can be ended as scheduled. Furthermore, if the emotional tone is neutral, the end time can be adjusted according to the progress of the meeting. By analyzing the content of comments made during a meeting and adjusting the end time based on the emotional tone of those comments, the system can make meetings run more smoothly.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The document sharing section allows users to share documents that were discussed during the meeting. For example, presentation materials and reports can be shared in real time. The document sharing section allows users to share presentation materials in slide format, reports in PDF format, and notes in text format. Step 2: The question reception team identifies any points of confusion for each participant and provides answers in real time. For example, if a participant has any questions during the meeting, the team will accept them and provide answers in real time using a generative AI. Questions can be submitted in text format or via voice input, and the generative AI will generate answers to those questions. Step 3: The minutes generation unit automatically generates meeting minutes after the meeting. For example, it can automatically generate minutes based on the content of discussions during the meeting and shared documents. It can also use speech recognition technology to convert the content of discussions during the meeting into text and generate the minutes. Furthermore, it can summarize the content of shared documents and discussions and reflect them in the minutes. Step 4: The emotion analysis unit analyzes stakeholders' emotions regarding the meeting minutes. For example, it analyzes stakeholders' emotions from their statements and reactions and reflects them in the minutes. Natural language processing technology can be used to analyze statements and estimate emotions. It can also analyze stakeholders' emotions using facial recognition technology and voice analysis technology.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0112] Each of the multiple elements described above, including the document sharing unit, question receiving unit, meeting minutes generation unit, and sentiment analysis unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the document sharing unit is implemented by the control unit 46A of the smart device 14 and shares documents such as presentation materials and reports that were discussed during the meeting in real time. The question receiving unit is implemented by the specific processing unit 290 of the data processing unit 12 and receives questions from participants and provides answers in real time using generating AI. The meeting minutes generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates meeting minutes based on the content of statements made during the meeting and the documents shared. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the sentiments of stakeholders from the content of statements and reactions and reflects them in the meeting minutes. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0116] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0117] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0119] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0120] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0121] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0122] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0123] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0124] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0127] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the document sharing unit, question reception unit, meeting minutes generation unit, and sentiment analysis unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the document sharing unit is implemented by the control unit 46A of the smart glasses 214 and shares documents such as presentation materials and reports that were discussed during the meeting in real time. The question reception unit is implemented by the specific processing unit 290 of the data processing unit 12 and receives questions from participants and provides answers in real time using generating AI. The meeting minutes generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates meeting minutes based on the content of statements made during the meeting and the documents shared. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the sentiments of stakeholders from the content of statements and reactions and reflects them in the meeting minutes. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the document sharing unit, question reception unit, meeting minutes generation unit, and sentiment analysis unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the document sharing unit is implemented by the control unit 46A of the headset terminal 314 and shares documents such as presentation materials and reports that are discussed during the meeting in real time. The question reception unit is implemented by the specific processing unit 290 of the data processing unit 12 and receives questions from participants and provides answers in real time using a generating AI. The meeting minutes generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates meeting minutes based on the content of statements made during the meeting and the documents shared. The sentiment analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the sentiments of stakeholders from the content of statements and reactions and reflects them in the meeting minutes. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

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

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

[0148] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

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

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

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

[0153] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

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

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

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

[0161] Each of the multiple elements described above, including the document sharing unit, question receiving unit, meeting minutes generation unit, and sentiment analysis unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the document sharing unit is implemented by the control unit 46A of the robot 414 and shares documents such as presentation materials and reports that are discussed during the meeting in real time. The question receiving unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and receives questions from participants and provides answers in real time using generating AI. The meeting minutes generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and automatically generates meeting minutes based on the content of statements made during the meeting and the documents that were shared. The sentiment analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the sentiments of stakeholders from the content of statements and reactions and reflects them in the meeting minutes. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0162] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0164] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0165] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0166] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0170] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0171] 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.

[0172] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0173] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0174] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0175] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0177] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0178] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0179] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0180] (Note 1) The document sharing department shares documents that were discussed during the meeting, A question reception unit that identifies any unclear points for each participant based on the documents shared by the aforementioned document sharing unit and provides answers in real time, A minutes generation unit automatically generates meeting minutes after the meeting based on the points of uncertainty captured by the aforementioned question reception unit, The system includes an emotion analysis unit that analyzes the sentiments of stakeholders regarding the minutes generated by the minutes generation unit. A system characterized by the following features. (Note 2) The aforementioned document sharing unit is Share presentation materials, reports, and other documents that were discussed during the meeting in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned question reception department, If participants have any questions during the meeting, we will accept them and provide answers in real time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned minutes generation unit, The system automatically generates meeting minutes based on the content of discussions during the meeting and shared documents. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned emotion analysis unit, Analyze stakeholders' sentiments based on their statements and reactions, and reflect this in the meeting minutes. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned document sharing unit is The system estimates the participants' emotions and adjusts the timing of document sharing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned document sharing unit is Prioritize sharing documents based on their importance during the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned document sharing unit is When sharing documents, provide customized documents tailored to the participants' roles and areas of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned document sharing unit is The system estimates the participants' emotions and adjusts how the document is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned document sharing unit is When sharing documents, prioritize sharing highly relevant documents by considering the geographical location of participants. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned document sharing unit is When sharing documents, the system analyzes participants' past meeting attendance history and provides relevant documents. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned question reception department, We estimate the participants' emotions and adjust the way questions are asked based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned question reception department, When accepting questions, we refer to the participant's past question history to provide the most appropriate answer. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned question reception department, When questions are accepted, the priority of the questions will be determined according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned question reception department, The system estimates the participants' emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned question reception department, When questions are submitted, we will provide customized answers tailored to the participant's area of ​​expertise and position. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned question reception department, When accepting questions, we will analyze participants' social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned minutes generation unit, We estimate the emotions of the participants and adjust the wording of the meeting minutes based on the estimated emotions of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned minutes generation unit, When generating meeting minutes, the level of detail in the minutes is adjusted based on the importance of the statements made during the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned minutes generation unit, When generating meeting minutes, different minute-generating algorithms are applied depending on the category of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned minutes generation unit, Estimate the participants' emotions and adjust the length of the meeting minutes based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned minutes generation unit, When generating meeting minutes, prioritize the minutes based on the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned minutes generation unit, When generating meeting minutes, we refer to relevant documents related to the meeting to improve the accuracy of the minutes. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned emotion analysis unit, We estimate the participants' emotions and adjust the emotion analysis method based on the estimated emotions of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned emotion analysis unit, During sentiment analysis, the level of detail is adjusted based on the importance of the statements made during the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned emotion analysis unit, When performing sentiment analysis, different sentiment analysis algorithms are applied depending on the category of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned emotion analysis unit, Adjust the method for estimating participants' emotions and displaying the results of the emotion analysis based on the estimated emotions of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned emotion analysis unit, During sentiment analysis, prioritize sentiment analysis based on the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned emotion analysis unit, When performing sentiment analysis, we improve the accuracy of the sentiment analysis by referring to relevant literature from the meeting. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The document sharing department shares documents that were discussed during the meeting, A question reception unit that identifies any unclear points for each participant based on the documents shared by the aforementioned document sharing unit and provides answers in real time, A minutes generation unit automatically generates meeting minutes after the meeting based on the points of uncertainty captured by the aforementioned question reception unit, The system includes an emotion analysis unit that analyzes the sentiments of stakeholders regarding the minutes generated by the minutes generation unit. A system characterized by the following features.

2. The aforementioned document sharing unit is Share presentation materials, reports, and other documents that were discussed during the meeting in real time. The system according to feature 1.

3. The aforementioned question reception department, If participants have any questions during the meeting, we will accept them and provide answers in real time. The system according to feature 1.

4. The aforementioned minutes generation unit, The system automatically generates meeting minutes based on the content of discussions during the meeting and shared documents. The system according to feature 1.

5. The aforementioned emotion analysis unit, Analyze stakeholders' sentiments based on their statements and reactions, and reflect this in the meeting minutes. The system according to feature 1.

6. The aforementioned document sharing unit is The system estimates the participants' emotions and adjusts the timing of document sharing based on those estimated emotions. The system according to feature 1.

7. The aforementioned document sharing unit is Prioritize sharing documents based on their importance during the meeting. The system according to feature 1.

8. The aforementioned document sharing unit is When sharing documents, provide customized documents tailored to the participants' roles and areas of expertise. The system according to feature 1.

Images