System

Abstract

An object of a system according to an embodiment is to improve efficiency of a conference by automatically generating minutes of the conference and providing related information.SOLUTION: A system includes an acquisition part, a minutes creation part, an information provision part, and a real-time provision part. The acquisition unit acquires voice data of a conference. The minutes generation unit converts the voice data acquired by the acquisition unit into text, and automatically generates minutes. The information providing unit analyzes the contents of the minutes generated by the minutes generating unit, and searches for and provides related information. The real-time providing unit provides information according to the progress of the conference based on the information provided by the information providing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have required the creation of meeting minutes and the provision of related information manually, which has led to problems with inefficiency.

[0005] The system according to the embodiment aims to improve the efficiency of meetings by automatically generating minutes of meetings and providing related information. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, a minutes generation unit, an information provision unit, and a real-time provision unit. The acquisition unit acquires audio data of a meeting. The minutes generation unit converts the audio data acquired by the acquisition unit into text and automatically generates minutes. The information provision unit analyzes the contents of the minutes generated by the minutes generation unit and searches for and provides related information. The real-time provision unit provides information according to the progress of the meeting based on the information provided by the information provision unit. [Effects of the Invention]

[0007] The system according to the embodiment can improve the efficiency of meetings by automatically generating minutes of meetings and providing related information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The "Super" Meeting Support System according to an embodiment of the present invention acquires meeting audio data, automatically generates meeting minutes using a generation AI, and provides related information. The "Super" Meeting Support System acquires meeting audio data, automatically generates meeting minutes using a generation AI, and analyzes the minutes to provide related information, thereby facilitating smooth meeting progress and allowing participants to instantly obtain the information they need. For example, the "Super" Meeting Support System acquires audio data from a meeting recording device and inputs it into a generation AI. The generation AI converts the audio data into text and automatically generates meeting minutes. The generation AI then analyzes the automatically generated minutes and searches for and provides relevant information. For example, it searches for and provides past meeting records, related literature, and data related to the agenda. Furthermore, the "Super" Meeting Support System provides relevant information in real time as the meeting progresses. For example, if a new agenda item arises during the discussion, information related to that agenda item is immediately provided. This allows participants to instantly obtain the information they need, improving meeting efficiency. The generation AI is also useful even after the meeting has ended. For example, the agenda for the next meeting can be created based on the minutes automatically generated by the generation AI. This will make preparations for the next meeting more efficient. In this way, the "super" meeting support system automates the creation of meeting minutes, making meetings run smoothly and allowing participants to instantly obtain the information they need. For example, if a new topic comes up during a meeting, the generation AI can instantly provide relevant information, deepening the discussion and improving the quality of the meeting. The generation AI is also useful after the meeting has ended. For example, the agenda for the next meeting can be created based on the minutes automatically generated by the generation AI. This will make preparations for the next meeting more efficient.

[0029] The "ultra" meeting support system according to the embodiment includes an acquisition unit, a minutes generation unit, an information provision unit, and a real-time provision unit. The acquisition unit acquires audio data of a meeting. The audio data of a meeting includes, for example, audio data acquired from a recording device of the meeting, but is not limited to such an example. The acquisition unit acquires audio data from, for example, a recording device of the meeting. The acquisition unit can also acquire audio data using a microphone or a recorder. The acquisition unit can also acquire audio data using recording software. For example, the acquisition unit acquires audio data from a recording device of the meeting and inputs it into a generation AI. The minutes generation unit uses the generation AI to convert the audio data acquired by the acquisition unit into text and automatically generate minutes. The generation AI converts the audio data into text, for example, using a text generation AI (e.g., LLM). The minutes generation unit can also use the generation AI to analyze the audio data and automatically generate minutes. The minutes generation unit can also use the generation AI to extract important parts of the audio data to generate minutes. For example, the generation AI has learned a large amount of voice data and has advanced voice recognition capabilities. The generation AI converts the voice data into text and automatically generates minutes. The information provision unit uses the generation AI to analyze the contents of the minutes generated by the minutes generation unit and search for and provide related information. For example, the information provision unit uses the generation AI to analyze the contents of the minutes and search for related information. The information provision unit can also use the generation AI to provide related information based on the contents of the minutes. The information provision unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI analyzes the contents of the minutes and searches for and provides related past meeting records, related literature, data, etc. The real-time provision unit provides information in real time according to the progress of the meeting based on the information provided by the information provision unit. For example, the real-time provision unit analyzes the progress of the meeting and provides necessary information in real time. The real-time provision unit can also provide related information in real time according to the progress of the meeting. The real-time providing unit can also provide information in real time in accordance with the progress of the conference.For example, the real-time providing unit analyzes the progress of a meeting and provides necessary information in real time. As a result, the "ultra" meeting support system according to the embodiment automates the creation of meeting minutes, smooths the progress of the meeting, and allows participants to instantly obtain necessary information. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can provide information using an AI model that analyzes the progress of a meeting and provides necessary information in real time.

[0030] The acquisition unit can acquire audio data from a conference recording device. The acquisition unit, for example, acquires audio data from the conference recording device. Conference recording devices include, but are not limited to, for example, a microphone, a recorder, and recording software. The acquisition unit, for example, acquires audio data from the conference recording device and inputs it to the generation AI. The acquisition unit can also acquire audio data using a microphone or a recorder. For example, the acquisition unit acquires audio data from the conference recording device and inputs it to the generation AI. By acquiring audio data from the conference recording device, accurate minutes can be created. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI or without AI. For example, the acquisition unit may input the audio data acquired from the conference recording device to the generation AI and cause the generation AI to analyze the audio data.

[0031] The minutes generation unit can convert audio data into text using a generation AI and automatically generate minutes. The minutes generation unit, for example, converts audio data into text using a generation AI and automatically generates minutes. The generation AI converts audio data into text using a text generation AI (e.g., LLM). The minutes generation unit can also analyze audio data and automatically generate minutes using the generation AI. The minutes generation unit can also extract important parts of audio data and generate minutes using the generation AI. For example, the generation AI has learned a large amount of audio data and has advanced speech recognition capabilities. The generation AI converts audio data into text and automatically generates minutes. This makes it possible to convert audio data into text and automatically generate minutes using the generation AI. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input audio data into the generation AI and have the generation AI convert it into text data.

[0032] The information providing unit can analyze the contents of the minutes using the generation AI and search for and provide related information. The information providing unit can, for example, analyze the contents of the minutes using the generation AI and search for related information. The generation AI can, for example, analyze the contents of the minutes using a text generation AI (e.g., LLM). The information providing unit can also use the generation AI to provide related information based on the contents of the minutes. The information providing unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI can analyze the contents of the minutes and search for and provide related past meeting records, related literature, data, etc. This makes it possible to use the generation AI to analyze the contents of the minutes and search for and provide related information. Some or all of the above-mentioned processing in the information providing unit can be performed using, for example, AI, or without AI. For example, the information providing unit can input the contents of the minutes into the generation AI and have the generation AI search for and provide related information.

[0033] The real-time providing unit can provide information in real time according to the progress of the conference. The real-time providing unit, for example, analyzes the progress of the conference and provides necessary information in real time. The real-time providing unit, for example, analyzes the progress of the conference and provides necessary information in real time. The real-time providing unit can also provide related information in real time according to the progress of the conference. The real-time providing unit can also provide information in real time according to the progress of the conference. For example, the real-time providing unit analyzes the progress of the conference and provides necessary information in real time. This improves the efficiency of the conference by providing information in real time according to the progress of the conference. Some or all of the above-described processing in the real-time providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the real-time providing unit can provide information using an AI model that analyzes the progress of the conference and provides necessary information in real time.

[0034] The information providing unit can search for and provide past meeting records, related literature, and data related to the agenda. The information providing unit, for example, uses a generation AI to analyze the contents of the minutes and search for related information. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the contents of the minutes. The information providing unit can also use the generation AI to provide related information based on the contents of the minutes. The information providing unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI analyzes the contents of the minutes and searches for and provides related past meeting records, related literature, data, etc. This improves the quality of the meeting by providing past meeting records, related literature, data, etc. related to the agenda. Some or all of the above-mentioned processing in the information providing unit may be performed, for example, using AI or without AI. For example, the information providing unit can input the contents of the minutes into the generation AI and cause the generation AI to search for and provide related information.

[0035] The acquisition unit can analyze the speech frequency of the conference participants and prioritize acquiring important speech. The acquisition unit, for example, analyzes the speech frequency of the conference participants and prioritizes acquiring important speech. The speech frequency is analyzed, for example, by counting the number of speeches and measuring the speech duration. The acquisition unit, for example, prioritizes acquiring speech from participants who speak frequently. The acquisition unit can also prioritize acquiring speech from participants who speak less frequently but have important positions. The acquisition unit can also combine speech frequency and the importance of the speech content to prioritize acquiring the most important speech. For example, the acquisition unit prioritizes acquiring speech from participants who speak more frequently to avoid missing important speech. In this way, important speech can be prioritized by analyzing the speech frequency. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input speech frequency data to a generation AI and cause the generation AI to identify important speech.

[0036] The acquisition unit can prioritize acquisition of audio data related to a specific agenda item according to the progress of the meeting. The acquisition unit, for example, analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to a specific agenda item. The progress is understood, for example, using the progress of the agenda items, the order of speakers, etc. The acquisition unit, for example, analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to the current agenda item. Furthermore, if the meeting is progressing slowly, the acquisition unit can prioritize acquisition of audio data related to important agenda items. Furthermore, if the meeting is progressing smoothly, the acquisition unit can acquire all audio data evenly. For example, the acquisition unit analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to a specific agenda item. In this way, by acquiring audio data according to the progress of the meeting, information related to important agenda items can be prioritized. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI or without AI. For example, the acquisition unit can input meeting progress data to the generation AI and cause the generation AI to acquire audio data related to a specific agenda item.

[0037] The acquisition unit can automatically remove noise when acquiring audio data to acquire clear audio data. For example, the acquisition unit can automatically remove noise when acquiring audio data to acquire clear audio data. Noise is removed using, for example, a noise filtering algorithm, an audio cleaning technique, or the like. For example, the acquisition unit can automatically filter background noise when acquiring audio data to acquire clear audio data. The acquisition unit can also automatically remove echo when acquiring audio data to acquire clear audio data. The acquisition unit can also automatically remove wind noise when acquiring audio data to acquire clear audio data. For example, the acquisition unit can automatically filter background noise to acquire clear audio data. In this way, clear audio data can be acquired by automatically removing noise. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the acquired audio data to a generation AI and cause the generation AI to perform noise removal.

[0038] The acquisition unit can evaluate the importance of utterances based on the job titles and expertise of the conference participants and select the audio data to acquire. The acquisition unit evaluates the importance of utterances based on, for example, the job titles and expertise of the conference participants and selects the audio data to acquire. Job titles and expertise are evaluated using, for example, job hierarchy, fields of expertise, etc. The acquisition unit, for example, preferentially acquires utterances from participants with higher job titles. The acquisition unit can also preferentially acquire utterances from participants with abundant expertise. The acquisition unit can also preferentially acquire the most important utterances by taking both job titles and expertise into consideration. For example, the acquisition unit preferentially acquires utterances from participants with higher job titles to avoid missing important utterances. In this way, by evaluating the importance of utterances based on job titles and expertise, important utterances can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the job titles and expertise data of the participants to a generation AI and cause the generation AI to evaluate the importance of utterances.

[0039] The acquisition unit can select an optimal audio capture method depending on the location and time of the meeting. The acquisition unit selects the optimal audio capture method depending on, for example, the location and time of the meeting. The location and time of the meeting are evaluated using, for example, indoor and outdoor environments, noise levels depending on the time of the day, etc. The acquisition unit selects an optimal microphone placement depending on, for example, the acoustic characteristics of the conference room. The acquisition unit can also select a time period with less noise depending on the time of the meeting. The acquisition unit can also select an optimal audio capture device depending on the location of the meeting. For example, the acquisition unit selects an optimal microphone placement depending on the acoustic characteristics of the conference room and acquires clear audio data. This allows for the acquisition of better audio data by selecting an optimal audio capture method depending on the location and time of the meeting. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the location and time of the meeting into a generation AI and cause the generation AI to select an optimal audio capture method.

[0040] The acquisition unit can refer to the past speech histories of the conference participants and preferentially acquire highly relevant utterances. The acquisition unit, for example, refers to the past speech histories of the conference participants and preferentially acquires highly relevant utterances. The past speech histories are referenced, for example, using a database of speech content, the frequency and importance of speech, etc. The acquisition unit, for example, preferentially acquires highly relevant utterances from the past speech histories. The acquisition unit can also analyze the past speech histories and preferentially acquire important utterances. The acquisition unit can also compare the past speech histories with the current agenda and preferentially acquire highly relevant utterances. For example, the acquisition unit preferentially acquires highly relevant utterances from the past speech histories to avoid missing important utterances. In this way, by referring to the past speech histories, highly relevant utterances can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input past speech history data to a generation AI and cause the generation AI to identify highly relevant utterances.

[0041] The minutes generation unit can adjust the level of detail of the minutes based on the importance of the audio data. The minutes generation unit adjusts the level of detail of the minutes based on, for example, the importance of the audio data. The importance is evaluated using, for example, the impact of the content of the remarks and the position of the speaker. The minutes generation unit generates detailed minutes based on, for example, important remarks. The minutes generation unit can also generate concise minutes based on remarks with low importance. The minutes generation unit can also generate balanced minutes by combining remarks with high and low importance. For example, the minutes generation unit generates detailed minutes based on important remarks and emphasizes important information. As a result, by adjusting the level of detail of the minutes based on the importance of the audio data, minutes that emphasize important information can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI or without AI. For example, the minutes generation unit can input importance data of the audio data into the generation AI and have the generation AI adjust the level of detail of the minutes.

[0042] The minutes generation unit can apply different minutes generation algorithms depending on the agenda of the meeting. The minutes generation unit applies different minutes generation algorithms depending on, for example, the agenda of the meeting. Agenda topics are evaluated using, for example, the type of agenda, the importance of the agenda, etc. The minutes generation unit generates minutes that make extensive use of technical terminology, for example, for technical topics. The minutes generation unit can also generate minutes that focus on the main points for business topics. The minutes generation unit can also generate minutes that emphasize ideas for creative topics. For example, the minutes generation unit generates minutes that make extensive use of technical terminology for technical topics, emphasizing specialized information. In this way, by applying different minutes generation algorithms depending on the agenda of the meeting, more appropriate minutes can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input agenda data into the generation AI and cause the generation AI to apply different minutes generation algorithms.

[0043] The minutes generation unit can improve the accuracy of the minutes by referring to past minutes generation results. The minutes generation unit, for example, improves the accuracy of the minutes by referring to past minutes generation results. Past minutes generation results are referenced, for example, using a database of past minutes, evaluation criteria for the generation results, etc. The minutes generation unit, for example, analyzes past minutes generation results to improve accuracy. The minutes generation unit can also select an optimal generation algorithm based on past minutes generation results. The minutes generation unit can also improve accuracy by comparing past minutes generation results with the current agenda. For example, the minutes generation unit analyzes past minutes generation results to improve accuracy. In this way, the accuracy of the minutes can be improved by referring to past minutes generation results. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the minutes generation unit can input past minutes generation result data into the generation AI and have the generation AI improve the accuracy of the minutes.

[0044] The minutes generation unit can determine the priority of minutes according to the progress of the meeting. The minutes generation unit determines the priority of minutes according to, for example, the progress of the meeting. The progress is grasped using, for example, the progress of agenda items, the order of speakers, etc. The minutes generation unit, for example, analyzes the progress of the meeting in real time and prioritizes reflecting important agenda items in the minutes. Furthermore, if the meeting is progressing slowly, the minutes generation unit can also prioritize reflecting important agenda items in the minutes. Furthermore, if the meeting is progressing smoothly, the minutes generation unit can generate minutes evenly overall. For example, the minutes generation unit analyzes the progress of the meeting in real time and prioritizes reflecting important agenda items in the minutes. In this way, by determining the priority of minutes according to the progress of the meeting, important information can be prioritized and reflected in the minutes. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI or without AI. For example, the minutes generation unit can input meeting progress data into the generation AI and have the generation AI determine the priority of the minutes.

[0045] The minutes generation unit can adjust the use of technical terms in the minutes according to the expertise levels of the meeting participants. The minutes generation unit adjusts the use of technical terms in the minutes according to, for example, the expertise levels of the meeting participants. The expertise levels are evaluated using, for example, the field of expertise, the depth of knowledge, etc. The minutes generation unit generates minutes that use a lot of technical terms for participants with extensive expertise. The minutes generation unit can also generate concise and easy-to-understand minutes for participants with little expertise. The minutes generation unit can also generate minutes in which the use of technical terms is adjusted according to the level of expertise. For example, the minutes generation unit generates minutes that use a lot of technical terms for participants with extensive expertise, emphasizing technical information. In this way, by adjusting the use of technical terms according to the expertise levels of the meeting participants, more understandable minutes can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input participants' expertise level data into the generation AI and have the generation AI adjust the use of technical terms.

[0046] The minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. The minutes generation unit can automatically extract keywords related to the meeting agenda using, for example, generation AI and reflect them in the minutes. Keywords are extracted using, for example, natural language processing technology, keyword extraction algorithms, etc. The minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. The minutes generation unit can also adjust the content of the minutes based on the importance of the keywords. The minutes generation unit can also adjust the content of the minutes based on the frequency of the keywords. For example, the minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. By automatically extracting keywords related to the meeting agenda, the content of the minutes can be enriched. Some or all of the above-mentioned processing in the minutes generation unit can be performed using, for example, AI, or without AI. For example, the minutes generation unit can input agenda data into the generation AI and have the generation AI extract keywords and reflect them in the minutes.

[0047] The information providing unit can dynamically adjust the search range for related information based on the content of the minutes. The information providing unit dynamically adjusts the search range for related information based on, for example, the content of the minutes. The search range is adjusted using, for example, a database to be searched, a search query setting, etc. The information providing unit broadens the search range for related information based on, for example, the content of the minutes. The information providing unit can also narrow the search range for related information based on the content of the minutes. The information providing unit can also dynamically adjust the optimal search range based on the content of the minutes. For example, the information providing unit broadens the search range for related information based on the content of the minutes. By dynamically adjusting the search range based on the content of the minutes, optimal related information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input content data of the minutes to a generation AI and cause the generation AI to adjust the search range for related information.

[0048] The information providing unit can evaluate the reliability of past meeting records and related literature and provide highly reliable information preferentially. The information providing unit, for example, evaluates the reliability of past meeting records and related literature and provides highly reliable information preferentially. Reliability is evaluated using, for example, information source evaluation criteria, reliability scoring, etc. The information providing unit, for example, evaluates the reliability of past meeting records and provides highly reliable information preferentially. The information providing unit can also evaluate the reliability of related literature and provide highly reliable information preferentially. The information providing unit can also set reliability evaluation criteria to provide highly reliable information preferentially. For example, the information providing unit evaluates the reliability of past meeting records and provides highly reliable information preferentially. This prioritizes the provision of highly reliable information, thereby improving the quality of the meeting. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input data of past meeting records and related literature into a generation AI and cause the generation AI to evaluate reliability and provide information.

[0049] The information providing unit can update necessary information in real time according to the progress of the conference. The information providing unit updates necessary information in real time according to, for example, the progress of the conference. The progress is grasped using, for example, the progress of the agenda, the order of speakers, etc. The information providing unit, for example, analyzes the progress of the conference in real time and updates necessary information. Furthermore, if the progress of the conference is delayed, the information providing unit can also prioritize updating important information. Furthermore, if the conference is progressing smoothly, the information providing unit can evenly update overall information. For example, the information providing unit analyzes the progress of the conference in real time and updates necessary information. In this way, by updating information in real time according to the progress of the conference, the latest information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input conference progress data to the generation AI and cause the generation AI to perform real-time updates of the information.

[0050] The information providing unit can automatically search for and provide the latest research results and technical information related to the meeting agenda. The information providing unit can automatically search for and provide the latest research results and technical information related to the meeting agenda, for example, using a generation AI. The latest research results and technical information are searched for, for example, using a specific database, a search query setting, etc. The information providing unit can automatically search for and provide the latest research results related to the meeting agenda, for example. The information providing unit can also automatically search for and provide the latest technical information related to the meeting agenda. The information providing unit can also automatically search for and provide the latest patent information related to the meeting agenda. For example, the information providing unit can automatically search for and provide the latest research results related to the meeting agenda. This improves the quality of the meeting by providing the latest research results and technical information. Some or all of the above-mentioned processing in the information providing unit can be performed, for example, using AI or without AI. For example, the information providing unit can input agenda data into the generation AI and cause the generation AI to search for and provide the latest research results and technical information.

[0051] The information providing unit can adjust the level of detail of the information to be provided according to the expertise of the conference participants. The information providing unit adjusts the level of detail of the information to be provided according to, for example, the expertise of the conference participants. Expertise is evaluated using, for example, the field of expertise, the depth of knowledge, etc. The information providing unit, for example, provides detailed information to participants with extensive expertise. The information providing unit can also provide concise and easy-to-understand information to participants with little expertise. The information providing unit can also adjust the level of detail of the information according to the level of expertise. For example, the information providing unit provides detailed information to participants with extensive expertise and emphasizes specialized information. In this way, by adjusting the level of detail of the information according to the participants' expertise, more understandable information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input the participants' expertise data to a generation AI and cause the generation AI to adjust the level of detail of the information.

[0052] The information providing unit can provide related visual data and graphs according to the progress of the meeting. The information providing unit provides related visual data and graphs, for example, according to the progress of the meeting. The progress is understood using, for example, the progress of agenda items, the order of speakers, etc. The information providing unit, for example, analyzes the progress of the meeting in real time and provides related visual data. Furthermore, if the progress of the meeting is delayed, the information providing unit can prioritize providing important visual data. Furthermore, if the progress of the meeting is smooth, the information providing unit can provide overall visual data evenly. For example, the information providing unit analyzes the progress of the meeting in real time and provides related visual data. As a result, by providing visual data and graphs according to the progress of the meeting, it is possible to provide information that is visually easy to understand. Some or all of the above-mentioned processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input conference progress data to a generation AI and cause the generation AI to provide visual data and graphs.

[0053] The real-time providing unit can dynamically adjust the content of the information to be provided in real time according to the progress of the conference. The real-time providing unit dynamically adjusts the content of the information to be provided in real time, for example, according to the progress of the conference. The progress is grasped, for example, using the progress of the agenda, the order of speakers, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and dynamically adjusts the necessary information. Furthermore, if the progress of the conference is delayed, the real-time providing unit can prioritize and provide important information in real time. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information evenly in real time. For example, the real-time providing unit analyzes the progress of the conference in real time and dynamically adjusts the necessary information. In this way, by dynamically adjusting the content of the information according to the progress of the conference, optimal information can be provided in real time. Some or all of the above-described processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to dynamically adjust the content of the information.

[0054] The real-time providing unit can analyze the content of statements made by conference participants in real time and provide relevant information instantly. The real-time providing unit can, for example, analyze the content of statements made by conference participants in real time and provide relevant information instantly. The content of statements is analyzed using, for example, natural language processing technology, speech recognition technology, etc. The real-time providing unit can, for example, analyze the content of statements made by conference participants in real time and provide relevant information instantly. The real-time providing unit can also instantly provide related literature and data based on the content of statements made by conference participants. The real-time providing unit can also instantly provide relevant past meeting records based on the content of statements made by conference participants. For example, the real-time providing unit can analyze the content of statements made by conference participants in real time and provide relevant information instantly. In this way, by analyzing the content of statements made by conference participants in real time, relevant information can be instantly provided. Some or all of the above-mentioned processing in the real-time providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the real-time providing unit can input content data of statements to a generation AI and cause the generation AI to instantly provide relevant information.

[0055] The real-time providing unit can filter and provide necessary information in real time according to the progress of the meeting. The real-time providing unit, for example, analyzes the progress of the meeting in real time and filters and provides the necessary information. The progress is grasped, for example, using the progress of the agenda, the importance of the content of the remarks, etc. The real-time providing unit, for example, analyzes the progress of the meeting in real time and filters and provides the necessary information. Furthermore, when the progress of the meeting is delayed, the real-time providing unit can preferentially filter and provide important information. Furthermore, when the progress of the meeting is smooth, the real-time providing unit can evenly filter and provide all the information. For example, the real-time providing unit analyzes the progress of the meeting in real time and filters and provides the necessary information. In this way, important information can be preferentially provided by filtering information according to the progress of the meeting. Some or all of the above-mentioned processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to filter the information.

[0056] The real-time providing unit can select the format of information to be provided in real time (e.g., text, audio, visual) depending on the progress of the conference. The real-time providing unit selects the format of information to be provided in real time depending on, for example, the progress of the conference. The progress is grasped using, for example, the progress of the agenda, the order of speakers, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and selects the optimal information format. Furthermore, if the conference is progressing slowly, the real-time providing unit can provide important information in text format. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information in visual format. For example, the real-time providing unit analyzes the progress of the conference in real time and selects the optimal information format. In this way, by selecting the information format depending on the progress of the conference, information can be provided in the optimal format. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to select the information format.

[0057] The real-time providing unit can adjust the level of detail of the information to be provided in real time based on the position and expertise of the conference participants. The real-time providing unit adjusts the level of detail of the information to be provided in real time based on, for example, the position and expertise of the conference participants. The position and expertise are evaluated using, for example, the position hierarchy, the field of expertise, etc. The real-time providing unit, for example, provides detailed information in real time to participants with high position. The real-time providing unit can also provide detailed information in real time to participants with extensive expertise. The real-time providing unit can also provide optimal information in real time by taking both the position and expertise into consideration. For example, the real-time providing unit provides detailed information in real time to participants with high position and emphasizes specialized information. In this way, by adjusting the level of detail of the information based on the position and expertise of the participants, more understandable information can be provided in real time. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can input the position and expertise data of the participants to the generation AI and cause the generation AI to adjust the level of detail of the information.

[0058] The real-time providing unit can acquire and provide information in real time from a related external database according to the progress of the conference. The real-time providing unit, for example, analyzes the progress of the conference in real time and acquires information from the related external database. The progress is grasped using, for example, the progress of the agenda, the importance of the content of the remarks, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and acquires information from the related external database. Furthermore, if the progress of the conference is delayed, the real-time providing unit can also prioritize acquiring important information from the external database. Furthermore, if the conference is progressing smoothly, the real-time providing unit can evenly acquire overall information from the external database. For example, the real-time providing unit analyzes the progress of the conference in real time and acquires information from the related external database. In this way, by acquiring information from the external database according to the progress of the conference, the latest information can be provided in real time. Some or all of the above-mentioned processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to the generation AI and cause the generation AI to acquire information from the external database.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The acquisition unit can analyze the content of statements made by meeting participants in real time and evaluate the importance of the statements. For example, the acquisition unit can analyze the content of statements using natural language processing technology and extract important keywords and phrases. The acquisition unit can also evaluate the importance of statements based on the speaker's position and expertise. Furthermore, the acquisition unit can prioritize acquisition of important statements according to the progress of the meeting. In this way, the acquisition unit can improve the quality of the meeting by analyzing the content of statements made by meeting participants in real time and prioritizing acquisition of important statements.

[0061] The minutes generation unit can analyze the content of statements made by meeting participants in real time and adjust the level of detail in the minutes based on the importance of the statements. For example, the minutes generation unit can analyze the content of statements using natural language processing technology and extract important keywords and phrases. The minutes generation unit can also evaluate the importance of statements based on the speaker's position and expertise, and generate detailed minutes based on important statements. Furthermore, the minutes generation unit can also prioritize reflecting important statements in the minutes depending on the progress of the meeting. In this way, the minutes generation unit can improve the quality of the minutes by analyzing the content of statements made by meeting participants in real time and prioritize reflecting important statements in the minutes.

[0062] The information providing unit can analyze the content of statements made by meeting participants in real time and provide relevant information immediately. For example, the information providing unit can analyze the content of statements using natural language processing technology and extract related keywords and phrases. The information providing unit can also instantly provide related literature and data based on the content of statements. Furthermore, the information providing unit can instantly provide related past meeting records based on the content of statements. In this way, the information providing unit can improve the quality of meetings by analyzing the content of statements made by meeting participants in real time and providing related information immediately.

[0063] The real-time providing unit can dynamically adjust the content of the information to be provided in real time according to the progress of the conference. For example, the real-time providing unit analyzes the progress of the conference in real time and dynamically adjusts the necessary information. Furthermore, if the conference is progressing slowly, the real-time providing unit can prioritize and provide important information in real time. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information evenly in real time. In this way, the real-time providing unit can dynamically adjust the content of the information according to the progress of the conference, thereby providing optimal information in real time.

[0064] The real-time providing unit can analyze the content of statements made by meeting participants in real time and provide related information instantly. For example, the real-time providing unit can analyze the content of statements using natural language processing technology and extract related keywords and phrases. The real-time providing unit can also instantly provide related literature and data based on the content of statements. Furthermore, the real-time providing unit can instantly provide related past meeting records based on the content of statements. In this way, the real-time providing unit can improve the quality of meetings by analyzing the content of statements made by meeting participants in real time and providing related information instantly.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The acquisition unit acquires audio data of the conference. The audio data of the conference includes, but is not limited to, audio data acquired from a recording device of the conference. The acquisition unit can also acquire audio data using a microphone, a recorder, or recording software. Step 2: The minutes generation unit converts the audio data acquired by the acquisition unit into text using a generation AI and automatically generates minutes. The generation AI can also convert audio data into text using a text generation AI (e.g., LLM) and extract important parts of the audio data to generate minutes. Step 3: The information provision unit uses the generation AI to analyze the contents of the minutes generated by the minutes generation unit, and searches for and provides related information. The generation AI analyzes the contents of the minutes, and searches for and provides related past meeting records, related literature, data, etc. Step 4: The real-time providing unit provides information in real time according to the progress of the conference based on the information provided by the information providing unit. The real-time providing unit can analyze the progress of the conference and provide necessary information in real time.

[0067] (Example 2) The "Super" Meeting Support System according to an embodiment of the present invention acquires meeting audio data, automatically generates meeting minutes using a generation AI, and provides related information. The "Super" Meeting Support System acquires meeting audio data, automatically generates meeting minutes using a generation AI, and analyzes the minutes to provide related information, thereby facilitating smooth meeting progress and allowing participants to instantly obtain the information they need. For example, the "Super" Meeting Support System acquires audio data from a meeting recording device and inputs it into a generation AI. The generation AI converts the audio data into text and automatically generates meeting minutes. The generation AI then analyzes the automatically generated minutes and searches for and provides relevant information. For example, it searches for and provides past meeting records, related literature, and data related to the agenda. Furthermore, the "Super" Meeting Support System provides relevant information in real time as the meeting progresses. For example, if a new agenda item arises during the discussion, information related to that agenda item is immediately provided. This allows participants to instantly obtain the information they need, improving meeting efficiency. The generation AI is also useful even after the meeting has ended. For example, the agenda for the next meeting can be created based on the minutes automatically generated by the generation AI. This will make preparations for the next meeting more efficient. In this way, the "super" meeting support system automates the creation of meeting minutes, making meetings run smoothly and allowing participants to instantly obtain the information they need. For example, if a new topic comes up during a meeting, the generation AI can instantly provide relevant information, deepening the discussion and improving the quality of the meeting. The generation AI is also useful after the meeting has ended. For example, the agenda for the next meeting can be created based on the minutes automatically generated by the generation AI. This will make preparations for the next meeting more efficient.

[0068] The "ultra" meeting support system according to the embodiment includes an acquisition unit, a minutes generation unit, an information provision unit, and a real-time provision unit. The acquisition unit acquires audio data of a meeting. The audio data of a meeting includes, for example, audio data acquired from a recording device of the meeting, but is not limited to such an example. The acquisition unit acquires audio data from, for example, a recording device of the meeting. The acquisition unit can also acquire audio data using a microphone or a recorder. The acquisition unit can also acquire audio data using recording software. For example, the acquisition unit acquires audio data from a recording device of the meeting and inputs it into a generation AI. The minutes generation unit uses the generation AI to convert the audio data acquired by the acquisition unit into text and automatically generate minutes. The generation AI converts the audio data into text, for example, using a text generation AI (e.g., LLM). The minutes generation unit can also use the generation AI to analyze the audio data and automatically generate minutes. The minutes generation unit can also use the generation AI to extract important parts of the audio data to generate minutes. For example, the generation AI has learned a large amount of voice data and has advanced voice recognition capabilities. The generation AI converts the voice data into text and automatically generates minutes. The information provision unit uses the generation AI to analyze the contents of the minutes generated by the minutes generation unit and search for and provide related information. For example, the information provision unit uses the generation AI to analyze the contents of the minutes and search for related information. The information provision unit can also use the generation AI to provide related information based on the contents of the minutes. The information provision unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI analyzes the contents of the minutes and searches for and provides related past meeting records, related literature, data, etc. The real-time provision unit provides information in real time according to the progress of the meeting based on the information provided by the information provision unit. For example, the real-time provision unit analyzes the progress of the meeting and provides necessary information in real time. The real-time provision unit can also provide related information in real time according to the progress of the meeting. The real-time providing unit can also provide information in real time in accordance with the progress of the conference.For example, the real-time providing unit analyzes the progress of a meeting and provides necessary information in real time. As a result, the "ultra" meeting support system according to the embodiment automates the creation of meeting minutes, smooths the progress of the meeting, and allows participants to instantly obtain necessary information. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can provide information using an AI model that analyzes the progress of a meeting and provides necessary information in real time.

[0069] The acquisition unit can acquire audio data from a conference recording device. The acquisition unit, for example, acquires audio data from the conference recording device. Conference recording devices include, but are not limited to, for example, a microphone, a recorder, and recording software. The acquisition unit, for example, acquires audio data from the conference recording device and inputs it to the generation AI. The acquisition unit can also acquire audio data using a microphone or a recorder. For example, the acquisition unit acquires audio data from the conference recording device and inputs it to the generation AI. By acquiring audio data from the conference recording device, accurate minutes can be created. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI or without AI. For example, the acquisition unit may input the audio data acquired from the conference recording device to the generation AI and cause the generation AI to analyze the audio data.

[0070] The minutes generation unit can convert audio data into text using a generation AI and automatically generate minutes. The minutes generation unit, for example, converts audio data into text using a generation AI and automatically generates minutes. The generation AI converts audio data into text using a text generation AI (e.g., LLM). The minutes generation unit can also analyze audio data and automatically generate minutes using the generation AI. The minutes generation unit can also extract important parts of audio data and generate minutes using the generation AI. For example, the generation AI has learned a large amount of audio data and has advanced speech recognition capabilities. The generation AI converts audio data into text and automatically generates minutes. This makes it possible to convert audio data into text and automatically generate minutes using the generation AI. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input audio data into the generation AI and have the generation AI convert it into text data.

[0071] The information providing unit can analyze the contents of the minutes using the generation AI and search for and provide related information. The information providing unit can, for example, analyze the contents of the minutes using the generation AI and search for related information. The generation AI can, for example, analyze the contents of the minutes using a text generation AI (e.g., LLM). The information providing unit can also use the generation AI to provide related information based on the contents of the minutes. The information providing unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI can analyze the contents of the minutes and search for and provide related past meeting records, related literature, data, etc. This makes it possible to use the generation AI to analyze the contents of the minutes and search for and provide related information. Some or all of the above-mentioned processing in the information providing unit can be performed using, for example, AI, or without AI. For example, the information providing unit can input the contents of the minutes into the generation AI and have the generation AI search for and provide related information.

[0072] The real-time providing unit can provide information in real time according to the progress of the conference. The real-time providing unit, for example, analyzes the progress of the conference and provides necessary information in real time. The real-time providing unit, for example, analyzes the progress of the conference and provides necessary information in real time. The real-time providing unit can also provide related information in real time according to the progress of the conference. The real-time providing unit can also provide information in real time according to the progress of the conference. For example, the real-time providing unit analyzes the progress of the conference and provides necessary information in real time. This improves the efficiency of the conference by providing information in real time according to the progress of the conference. Some or all of the above-described processing in the real-time providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the real-time providing unit can provide information using an AI model that analyzes the progress of the conference and provides necessary information in real time.

[0073] The information providing unit can search for and provide past meeting records, related literature, and data related to the agenda. The information providing unit, for example, uses a generation AI to analyze the contents of the minutes and search for related information. The generation AI, for example, uses a text generation AI (e.g., LLM) to analyze the contents of the minutes. The information providing unit can also use the generation AI to provide related information based on the contents of the minutes. The information providing unit can also use the generation AI to analyze the contents of the minutes and provide related information. For example, the generation AI analyzes the contents of the minutes and searches for and provides related past meeting records, related literature, data, etc. This improves the quality of the meeting by providing past meeting records, related literature, data, etc. related to the agenda. Some or all of the above-mentioned processing in the information providing unit may be performed, for example, using AI or without AI. For example, the information providing unit can input the contents of the minutes into the generation AI and cause the generation AI to search for and provide related information.

[0074] The acquisition unit can estimate a user's emotion and adjust the timing of voice data acquisition based on the estimated user emotion. The acquisition unit, for example, estimates a user's emotion and adjusts the timing of voice data acquisition based on the estimated user emotion. The user's emotion is estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, if the user is nervous, the acquisition unit adjusts the acquisition so that important parts of a meeting are prioritized. Furthermore, if the user is relaxed, the acquisition unit can adjust the acquisition so that overall voice data is acquired evenly. Furthermore, if the user is in a hurry, the acquisition unit can adjust the acquisition so that key points are prioritized. For example, the acquisition unit monitors the user's emotion in real time and adjusts the timing of voice data acquisition according to changes in emotion. This allows for more appropriate voice data to be acquired by adjusting the timing of voice data acquisition based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input user emotion data to the generation AI and cause the generation AI to adjust the timing of acquiring voice data based on the emotion.

[0075] The acquisition unit can analyze the speech frequency of the conference participants and prioritize acquiring important speech. The acquisition unit, for example, analyzes the speech frequency of the conference participants and prioritizes acquiring important speech. The speech frequency is analyzed, for example, by counting the number of speeches and measuring the speech duration. The acquisition unit, for example, prioritizes acquiring speech from participants who speak frequently. The acquisition unit can also prioritize acquiring speech from participants who speak less frequently but have important positions. The acquisition unit can also combine speech frequency and the importance of the speech content to prioritize acquiring the most important speech. For example, the acquisition unit prioritizes acquiring speech from participants who speak more frequently to avoid missing important speech. In this way, important speech can be prioritized by analyzing the speech frequency. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input speech frequency data to a generation AI and cause the generation AI to identify important speech.

[0076] The acquisition unit can prioritize acquisition of audio data related to a specific agenda item according to the progress of the meeting. The acquisition unit, for example, analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to a specific agenda item. The progress is understood, for example, using the progress of the agenda items, the order of speakers, etc. The acquisition unit, for example, analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to the current agenda item. Furthermore, if the meeting is progressing slowly, the acquisition unit can prioritize acquisition of audio data related to important agenda items. Furthermore, if the meeting is progressing smoothly, the acquisition unit can acquire all audio data evenly. For example, the acquisition unit analyzes the progress of the meeting in real time and prioritizes acquisition of audio data related to a specific agenda item. In this way, by acquiring audio data according to the progress of the meeting, information related to important agenda items can be prioritized. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI or without AI. For example, the acquisition unit can input meeting progress data to the generation AI and cause the generation AI to acquire audio data related to a specific agenda item.

[0077] The acquisition unit can automatically remove noise when acquiring audio data to acquire clear audio data. For example, the acquisition unit can automatically remove noise when acquiring audio data to acquire clear audio data. Noise is removed using, for example, a noise filtering algorithm, an audio cleaning technique, or the like. For example, the acquisition unit can automatically filter background noise when acquiring audio data to acquire clear audio data. The acquisition unit can also automatically remove echo when acquiring audio data to acquire clear audio data. The acquisition unit can also automatically remove wind noise when acquiring audio data to acquire clear audio data. For example, the acquisition unit can automatically filter background noise to acquire clear audio data. In this way, clear audio data can be acquired by automatically removing noise. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the acquired audio data to a generation AI and cause the generation AI to perform noise removal.

[0078] The acquisition unit can estimate the user's emotions and determine the priority of the voice data to be acquired based on the estimated user emotions. The acquisition unit, for example, estimates the user's emotions and determines the priority of the voice data to be acquired based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, when the user is nervous, the acquisition unit prioritizes acquiring important statements. Furthermore, when the user is relaxed, the acquisition unit can evenly acquire overall voice data. Furthermore, when the user is in a hurry, the acquisition unit can prioritize acquiring voice data that highlights the main points. For example, the acquisition unit monitors the user's emotions in real time and determines the priority of the voice data according to changes in emotions. Thus, by prioritizing the voice data based on the user's emotions, important voice data can be preferentially acquired. The emotion estimation is realized using, for example, an emotion engine or a generation AI, using an emotion estimation function. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input user emotion data to the generation AI and cause the generation AI to determine the priority of voice data based on emotion.

[0079] The acquisition unit can evaluate the importance of utterances based on the job titles and expertise of the conference participants and select the audio data to acquire. The acquisition unit evaluates the importance of utterances based on, for example, the job titles and expertise of the conference participants and selects the audio data to acquire. Job titles and expertise are evaluated using, for example, job hierarchy, fields of expertise, etc. The acquisition unit, for example, preferentially acquires utterances from participants with higher job titles. The acquisition unit can also preferentially acquire utterances from participants with abundant expertise. The acquisition unit can also preferentially acquire the most important utterances by taking both job titles and expertise into consideration. For example, the acquisition unit preferentially acquires utterances from participants with higher job titles to avoid missing important utterances. In this way, by evaluating the importance of utterances based on job titles and expertise, important utterances can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the job titles and expertise data of the participants to a generation AI and cause the generation AI to evaluate the importance of utterances.

[0080] The acquisition unit can select an optimal audio capture method depending on the location and time of the meeting. The acquisition unit selects the optimal audio capture method depending on, for example, the location and time of the meeting. The location and time of the meeting are evaluated using, for example, indoor and outdoor environments, noise levels depending on the time of the day, etc. The acquisition unit selects an optimal microphone placement depending on, for example, the acoustic characteristics of the conference room. The acquisition unit can also select a time period with less noise depending on the time of the meeting. The acquisition unit can also select an optimal audio capture device depending on the location of the meeting. For example, the acquisition unit selects an optimal microphone placement depending on the acoustic characteristics of the conference room and acquires clear audio data. This allows for the acquisition of better audio data by selecting an optimal audio capture method depending on the location and time of the meeting. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input data on the location and time of the meeting into a generation AI and cause the generation AI to select an optimal audio capture method.

[0081] The acquisition unit can refer to the past speech histories of the conference participants and preferentially acquire highly relevant utterances. The acquisition unit, for example, refers to the past speech histories of the conference participants and preferentially acquires highly relevant utterances. The past speech histories are referenced, for example, using a database of speech content, the frequency and importance of speech, etc. The acquisition unit, for example, preferentially acquires highly relevant utterances from the past speech histories. The acquisition unit can also analyze the past speech histories and preferentially acquire important utterances. The acquisition unit can also compare the past speech histories with the current agenda and preferentially acquire highly relevant utterances. For example, the acquisition unit preferentially acquires highly relevant utterances from the past speech histories to avoid missing important utterances. In this way, by referring to the past speech histories, highly relevant utterances can be preferentially acquired. Some or all of the above-described processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input past speech history data to a generation AI and cause the generation AI to identify highly relevant utterances.

[0082] The minutes generation unit can estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user emotions. The minutes generation unit, for example, estimates the user's emotions and adjusts the presentation style of the minutes based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, if the user is nervous, the minutes generation unit generates concise and to-the-point minutes. The minutes generation unit can also generate detailed minutes if the user is relaxed. The minutes generation unit can also generate minutes that emphasize the main points if the user is in a hurry. For example, the minutes generation unit monitors the user's emotions in real time and adjusts the presentation style of the minutes according to changes in emotions. This allows for more appropriate minutes to be generated by adjusting the presentation style of the minutes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the minutes generation unit may be performed using AI, for example, or may be performed without using AI. For example, the minutes generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the expression method of the minutes based on the emotion.

[0083] The minutes generation unit can adjust the level of detail of the minutes based on the importance of the audio data. The minutes generation unit adjusts the level of detail of the minutes based on, for example, the importance of the audio data. The importance is evaluated using, for example, the impact of the content of the remarks and the position of the speaker. The minutes generation unit generates detailed minutes based on, for example, important remarks. The minutes generation unit can also generate concise minutes based on remarks with low importance. The minutes generation unit can also generate balanced minutes by combining remarks with high and low importance. For example, the minutes generation unit generates detailed minutes based on important remarks and emphasizes important information. As a result, by adjusting the level of detail of the minutes based on the importance of the audio data, minutes that emphasize important information can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI or without AI. For example, the minutes generation unit can input importance data of the audio data into the generation AI and have the generation AI adjust the level of detail of the minutes.

[0084] The minutes generation unit can apply different minutes generation algorithms depending on the agenda of the meeting. The minutes generation unit applies different minutes generation algorithms depending on, for example, the agenda of the meeting. Agenda topics are evaluated using, for example, the type of agenda, the importance of the agenda, etc. The minutes generation unit generates minutes that make extensive use of technical terminology, for example, for technical topics. The minutes generation unit can also generate minutes that focus on the main points for business topics. The minutes generation unit can also generate minutes that emphasize ideas for creative topics. For example, the minutes generation unit generates minutes that make extensive use of technical terminology for technical topics, emphasizing specialized information. In this way, by applying different minutes generation algorithms depending on the agenda of the meeting, more appropriate minutes can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input agenda data into the generation AI and cause the generation AI to apply different minutes generation algorithms.

[0085] The minutes generation unit can improve the accuracy of the minutes by referring to past minutes generation results. The minutes generation unit, for example, improves the accuracy of the minutes by referring to past minutes generation results. Past minutes generation results are referenced, for example, using a database of past minutes, evaluation criteria for the generation results, etc. The minutes generation unit, for example, analyzes past minutes generation results to improve accuracy. The minutes generation unit can also select an optimal generation algorithm based on past minutes generation results. The minutes generation unit can also improve accuracy by comparing past minutes generation results with the current agenda. For example, the minutes generation unit analyzes past minutes generation results to improve accuracy. In this way, the accuracy of the minutes can be improved by referring to past minutes generation results. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the minutes generation unit can input past minutes generation result data into the generation AI and have the generation AI improve the accuracy of the minutes.

[0086] The minutes generation unit can estimate the user's emotions and adjust the length of the minutes based on the estimated user emotions. The minutes generation unit, for example, estimates the user's emotions and adjusts the length of the minutes based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, if the user is nervous, the minutes generation unit generates short, concise minutes. The minutes generation unit can also generate detailed minutes if the user is relaxed. The minutes generation unit can also generate concise minutes if the user is in a hurry. For example, the minutes generation unit monitors the user's emotions in real time and adjusts the length of the minutes according to changes in emotions. This allows for more appropriate minutes to be generated by adjusting the length of the minutes based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit may input user emotion data into the generation AI and cause the generation AI to adjust the length of the minutes based on the emotion.

[0087] The minutes generation unit can determine the priority of minutes according to the progress of the meeting. The minutes generation unit determines the priority of minutes according to, for example, the progress of the meeting. The progress is grasped using, for example, the progress of agenda items, the order of speakers, etc. The minutes generation unit, for example, analyzes the progress of the meeting in real time and prioritizes reflecting important agenda items in the minutes. Furthermore, if the meeting is progressing slowly, the minutes generation unit can also prioritize reflecting important agenda items in the minutes. Furthermore, if the meeting is progressing smoothly, the minutes generation unit can generate minutes evenly overall. For example, the minutes generation unit analyzes the progress of the meeting in real time and prioritizes reflecting important agenda items in the minutes. In this way, by determining the priority of minutes according to the progress of the meeting, important information can be prioritized and reflected in the minutes. Some or all of the above-mentioned processing in the minutes generation unit may be performed, for example, using AI or without AI. For example, the minutes generation unit can input meeting progress data into the generation AI and have the generation AI determine the priority of the minutes.

[0088] The minutes generation unit can adjust the use of technical terms in the minutes according to the expertise levels of the meeting participants. The minutes generation unit adjusts the use of technical terms in the minutes according to, for example, the expertise levels of the meeting participants. The expertise levels are evaluated using, for example, the field of expertise, the depth of knowledge, etc. The minutes generation unit generates minutes that use a lot of technical terms for participants with extensive expertise. The minutes generation unit can also generate concise and easy-to-understand minutes for participants with little expertise. The minutes generation unit can also generate minutes in which the use of technical terms is adjusted according to the level of expertise. For example, the minutes generation unit generates minutes that use a lot of technical terms for participants with extensive expertise, emphasizing technical information. In this way, by adjusting the use of technical terms according to the expertise levels of the meeting participants, more understandable minutes can be generated. Some or all of the above-mentioned processing in the minutes generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the minutes generation unit can input participants' expertise level data into the generation AI and have the generation AI adjust the use of technical terms.

[0089] The minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. The minutes generation unit can automatically extract keywords related to the meeting agenda using, for example, generation AI and reflect them in the minutes. Keywords are extracted using, for example, natural language processing technology, keyword extraction algorithms, etc. The minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. The minutes generation unit can also adjust the content of the minutes based on the importance of the keywords. The minutes generation unit can also adjust the content of the minutes based on the frequency of the keywords. For example, the minutes generation unit can automatically extract keywords related to the meeting agenda and reflect them in the minutes. By automatically extracting keywords related to the meeting agenda, the content of the minutes can be enriched. Some or all of the above-mentioned processing in the minutes generation unit can be performed using, for example, AI, or without AI. For example, the minutes generation unit can input agenda data into the generation AI and have the generation AI extract keywords and reflect them in the minutes.

[0090] The information providing unit can estimate the user's emotions and determine the priority of information to be provided based on the estimated user emotions. The information providing unit, for example, estimates the user's emotions and determines the priority of information to be provided based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, when the user is nervous, the information providing unit can prioritize providing important information. Furthermore, when the user is relaxed, the information providing unit can also provide general information evenly. Furthermore, when the user is in a hurry, the information providing unit can prioritize providing information that focuses on the main points. For example, the information providing unit can monitor the user's emotions in real time and determine the priority of information to be provided based on changes in emotions. Thus, by determining the priority of information based on the user's emotions, important information can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit may input user emotion data to the generation AI and cause the generation AI to determine the priority of information based on emotion.

[0091] The information providing unit can dynamically adjust the search range for related information based on the content of the minutes. The information providing unit dynamically adjusts the search range for related information based on, for example, the content of the minutes. The search range is adjusted using, for example, a database to be searched, a search query setting, etc. The information providing unit broadens the search range for related information based on, for example, the content of the minutes. The information providing unit can also narrow the search range for related information based on the content of the minutes. The information providing unit can also dynamically adjust the optimal search range based on the content of the minutes. For example, the information providing unit broadens the search range for related information based on the content of the minutes. By dynamically adjusting the search range based on the content of the minutes, optimal related information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input content data of the minutes to a generation AI and cause the generation AI to adjust the search range for related information.

[0092] The information providing unit can evaluate the reliability of past meeting records and related literature and provide highly reliable information preferentially. The information providing unit, for example, evaluates the reliability of past meeting records and related literature and provides highly reliable information preferentially. Reliability is evaluated using, for example, information source evaluation criteria, reliability scoring, etc. The information providing unit, for example, evaluates the reliability of past meeting records and provides highly reliable information preferentially. The information providing unit can also evaluate the reliability of related literature and provide highly reliable information preferentially. The information providing unit can also set reliability evaluation criteria to provide highly reliable information preferentially. For example, the information providing unit evaluates the reliability of past meeting records and provides highly reliable information preferentially. This prioritizes the provision of highly reliable information, thereby improving the quality of the meeting. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input data of past meeting records and related literature into a generation AI and cause the generation AI to evaluate reliability and provide information.

[0093] The information providing unit can update necessary information in real time according to the progress of the conference. The information providing unit updates necessary information in real time according to, for example, the progress of the conference. The progress is grasped using, for example, the progress of the agenda, the order of speakers, etc. The information providing unit, for example, analyzes the progress of the conference in real time and updates necessary information. Furthermore, if the progress of the conference is delayed, the information providing unit can also prioritize updating important information. Furthermore, if the conference is progressing smoothly, the information providing unit can evenly update overall information. For example, the information providing unit analyzes the progress of the conference in real time and updates necessary information. In this way, by updating information in real time according to the progress of the conference, the latest information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input conference progress data to the generation AI and cause the generation AI to perform real-time updates of the information.

[0094] The information providing unit can estimate the user's emotions and adjust the display method of the information to be provided based on the estimated user emotions. The information providing unit, for example, estimates the user's emotions and adjusts the display method of the information to be provided based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, if the user is nervous, the information providing unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the information providing unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the information providing unit can provide a display method that focuses on the main points. For example, the information providing unit can monitor the user's emotions in real time and adjust the display method of the information to be provided in response to changes in emotions. This allows for highly visible information to be provided by adjusting the display method of information based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit may input user emotion data to the generation AI and cause the generation AI to adjust the information display method based on the emotion.

[0095] The information providing unit can automatically search for and provide the latest research results and technical information related to the meeting agenda. The information providing unit can automatically search for and provide the latest research results and technical information related to the meeting agenda, for example, using a generation AI. The latest research results and technical information are searched for, for example, using a specific database, a search query setting, etc. The information providing unit can automatically search for and provide the latest research results related to the meeting agenda, for example. The information providing unit can also automatically search for and provide the latest technical information related to the meeting agenda. The information providing unit can also automatically search for and provide the latest patent information related to the meeting agenda. For example, the information providing unit can automatically search for and provide the latest research results related to the meeting agenda. This improves the quality of the meeting by providing the latest research results and technical information. Some or all of the above-mentioned processing in the information providing unit can be performed, for example, using AI or without AI. For example, the information providing unit can input agenda data into the generation AI and cause the generation AI to search for and provide the latest research results and technical information.

[0096] The information providing unit can adjust the level of detail of the information to be provided according to the expertise of the conference participants. The information providing unit adjusts the level of detail of the information to be provided according to, for example, the expertise of the conference participants. Expertise is evaluated using, for example, the field of expertise, the depth of knowledge, etc. The information providing unit, for example, provides detailed information to participants with extensive expertise. The information providing unit can also provide concise and easy-to-understand information to participants with little expertise. The information providing unit can also adjust the level of detail of the information according to the level of expertise. For example, the information providing unit provides detailed information to participants with extensive expertise and emphasizes specialized information. In this way, by adjusting the level of detail of the information according to the participants' expertise, more understandable information can be provided. Some or all of the above-described processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input the participants' expertise data to a generation AI and cause the generation AI to adjust the level of detail of the information.

[0097] The information providing unit can provide related visual data and graphs according to the progress of the meeting. The information providing unit provides related visual data and graphs, for example, according to the progress of the meeting. The progress is understood using, for example, the progress of agenda items, the order of speakers, etc. The information providing unit, for example, analyzes the progress of the meeting in real time and provides related visual data. Furthermore, if the progress of the meeting is delayed, the information providing unit can prioritize providing important visual data. Furthermore, if the progress of the meeting is smooth, the information providing unit can provide overall visual data evenly. For example, the information providing unit analyzes the progress of the meeting in real time and provides related visual data. As a result, by providing visual data and graphs according to the progress of the meeting, it is possible to provide information that is visually easy to understand. Some or all of the above-mentioned processing in the information providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the information providing unit can input conference progress data to a generation AI and cause the generation AI to provide visual data and graphs.

[0098] The real-time providing unit can estimate the user's emotions and determine the priority of information to be provided in real time based on the estimated user emotions. The real-time providing unit can, for example, estimate the user's emotions and determine the priority of information to be provided in real time based on the estimated user emotions. The user's emotions can be estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, when the user is nervous, the real-time providing unit can prioritize providing important information in real time. Furthermore, when the user is relaxed, the real-time providing unit can also provide overall information evenly in real time. Furthermore, when the user is in a hurry, the real-time providing unit can prioritize providing information that covers the main points in real time. For example, the real-time providing unit can monitor the user's emotions in real time and determine the priority of information to be provided in accordance with changes in emotions. In this way, by determining the priority of information based on the user's emotions, important information can be provided preferentially in real time. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit may input user emotion data to the generation AI and cause the generation AI to determine the priority of information based on the emotion.

[0099] The real-time providing unit can dynamically adjust the content of the information to be provided in real time according to the progress of the conference. The real-time providing unit dynamically adjusts the content of the information to be provided in real time, for example, according to the progress of the conference. The progress is grasped, for example, using the progress of the agenda, the order of speakers, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and dynamically adjusts the necessary information. Furthermore, if the progress of the conference is delayed, the real-time providing unit can prioritize and provide important information in real time. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information evenly in real time. For example, the real-time providing unit analyzes the progress of the conference in real time and dynamically adjusts the necessary information. In this way, by dynamically adjusting the content of the information according to the progress of the conference, optimal information can be provided in real time. Some or all of the above-described processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to dynamically adjust the content of the information.

[0100] The real-time providing unit can analyze the content of statements made by conference participants in real time and provide relevant information instantly. The real-time providing unit can, for example, analyze the content of statements made by conference participants in real time and provide relevant information instantly. The content of statements is analyzed using, for example, natural language processing technology, speech recognition technology, etc. The real-time providing unit can, for example, analyze the content of statements made by conference participants in real time and provide relevant information instantly. The real-time providing unit can also instantly provide related literature and data based on the content of statements made by conference participants. The real-time providing unit can also instantly provide relevant past meeting records based on the content of statements made by conference participants. For example, the real-time providing unit can analyze the content of statements made by conference participants in real time and provide relevant information instantly. In this way, by analyzing the content of statements made by conference participants in real time, relevant information can be instantly provided. Some or all of the above-mentioned processing in the real-time providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the real-time providing unit can input content data of statements to a generation AI and cause the generation AI to instantly provide relevant information.

[0101] The real-time providing unit can filter and provide necessary information in real time according to the progress of the meeting. The real-time providing unit, for example, analyzes the progress of the meeting in real time and filters and provides the necessary information. The progress is grasped, for example, using the progress of the agenda, the importance of the content of the remarks, etc. The real-time providing unit, for example, analyzes the progress of the meeting in real time and filters and provides the necessary information. Furthermore, when the progress of the meeting is delayed, the real-time providing unit can preferentially filter and provide important information. Furthermore, when the progress of the meeting is smooth, the real-time providing unit can evenly filter and provide all the information. For example, the real-time providing unit analyzes the progress of the meeting in real time and filters and provides the necessary information. In this way, important information can be preferentially provided by filtering information according to the progress of the meeting. Some or all of the above-mentioned processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to filter the information.

[0102] The real-time providing unit can estimate the user's emotions and adjust the display method of the information provided in real time based on the estimated user emotions. The real-time providing unit, for example, estimates the user's emotions and adjusts the display method of the information provided in real time based on the estimated user emotions. The user's emotions are estimated using, for example, facial expression recognition, voice tone analysis, survey results, etc. For example, if the user is nervous, the real-time providing unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the real-time providing unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the real-time providing unit can also provide a display method that focuses on the main points. For example, the real-time providing unit can monitor the user's emotions in real time and adjust the display method of the information to be provided in response to changes in emotions. By adjusting the display method of information based on the user's emotions, highly visible information can be provided in real time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit may input user emotion data to the generating AI and cause the generating AI to adjust the display method of information based on the emotion.

[0103] The real-time providing unit can select the format of information to be provided in real time (e.g., text, audio, visual) depending on the progress of the conference. The real-time providing unit selects the format of information to be provided in real time depending on, for example, the progress of the conference. The progress is grasped using, for example, the progress of the agenda, the order of speakers, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and selects the optimal information format. Furthermore, if the conference is progressing slowly, the real-time providing unit can provide important information in text format. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information in visual format. For example, the real-time providing unit analyzes the progress of the conference in real time and selects the optimal information format. In this way, by selecting the information format depending on the progress of the conference, information can be provided in the optimal format. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to a generation AI and cause the generation AI to select the information format.

[0104] The real-time providing unit can adjust the level of detail of the information to be provided in real time based on the position and expertise of the conference participants. The real-time providing unit adjusts the level of detail of the information to be provided in real time based on, for example, the position and expertise of the conference participants. The position and expertise are evaluated using, for example, the position hierarchy, the field of expertise, etc. The real-time providing unit, for example, provides detailed information in real time to participants with high position. The real-time providing unit can also provide detailed information in real time to participants with extensive expertise. The real-time providing unit can also provide optimal information in real time by taking both the position and expertise into consideration. For example, the real-time providing unit provides detailed information in real time to participants with high position and emphasizes specialized information. In this way, by adjusting the level of detail of the information based on the position and expertise of the participants, more understandable information can be provided in real time. Some or all of the above-described processing in the real-time providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the real-time providing unit can input the position and expertise data of the participants to the generation AI and cause the generation AI to adjust the level of detail of the information.

[0105] The real-time providing unit can acquire and provide information in real time from a related external database according to the progress of the conference. The real-time providing unit, for example, analyzes the progress of the conference in real time and acquires information from the related external database. The progress is grasped using, for example, the progress of the agenda, the importance of the content of the remarks, etc. The real-time providing unit, for example, analyzes the progress of the conference in real time and acquires information from the related external database. Furthermore, if the progress of the conference is delayed, the real-time providing unit can also prioritize acquiring important information from the external database. Furthermore, if the conference is progressing smoothly, the real-time providing unit can evenly acquire overall information from the external database. For example, the real-time providing unit analyzes the progress of the conference in real time and acquires information from the related external database. In this way, by acquiring information from the external database according to the progress of the conference, the latest information can be provided in real time. Some or all of the above-mentioned processing in the real-time providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the real-time providing unit can input conference progress data to the generation AI and cause the generation AI to acquire information from the external database. === Hard Collateral 1-1 === Each of the multiple elements, including the acquisition unit, minutes generation unit, information provision unit, and real-time provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit acquires audio data of the meeting using the microphone 38B or camera 42 of the smart device 14. The minutes generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text using a generation AI and automatically generates minutes. The information provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the contents of the minutes using a generation AI and searches for and provides related information. The real-time provision unit, realized, for example, by the control unit 46A of the smart device 14, provides information in real time as the meeting progresses. === Hard Collateral 1-2 === Each of the multiple elements, including the acquisition unit, minutes generation unit, information provision unit, and real-time provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit acquires audio data of the meeting using the microphone 238 or camera 42 of the smart glasses 214. The minutes generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, converts the audio data into text using a generation AI and automatically generates minutes. The information provision unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the contents of the minutes using a generation AI and searches for and provides related information. The real-time provision unit, realized, for example, by the control unit 46A of the smart glasses 214, provides information in real time according to the progress of the meeting. === Hard Collateral 1-3 === Each of the multiple elements, including the acquisition unit, minutes generation unit, information provision unit, and real-time provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit acquires audio data of the meeting using the microphone 238 or camera 42 of the headset-type terminal 314. The minutes generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and converts the audio data into text using a generation AI to automatically generate minutes. The information provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the minutes using a generation AI to search for and provide related information. The real-time provision unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and provides information in real time as the meeting progresses. === Hard Collateral 1-4 === Each of the multiple elements, including the acquisition unit, minutes generation unit, information provision unit, and real-time provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit acquires audio data of the meeting using the microphone 238 or camera 42 of the robot 414. The minutes generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and converts the audio data into text using a generation AI to automatically generate minutes. The information provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the minutes using a generation AI to search for and provide related information. The real-time provision unit is realized, for example, by the control unit 46A of the robot 414, and provides information in real time according to the progress of the meeting.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The acquisition unit can analyze the content of statements made by meeting participants in real time and evaluate the importance of the statements. For example, the acquisition unit can analyze the content of statements using natural language processing technology and extract important keywords and phrases. The acquisition unit can also evaluate the importance of statements based on the speaker's position and expertise. Furthermore, the acquisition unit can prioritize acquisition of important statements according to the progress of the meeting. In this way, the acquisition unit can improve the quality of the meeting by analyzing the content of statements made by meeting participants in real time and prioritizing acquisition of important statements.

[0108] The minutes generation unit can analyze the content of statements made by meeting participants in real time and adjust the level of detail in the minutes based on the importance of the statements. For example, the minutes generation unit can analyze the content of statements using natural language processing technology and extract important keywords and phrases. The minutes generation unit can also evaluate the importance of statements based on the speaker's position and expertise, and generate detailed minutes based on important statements. Furthermore, the minutes generation unit can also prioritize reflecting important statements in the minutes depending on the progress of the meeting. In this way, the minutes generation unit can improve the quality of the minutes by analyzing the content of statements made by meeting participants in real time and prioritize reflecting important statements in the minutes.

[0109] The information providing unit can analyze the content of statements made by meeting participants in real time and provide relevant information immediately. For example, the information providing unit can analyze the content of statements using natural language processing technology and extract related keywords and phrases. The information providing unit can also instantly provide related literature and data based on the content of statements. Furthermore, the information providing unit can instantly provide related past meeting records based on the content of statements. In this way, the information providing unit can improve the quality of meetings by analyzing the content of statements made by meeting participants in real time and providing related information immediately.

[0110] The real-time providing unit can dynamically adjust the content of the information to be provided in real time according to the progress of the conference. For example, the real-time providing unit analyzes the progress of the conference in real time and dynamically adjusts the necessary information. Furthermore, if the conference is progressing slowly, the real-time providing unit can prioritize and provide important information in real time. Furthermore, if the conference is progressing smoothly, the real-time providing unit can provide overall information evenly in real time. In this way, the real-time providing unit can dynamically adjust the content of the information according to the progress of the conference, thereby providing optimal information in real time.

[0111] The real-time providing unit can analyze the content of statements made by meeting participants in real time and provide related information instantly. For example, the real-time providing unit can analyze the content of statements using natural language processing technology and extract related keywords and phrases. The real-time providing unit can also instantly provide related literature and data based on the content of statements. Furthermore, the real-time providing unit can instantly provide related past meeting records based on the content of statements. In this way, the real-time providing unit can improve the quality of meetings by analyzing the content of statements made by meeting participants in real time and providing related information instantly.

[0112] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring voice data based on the estimated user's emotions. For example, if the user is nervous, the acquisition unit adjusts the timing to prioritize acquiring important parts of the meeting. Also, if the user is relaxed, the acquisition unit can acquire overall voice data evenly. Furthermore, if the user is in a hurry, the acquisition unit can prioritize acquiring voice data that highlights the main points. In this way, the acquisition unit can acquire more appropriate voice data by adjusting the timing of acquiring voice data based on the user's emotions.

[0113] The minutes generation unit can estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user's emotions. For example, if the user is nervous, the minutes generation unit can generate concise minutes that are concise and to the point. Also, if the user is relaxed, the minutes generation unit can generate detailed minutes. Furthermore, if the user is in a hurry, the minutes generation unit can generate minutes that emphasize the main points. In this way, the minutes generation unit can generate more appropriate minutes by adjusting the presentation style of the minutes based on the user's emotions.

[0114] The information providing unit can estimate the user's emotions and determine the priority of information to be provided based on the estimated user's emotions. For example, when the user is nervous, the information providing unit can provide important information with priority. When the user is relaxed, the information providing unit can also provide general information evenly. Furthermore, when the user is in a hurry, the information providing unit can also provide information that focuses on the main points with priority. In this way, the information providing unit can provide important information with priority by determining the priority of information based on the user's emotions.

[0115] The real-time providing unit can estimate the user's emotions and determine the priority of information to be provided in real time based on the estimated user's emotions. For example, when the user is nervous, the real-time providing unit can provide important information preferentially in real time. Also, when the user is relaxed, the real-time providing unit can provide overall information evenly in real time. Furthermore, when the user is in a hurry, the real-time providing unit can provide information that focuses on the main points preferentially in real time. In this way, the real-time providing unit can provide important information preferentially in real time by determining the priority of information based on the user's emotions.

[0116] The real-time providing unit can estimate the user's emotions and adjust the display method of the information to be provided in real time based on the estimated user's emotions. For example, if the user is nervous, the real-time providing unit can provide a simple, highly visible display method. If the user is relaxed, the real-time providing unit can also provide a display method including detailed information. Furthermore, if the user is in a hurry, the real-time providing unit can also provide a display method that focuses on the main points. In this way, the real-time providing unit can provide highly visible information in real time by adjusting the display method of information based on the user's emotions.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The acquisition unit acquires audio data of the conference. The audio data of the conference includes, but is not limited to, audio data acquired from a recording device of the conference. The acquisition unit can also acquire audio data using a microphone, a recorder, or recording software. Step 2: The minutes generation unit converts the audio data acquired by the acquisition unit into text using a generation AI and automatically generates minutes. The generation AI can also convert audio data into text using a text generation AI (e.g., LLM) and extract important parts of the audio data to generate minutes. Step 3: The information provision unit uses the generation AI to analyze the contents of the minutes generated by the minutes generation unit, and searches for and provides related information. The generation AI analyzes the contents of the minutes, and searches for and provides related past meeting records, related literature, data, etc. Step 4: The real-time providing unit provides information in real time according to the progress of the conference based on the information provided by the information providing unit. The real-time providing unit can analyze the progress of the conference and provide necessary information in real time.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0122] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0146] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0163] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0164] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0166] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0167] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0171] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0173] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0175] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0177] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0179] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0180] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0181] 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.

[0182] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0183] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0184] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0185] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0186] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0188] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0190] [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an acquisition unit for acquiring audio data of a conference; a minutes generation unit that converts the voice data acquired by the acquisition unit into text and automatically generates minutes; an information providing unit that analyzes the contents of the minutes generated by the minutes generating unit and searches for and provides related information; a real-time providing unit that provides information according to the progress of the conference based on the information provided by the information providing unit. A system characterized by:

2. The acquisition unit Capture audio data from a meeting recording device 2. The system of claim 1.

3. The minutes generation unit Generative AI converts voice data into text and automatically generates minutes.

2. The system of claim 1.

4. The information providing unit Analyze the contents of the minutes using generative AI and search for and provide related information 2. The system of claim 1.

5. The real-time providing unit Provide real-time information as the meeting progresses 2. The system of claim 1.

6. The information providing unit Search and provide past conference records, related literature, and data related to the agenda 2. The system of claim 1.

7. The acquisition unit The user's emotions are estimated, and the timing of acquiring voice data is adjusted based on the estimated user's emotions.

2. The system of claim 1.

8. The acquisition unit Analyze the frequency of speech by meeting participants and prioritize important speech 2. The system of claim 1.

Images