System

Abstract

An object of a system according to an embodiment is to automatically create minutes of a meeting and convert the minutes into a material.SOLUTION: A system includes a collection unit, an analysis unit, and a creation unit. The collection unit collects voice data of a conference. The analysis unit analyzes the voice data collected by the collection unit and automatically generates minutes. The creation unit automatically creates a material based on the minutes generated by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem that creating meeting minutes and documenting them takes a lot of time and effort.

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

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a creation unit. The collection unit collects audio data of a meeting. The analysis unit analyzes the audio data collected by the collection unit and automatically generates minutes. The creation unit automatically creates materials based on the minutes generated by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically create minutes of a meeting and document them. [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) An automatic minutes-taking system according to an embodiment of the present invention automatically collects and analyzes audio data from meetings, generates minutes, and automatically creates materials. The automatic minutes-taking system collects audio data from meetings, analyzes it using AI, automatically generates minutes, and automatically creates materials based on the minutes. For example, the automatic minutes-taking system collects audio data from meetings using microphones installed in conference rooms. The collected audio data is then analyzed by AI and converted into text data. For example, the system extracts the names of speakers and the content of their remarks as text and formats it into minutes. Furthermore, the automatic minutes-taking system automatically creates presentation materials and reports based on the generated minutes using AI. This significantly reduces the effort required for creating minutes and enables efficient meeting management. The automatic minutes-taking system automatically collects and analyzes audio data from meetings, generates minutes, and automatically creates materials. For example, by introducing this system into regular corporate meetings, the contents of meetings can be quickly and accurately recorded and documented. This improves meeting efficiency and reduces the burden on participants. It also improves the quality of meeting minutes and materials, allowing the results of meetings to be utilized more effectively.

[0029] An automatic minutes-creation system according to an embodiment includes a collection unit, an analysis unit, and a creation unit. The collection unit collects audio data of a meeting. The collection unit collects the audio data of a meeting using, for example, a microphone installed in a conference room. The collection unit can also record speeches made by meeting participants and save the data as audio data. For example, the collection unit collects the entire audio of a meeting using a microphone installed in a conference room. The analysis unit analyzes the audio data collected by the collection unit and automatically generates minutes. The analysis unit converts the audio data into text data using, for example, voice recognition technology. For example, the analysis unit extracts the names of speakers and speech content as text and formats the text into minutes. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input audio data into AI and have the AI ​​convert the audio data into text data. The creation unit automatically creates materials based on the minutes generated by the analysis unit. The creation unit automatically creates presentation materials and reports based on the contents of the minutes, for example. For example, the creation unit can automatically create presentation materials and reports based on the contents of the minutes. As a result, the automatic minutes creation system according to the embodiment can automatically collect and analyze audio data of a meeting, generate minutes, and further automatically create materials. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the contents of the minutes into AI and have the AI ​​create the materials.

[0030] The collection unit can collect audio data of a conference using microphones installed in the conference room. Examples of microphones installed in the conference room include, but are not limited to, directional microphones and omnidirectional microphones. For example, the collection unit can collect the audio of a specific speaker using directional microphones installed in the conference room. The collection unit can also collect audio from the entire conference room using omnidirectional microphones. For example, the collection unit can install an omnidirectional microphone in the center of the conference room to collect the entire audio. The collection unit can also efficiently collect audio data of a conference by combining multiple microphones. For example, the collection unit can install directional microphones in various locations in the conference room and collect the audio of each speaker individually. In this way, audio data of a conference can be efficiently collected using the microphones installed in the conference room. Some or all of the above-mentioned processing by the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input audio data acquired from the microphones installed in the conference room into AI and have the AI ​​collect the audio data.

[0031] The analysis unit can convert voice data into text data using voice recognition technology. Voice recognition technology includes, but is not limited to, deep learning-based voice recognition and HMM-based voice recognition. The analysis unit can convert voice data into text data with high accuracy using, for example, deep learning-based voice recognition technology. The analysis unit can also convert voice data into text data using HMM-based voice recognition technology. For example, the analysis unit inputs voice data into a deep learning model and outputs text data. The analysis unit can also input voice data into an HMM model and output text data. In this way, voice data can be accurately converted into text data using voice recognition technology. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input voice data into AI and have the AI ​​convert the voice data into text data.

[0032] The analysis unit can extract the speaker's name and the speech content as text and format it into minutes. Methods for extracting the speaker's name and the speech content include, but are not limited to, for example, speech recognition accuracy and a speaker identification method. The analysis unit, for example, extracts the speaker's name using speech recognition technology and records the speech content as text. The analysis unit can also accurately extract the speaker's name using a speaker identification method. For example, the analysis unit extracts the speaker's name using speech recognition technology and records the speech content as text. The analysis unit can also accurately extract the speaker's name using a speaker identification method. This accurately extracts the speaker's name and the speech content and formats it into minutes, thereby improving the quality of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input voice data into AI and have the AI ​​extract the speaker's name and the speech content.

[0033] The creation unit can automatically create presentation materials and reports based on the contents of the minutes. Presentation materials and reports include, but are not limited to, slide presentations and text reports, for example. The creation unit, for example, automatically creates a slide presentation based on the contents of the minutes. The creation unit can also automatically create a text report based on the contents of the minutes. For example, the creation unit automatically creates a slide presentation based on the contents of the minutes. The creation unit can also automatically create a text report based on the contents of the minutes. This automatically creates materials based on the contents of the minutes, thereby reducing the effort required for creating materials. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the contents of the minutes into AI and have the AI ​​create the materials.

[0034] The collection unit can analyze the speech frequency of meeting participants and prioritize collecting important speech. For example, the collection unit can prioritize collecting speech from participants who speak frequently and reflect them in the minutes. The collection unit can also prioritize collecting speech from participants who speak less frequently but in important positions. The collection unit can also use AI to analyze speech frequency and the importance of speech content and prioritize collecting important speech. In this way, important speech can be prioritized by analyzing speech frequency. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input speech frequency data into AI and have the AI ​​execute the prioritized collection of important speech.

[0035] The collection unit can add a filtering function that automatically removes background noise when collecting audio data. For example, the collection unit can automatically remove noise from the air conditioner or projector in the conference room to clearly collect what is being said. The collection unit can also filter out chatter and unnecessary sounds during the meeting to collect only important comments. The collection unit can also automatically detect and remove noise outside the conference room to clearly collect what is being said. This allows for the removal of background noise and the clear collection of what is being said. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input background noise data into AI and have the AI ​​perform noise removal filtering.

[0036] When collecting voice data, the collection unit can limit the collection range based on the theme of the meeting. For example, if the theme of the meeting is technical, the collection unit can prioritize collecting technical comments. Furthermore, if the theme of the meeting is management strategy, the collection unit can also prioritize collecting comments related to management. Furthermore, if the theme of the meeting is project progress, the collection unit can also prioritize collecting comments related to the progress. In this way, by limiting the collection range based on the theme of the meeting, important comments can be collected efficiently. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input meeting theme data into AI and have the AI ​​limit the collection range.

[0037] When collecting voice data, the collection unit can customize the collection method based on the positions and expertise of the participants in the meeting. For example, the collection unit prioritizes collection of utterances from participants with higher positions. The collection unit can also prioritize collection of utterances from participants with extensive expertise. The collection unit can also prioritize collection of important utterances by taking into consideration both the positions and expertise. In this way, by customizing the collection method based on the positions and expertise of the participants, important utterances can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and expertise data of the participants into AI and have the AI ​​customize the collection method.

[0038] The collection unit can automatically adjust collection settings according to the location and time of the meeting when collecting audio data. The collection unit automatically adjusts the collection settings, for example, taking into account the environmental sounds in the conference room. The collection unit can also automatically adjust the collection settings according to the time of the meeting. The collection unit can also automatically adjust optimal collection settings according to the location and time of the meeting. This enables optimal collection by automatically adjusting the collection settings according to the location and time of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the location and time of the meeting into AI and have the AI ​​perform automatic adjustment of the collection settings.

[0039] When analyzing the audio data, the analysis unit can adjust the level of detail of the text data based on the importance of the utterance. For example, the analysis unit records important utterances in detail and other utterances briefly. The analysis unit can also dynamically adjust the level of detail of the text data according to the importance of the utterance. The analysis unit can also emphasize important utterances and record other utterances briefly. In this way, important utterances can be recorded in detail by adjusting the level of detail of the text data based on the importance of the utterance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance importance data into AI and have the AI ​​adjust the level of detail of the text data.

[0040] When analyzing the audio data, the analysis unit can apply different analysis algorithms depending on the theme of the meeting. For example, in a technical meeting, the analysis unit can apply an algorithm that accurately analyzes technical terms. In addition, in a meeting on business strategy, the analysis unit can also apply an algorithm that accurately analyzes management terms. In addition, in a meeting on project progress, the analysis unit can apply an algorithm that accurately analyzes terms related to progress. In this way, by applying an appropriate analysis algorithm depending on the theme of the meeting, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input meeting theme data into AI and have the AI ​​apply the analysis algorithm.

[0041] When analyzing the voice data, the analysis unit can improve the accuracy of the analysis by referring to past minutes data. For example, the analysis unit can refer to past minutes data and accurately analyze similar utterances. The analysis unit can also analyze the characteristics of the speaker based on the past minutes data to improve accuracy. The analysis unit can also refer to past minutes data and perform analysis according to the theme of the meeting. In this way, by referring to past minutes data, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past minutes data into AI and have the AI ​​improve the accuracy of the analysis.

[0042] When analyzing the audio data, the analysis unit can dynamically change the analysis method according to the progress of the conference. For example, the analysis unit analyzes all comments at the start of the conference, and as the conference progresses, it focuses on analyzing comments from specific speakers. Furthermore, if the conference progresses quickly, the analysis unit can increase the analysis frequency to avoid missing important comments. Furthermore, if the conference progresses slowly, the analysis unit can decrease the analysis frequency to focus on important comments. In this way, by changing the analysis method according to the progress of the conference, it is possible to analyze important comments without missing them. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conference progress data into AI and have the AI ​​dynamically change the analysis method.

[0043] When analyzing audio data, the analysis unit can improve the accuracy of the analysis by referring to the speaker's past speech history. For example, the analysis unit can refer to the speaker's past speech history and accurately analyze similar speech content. The analysis unit can also analyze the speaker's characteristics based on the speaker's past speech history to improve accuracy. The analysis unit can also refer to the speaker's past speech history and perform analysis according to the theme of the meeting. In this way, by referring to the speaker's past speech history, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's past speech history data into AI and have the AI ​​improve the accuracy of the analysis.

[0044] The creation unit can adjust the level of detail of the materials based on the importance of the minutes when creating the materials. For example, the creation unit records important minutes in detail and other minutes in brief. The creation unit can also dynamically adjust the level of detail of the materials according to the importance of the minutes. The creation unit can also emphasize important minutes and record other minutes in brief. In this way, important content can be recorded in detail by adjusting the level of detail of the materials based on the importance of the minutes. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input importance data of the minutes into AI and have the AI ​​adjust the level of detail of the materials.

[0045] When creating materials, the creation unit can apply different material creation algorithms depending on the theme of the meeting. For example, in a technical meeting, the creation unit can apply an algorithm that accurately analyzes technical terms. In a meeting on business strategy, the creation unit can also apply an algorithm that accurately analyzes business terms. In a meeting on project progress, the creation unit can also apply an algorithm that accurately analyzes terms related to progress. This improves the accuracy of the materials by applying an appropriate material creation algorithm depending on the theme of the meeting. Some or all of the above-mentioned processing in the creation unit can be performed using, for example, AI, or can be performed without using AI. For example, the creation unit can input meeting theme data into AI and have the AI ​​apply the material creation algorithm.

[0046] When creating a document, the creation unit can improve the accuracy of the creation by referring to past document data. For example, the creation unit references past document data to accurately reflect similar content. The creation unit can also unify the format and style of the document based on the past document data. The creation unit can also create a document according to the theme of the meeting by referring to the past document data. In this way, the accuracy of the document is improved by referring to the past document data. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input past document data into AI and have the AI ​​improve the accuracy of the creation.

[0047] When creating materials, the creation unit can dynamically change the presentation method of the materials depending on the progress of the meeting. For example, the creation unit can briefly summarize the overall content at the start of the meeting and add more detailed content as the meeting progresses. Furthermore, if the meeting progresses quickly, the creation unit can increase the frequency of creating materials to avoid missing important content. Furthermore, if the meeting progresses slowly, the creation unit can reduce the frequency of creating materials to focus on important content. In this way, by changing the presentation method of the materials depending on the progress of the meeting, important content can be recorded without missing it. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input meeting progress data into AI and have the AI ​​dynamically change the presentation method of the materials.

[0048] When creating materials, the creation unit can customize the presentation method of the materials based on the speaker's position and expertise. For example, the creation unit records in detail the statements of speakers with high positions. The creation unit can also record in detail the statements of speakers with extensive expertise. The creation unit can also customize the presentation method of the materials taking into consideration both the position and expertise. In this way, important content can be recorded in detail by customizing the presentation method based on the speaker's position and expertise. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the speaker's position and expertise data into AI and have the AI ​​customize the presentation method of the materials.

[0049] When creating a document, the creation unit can automatically adjust the content of the document depending on the location and time of the meeting. For example, the creation unit automatically adjusts the content of the document taking into account the ambient noise in the conference room. The creation unit can also automatically adjust the content of the document depending on the time of the meeting. The creation unit can also automatically adjust the content of the document to be optimal depending on the location and time of the meeting. In this way, optimal documents are created by adjusting the content of the document depending on the location and time of the meeting. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the location and time of the meeting into AI and have the AI ​​automatically adjust the content of the document.

[0050] When creating materials, the creation unit can customize the presentation method of the materials based on the speaker's position and expertise. For example, the creation unit records in detail the statements of speakers with high positions. The creation unit can also record in detail the statements of speakers with extensive expertise. The creation unit can also customize the presentation method of the materials taking into consideration both the position and expertise. In this way, important content can be recorded in detail by customizing the presentation method based on the speaker's position and expertise. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the speaker's position and expertise data into AI and have the AI ​​customize the presentation method of the materials.

[0051] When creating a document, the creation unit can automatically adjust the content of the document depending on the location and time of the meeting. For example, the creation unit automatically adjusts the content of the document taking into account the ambient noise in the conference room. The creation unit can also automatically adjust the content of the document depending on the time of the meeting. The creation unit can also automatically adjust the content of the document to be optimal depending on the location and time of the meeting. In this way, optimal documents are created by adjusting the content of the document depending on the location and time of the meeting. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the location and time of the meeting into AI and have the AI ​​automatically adjust the content of the document.

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

[0053] The collection unit can translate statements made by meeting participants in real time and record them in multiple languages. For example, the collection unit can translate statements made in English into Japanese and reflect them in the minutes. The collection unit can also translate statements made in French into English and reflect them in the minutes. If meeting participants speak different languages, the collection unit can also translate each language and reflect them in the minutes. This makes it possible to create accurate minutes even for meetings with participants speaking different languages. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input voice data into AI and have the AI ​​perform the translation.

[0054] The collection unit can summarize the statements made by meeting participants in real time and record only the important points. For example, the collection unit can summarize long statements in short sentences and reflect them in the minutes. The collection unit can also summarize multiple statements together and reflect them in the minutes. The collection unit can also summarize important points in real time as the meeting progresses and reflect them in the minutes. This makes it possible to efficiently record important points even in long meetings. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input audio data into AI and have the AI ​​perform the summarization.

[0055] The analysis unit can classify the content of comments made by meeting participants in real time and organize the minutes by theme. For example, the analysis unit can classify technical comments into a technology category and reflect this in the minutes. The analysis unit can also classify comments related to management into a management category and reflect this in the minutes. The analysis unit can also classify comments related to project progress into a project category and reflect this in the minutes. In this way, organizing the minutes by theme makes them easier to search and refer to later. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the classification.

[0056] The analysis unit can evaluate the content of statements made by meeting participants in real time and record the reliability of the statements. For example, if a statement is based on a reliable source, the analysis unit can reflect the reliability in the minutes. If a statement is based on uncertain information, the analysis unit can also reflect the reliability in the minutes. If a statement is consistent with past data, the analysis unit can also reflect the reliability in the minutes. By recording the reliability of statements, this makes it easier to verify and reference them later. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the evaluation.

[0057] The analysis unit can summarize the statements made by meeting participants in real time and record only the important points. For example, the analysis unit can summarize long statements in shorter form and reflect them in the minutes. The analysis unit can also summarize multiple statements together and reflect them in the minutes. The analysis unit can also summarize important points in real time as the meeting progresses and reflect them in the minutes. This makes it possible to efficiently record important points even in long meetings. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input audio data into AI and have the AI ​​perform the summarization.

[0058] The analysis unit can classify the content of comments made by meeting participants in real time and organize the minutes by theme. For example, the analysis unit can classify technical comments into a technology category and reflect this in the minutes. The analysis unit can also classify comments related to management into a management category and reflect this in the minutes. The analysis unit can also classify comments related to project progress into a project category and reflect this in the minutes. In this way, organizing the minutes by theme makes them easier to search and refer to later. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the classification.

[0059] The analysis unit can evaluate the content of statements made by meeting participants in real time and record the reliability of the statements. For example, if a statement is based on a reliable source, the analysis unit can reflect the reliability in the minutes. If a statement is based on uncertain information, the analysis unit can also reflect the reliability in the minutes. If a statement is consistent with past data, the analysis unit can also reflect the reliability in the minutes. By recording the reliability of statements, this makes it easier to verify and reference them later. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the evaluation.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The collection unit collects audio data of the meeting. For example, the collection unit collects audio data of the meeting using a microphone installed in the meeting room. The collection unit can also record what the participants in the meeting say and save it as audio data. Step 2: The analysis unit analyzes the voice data collected by the collection unit and automatically generates minutes. The analysis unit converts the voice data into text data, for example, using voice recognition technology. For example, the analysis unit extracts the names of speakers and the content of their remarks as text and formats it into minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. Step 3: The creation unit automatically creates materials based on the minutes generated by the analysis unit. The creation unit automatically creates, for example, presentation materials or reports based on the contents of the minutes. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI.

[0062] (Example 2) An automatic minutes-taking system according to an embodiment of the present invention automatically collects and analyzes audio data from meetings, generates minutes, and automatically creates materials. The automatic minutes-taking system collects audio data from meetings, analyzes it using AI, automatically generates minutes, and automatically creates materials based on the minutes. For example, the automatic minutes-taking system collects audio data from meetings using microphones installed in conference rooms. The collected audio data is then analyzed by AI and converted into text data. For example, the system extracts the names of speakers and the content of their remarks as text and formats it into minutes. Furthermore, the automatic minutes-taking system automatically creates presentation materials and reports based on the generated minutes using AI. This significantly reduces the effort required for creating minutes and enables efficient meeting management. The automatic minutes-taking system automatically collects and analyzes audio data from meetings, generates minutes, and automatically creates materials. For example, by introducing this system into regular corporate meetings, the contents of meetings can be quickly and accurately recorded and documented. This improves meeting efficiency and reduces the burden on participants. It also improves the quality of meeting minutes and materials, allowing the results of meetings to be utilized more effectively.

[0063] An automatic minutes-creation system according to an embodiment includes a collection unit, an analysis unit, and a creation unit. The collection unit collects audio data of a meeting. The collection unit collects the audio data of a meeting using, for example, a microphone installed in a conference room. The collection unit can also record speeches made by meeting participants and save the data as audio data. For example, the collection unit collects the entire audio of a meeting using a microphone installed in a conference room. The analysis unit analyzes the audio data collected by the collection unit and automatically generates minutes. The analysis unit converts the audio data into text data using, for example, voice recognition technology. For example, the analysis unit extracts the names of speakers and speech content as text and formats the text into minutes. Some or all of the above-described processing by the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input audio data into AI and have the AI ​​convert the audio data into text data. The creation unit automatically creates materials based on the minutes generated by the analysis unit. The creation unit automatically creates presentation materials and reports based on the contents of the minutes, for example. For example, the creation unit can automatically create presentation materials and reports based on the contents of the minutes. As a result, the automatic minutes creation system according to the embodiment can automatically collect and analyze audio data of a meeting, generate minutes, and further automatically create materials. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the contents of the minutes into AI and have the AI ​​create the materials.

[0064] The collection unit can collect audio data of a conference using microphones installed in the conference room. Examples of microphones installed in the conference room include, but are not limited to, directional microphones and omnidirectional microphones. For example, the collection unit can collect the audio of a specific speaker using directional microphones installed in the conference room. The collection unit can also collect audio from the entire conference room using omnidirectional microphones. For example, the collection unit can install an omnidirectional microphone in the center of the conference room to collect the entire audio. The collection unit can also efficiently collect audio data of a conference by combining multiple microphones. For example, the collection unit can install directional microphones in various locations in the conference room and collect the audio of each speaker individually. In this way, audio data of a conference can be efficiently collected using the microphones installed in the conference room. Some or all of the above-mentioned processing by the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input audio data acquired from the microphones installed in the conference room into AI and have the AI ​​collect the audio data.

[0065] The analysis unit can convert voice data into text data using voice recognition technology. Voice recognition technology includes, but is not limited to, deep learning-based voice recognition and HMM-based voice recognition. The analysis unit can convert voice data into text data with high accuracy using, for example, deep learning-based voice recognition technology. The analysis unit can also convert voice data into text data using HMM-based voice recognition technology. For example, the analysis unit inputs voice data into a deep learning model and outputs text data. The analysis unit can also input voice data into an HMM model and output text data. In this way, voice data can be accurately converted into text data using voice recognition technology. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input voice data into AI and have the AI ​​convert the voice data into text data.

[0066] The analysis unit can extract the speaker's name and the speech content as text and format it into minutes. Methods for extracting the speaker's name and the speech content include, but are not limited to, for example, speech recognition accuracy and a speaker identification method. The analysis unit, for example, extracts the speaker's name using speech recognition technology and records the speech content as text. The analysis unit can also accurately extract the speaker's name using a speaker identification method. For example, the analysis unit extracts the speaker's name using speech recognition technology and records the speech content as text. The analysis unit can also accurately extract the speaker's name using a speaker identification method. This accurately extracts the speaker's name and the speech content and formats it into minutes, thereby improving the quality of the minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input voice data into AI and have the AI ​​extract the speaker's name and the speech content.

[0067] The creation unit can automatically create presentation materials and reports based on the contents of the minutes. Presentation materials and reports include, but are not limited to, slide presentations and text reports, for example. The creation unit, for example, automatically creates a slide presentation based on the contents of the minutes. The creation unit can also automatically create a text report based on the contents of the minutes. For example, the creation unit automatically creates a slide presentation based on the contents of the minutes. The creation unit can also automatically create a text report based on the contents of the minutes. This automatically creates materials based on the contents of the minutes, thereby reducing the effort required for creating materials. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the contents of the minutes into AI and have the AI ​​create the materials.

[0068] The collection unit can estimate the user's emotions and adjust the timing of voice data collection based on the estimated user emotions. For example, if the user is nervous, the collection unit can start collecting voice data immediately after the start of the meeting to avoid missing important comments. Furthermore, if the user is relaxed, the collection unit can gradually collect voice data as the meeting progresses. Furthermore, if the user is tired, the collection unit can start collecting voice data from the middle of the meeting to focus on collecting important points. This allows the timing of voice data collection to be adjusted according to the user's emotions, preventing important comments from being missed. Emotion estimation is achieved using an emotion estimation function, such as 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 collection unit can be performed using, for example, an AI. For example, the collection unit can input the user's emotion data into an AI and have the AI ​​adjust the timing of voice data collection.

[0069] The collection unit can analyze the speech frequency of meeting participants and prioritize collecting important speech. For example, the collection unit can prioritize collecting speech from participants who speak frequently and reflect them in the minutes. The collection unit can also prioritize collecting speech from participants who speak less frequently but in important positions. The collection unit can also use AI to analyze speech frequency and the importance of speech content and prioritize collecting important speech. In this way, important speech can be prioritized by analyzing speech frequency. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input speech frequency data into AI and have the AI ​​execute the prioritized collection of important speech.

[0070] The collection unit can add a filtering function that automatically removes background noise when collecting audio data. For example, the collection unit can automatically remove noise from the air conditioner or projector in the conference room to clearly collect what is being said. The collection unit can also filter out chatter and unnecessary sounds during the meeting to collect only important comments. The collection unit can also automatically detect and remove noise outside the conference room to clearly collect what is being said. This allows for the removal of background noise and the clear collection of what is being said. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input background noise data into AI and have the AI ​​perform noise removal filtering.

[0071] The collection unit can estimate the user's emotions and determine the priority of the voice data to be collected based on the estimated user emotions. For example, when the user is nervous, the collection unit prioritizes collecting important utterances. Furthermore, when the user is relaxed, the collection unit can also collect all of the user's utterances in a balanced manner. Furthermore, when the user is tired, the collection unit can prioritize collecting utterances that highlight the main points. Thus, by determining the priority of the voice data according to the user's emotions, important utterances can be preferentially collected. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may 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 collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data into an AI and have the AI ​​determine the priority of the voice data.

[0072] When collecting voice data, the collection unit can limit the collection range based on the theme of the meeting. For example, if the theme of the meeting is technical, the collection unit can prioritize collecting technical comments. Furthermore, if the theme of the meeting is management strategy, the collection unit can also prioritize collecting comments related to management. Furthermore, if the theme of the meeting is project progress, the collection unit can also prioritize collecting comments related to the progress. In this way, by limiting the collection range based on the theme of the meeting, important comments can be collected efficiently. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input meeting theme data into AI and have the AI ​​limit the collection range.

[0073] When collecting voice data, the collection unit can customize the collection method based on the positions and expertise of the participants in the meeting. For example, the collection unit prioritizes collection of utterances from participants with higher positions. The collection unit can also prioritize collection of utterances from participants with extensive expertise. The collection unit can also prioritize collection of important utterances by taking into consideration both the positions and expertise. In this way, by customizing the collection method based on the positions and expertise of the participants, important utterances can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the positions and expertise data of the participants into AI and have the AI ​​customize the collection method.

[0074] The collection unit can automatically adjust collection settings according to the location and time of the meeting when collecting audio data. The collection unit automatically adjusts the collection settings, for example, taking into account the environmental sounds in the conference room. The collection unit can also automatically adjust the collection settings according to the time of the meeting. The collection unit can also automatically adjust optimal collection settings according to the location and time of the meeting. This enables optimal collection by automatically adjusting the collection settings according to the location and time of the meeting. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the location and time of the meeting into AI and have the AI ​​perform automatic adjustment of the collection settings.

[0075] The analysis unit can estimate the user's emotions and adjust the way the text data is expressed based on the estimated user's emotions. For example, if the user is nervous, the analysis unit can use a concise and clear expression. Furthermore, if the user is relaxed, the analysis unit can use a detailed and polite expression. Furthermore, if the user is tired, the analysis unit can use a concise expression that focuses on the main points. By adjusting the way the text data is expressed based on the user's emotions, more appropriate minutes are generated. The 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 analysis unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the analysis unit can input the user's emotion data into an AI and have the AI ​​adjust the way the text data is expressed.

[0076] When analyzing the audio data, the analysis unit can adjust the level of detail of the text data based on the importance of the utterance. For example, the analysis unit records important utterances in detail and other utterances briefly. The analysis unit can also dynamically adjust the level of detail of the text data according to the importance of the utterance. The analysis unit can also emphasize important utterances and record other utterances briefly. In this way, important utterances can be recorded in detail by adjusting the level of detail of the text data based on the importance of the utterance. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input utterance importance data into AI and have the AI ​​adjust the level of detail of the text data.

[0077] When analyzing the audio data, the analysis unit can apply different analysis algorithms depending on the theme of the meeting. For example, in a technical meeting, the analysis unit can apply an algorithm that accurately analyzes technical terms. In addition, in a meeting on business strategy, the analysis unit can also apply an algorithm that accurately analyzes management terms. In addition, in a meeting on project progress, the analysis unit can apply an algorithm that accurately analyzes terms related to progress. In this way, by applying an appropriate analysis algorithm depending on the theme of the meeting, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input meeting theme data into AI and have the AI ​​apply the analysis algorithm.

[0078] When analyzing the voice data, the analysis unit can improve the accuracy of the analysis by referring to past minutes data. For example, the analysis unit can refer to past minutes data and accurately analyze similar utterances. The analysis unit can also analyze the characteristics of the speaker based on the past minutes data to improve accuracy. The analysis unit can also refer to past minutes data and perform analysis according to the theme of the meeting. In this way, by referring to past minutes data, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past minutes data into AI and have the AI ​​improve the accuracy of the analysis.

[0079] The analysis unit can estimate the user's emotions and adjust the length of the text data based on the estimated user emotions. For example, if the user is nervous, the analysis unit can generate concise, short text data. Furthermore, if the user is relaxed, the analysis unit can generate detailed, long text data. Furthermore, if the user is tired, the analysis unit can generate short text data that focuses on the main points. By adjusting the length of the text data according to the user's emotions, more appropriate minutes can be generated. The 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 analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into an AI and have the AI ​​adjust the length of the text data.

[0080] When analyzing the audio data, the analysis unit can dynamically change the analysis method according to the progress of the conference. For example, the analysis unit analyzes all comments at the start of the conference, and as the conference progresses, it focuses on analyzing comments from specific speakers. Furthermore, if the conference progresses quickly, the analysis unit can increase the analysis frequency to avoid missing important comments. Furthermore, if the conference progresses slowly, the analysis unit can decrease the analysis frequency to focus on important comments. In this way, by changing the analysis method according to the progress of the conference, it is possible to analyze important comments without missing them. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input conference progress data into AI and have the AI ​​dynamically change the analysis method.

[0081] When analyzing audio data, the analysis unit can improve the accuracy of the analysis by referring to the speaker's past speech history. For example, the analysis unit can refer to the speaker's past speech history and accurately analyze similar speech content. The analysis unit can also analyze the speaker's characteristics based on the speaker's past speech history to improve accuracy. The analysis unit can also refer to the speaker's past speech history and perform analysis according to the theme of the meeting. In this way, by referring to the speaker's past speech history, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the speaker's past speech history data into AI and have the AI ​​improve the accuracy of the analysis.

[0082] The creation unit can estimate the user's emotions and adjust the presentation style of the materials based on the estimated user emotions. For example, if the user is nervous, the creation unit can use a concise and clear presentation style. Furthermore, if the user is relaxed, the creation unit can use a detailed and polite presentation style. Furthermore, if the user is tired, the creation unit can use a concise presentation style that focuses on the main points. By adjusting the presentation style of the materials according to the user's emotions, more appropriate materials can be created. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can 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 creation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the creation unit can input the user's emotion data into an AI and have the AI ​​adjust the presentation style of the materials.

[0083] The creation unit can adjust the level of detail of the materials based on the importance of the minutes when creating the materials. For example, the creation unit records important minutes in detail and other minutes in brief. The creation unit can also dynamically adjust the level of detail of the materials according to the importance of the minutes. The creation unit can also emphasize important minutes and record other minutes in brief. In this way, important content can be recorded in detail by adjusting the level of detail of the materials based on the importance of the minutes. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input importance data of the minutes into AI and have the AI ​​adjust the level of detail of the materials.

[0084] When creating materials, the creation unit can apply different material creation algorithms depending on the theme of the meeting. For example, in a technical meeting, the creation unit can apply an algorithm that accurately analyzes technical terms. In a meeting on business strategy, the creation unit can also apply an algorithm that accurately analyzes business terms. In a meeting on project progress, the creation unit can also apply an algorithm that accurately analyzes terms related to progress. This improves the accuracy of the materials by applying an appropriate material creation algorithm depending on the theme of the meeting. Some or all of the above-mentioned processing in the creation unit can be performed using, for example, AI, or can be performed without using AI. For example, the creation unit can input meeting theme data into AI and have the AI ​​apply the material creation algorithm.

[0085] When creating a document, the creation unit can improve the accuracy of the creation by referring to past document data. For example, the creation unit references past document data to accurately reflect similar content. The creation unit can also unify the format and style of the document based on the past document data. The creation unit can also create a document according to the theme of the meeting by referring to the past document data. In this way, the accuracy of the document is improved by referring to the past document data. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input past document data into AI and have the AI ​​improve the accuracy of the creation.

[0086] The creation unit can estimate the user's emotions and adjust the length of the materials based on the estimated user emotions. For example, if the user is nervous, the creation unit can create concise, short materials. Furthermore, if the user is relaxed, the creation unit can create detailed, long materials. Furthermore, if the user is tired, the creation unit can create short materials that focus on the main points. This allows for the creation of more appropriate materials by adjusting the length of the materials according to the user's emotions. The 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 creation unit can be performed using, for example, an AI, or without an AI. For example, the creation unit can input the user's emotion data into an AI and have the AI ​​adjust the length of the materials.

[0087] When creating materials, the creation unit can dynamically change the presentation method of the materials depending on the progress of the meeting. For example, the creation unit can briefly summarize the overall content at the start of the meeting and add more detailed content as the meeting progresses. Furthermore, if the meeting progresses quickly, the creation unit can increase the frequency of creating materials to avoid missing important content. Furthermore, if the meeting progresses slowly, the creation unit can reduce the frequency of creating materials to focus on important content. In this way, by changing the presentation method of the materials depending on the progress of the meeting, important content can be recorded without missing it. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input meeting progress data into AI and have the AI ​​dynamically change the presentation method of the materials.

[0088] When creating materials, the creation unit can customize the presentation method of the materials based on the speaker's position and expertise. For example, the creation unit records in detail the statements of speakers with high positions. The creation unit can also record in detail the statements of speakers with extensive expertise. The creation unit can also customize the presentation method of the materials taking into consideration both the position and expertise. In this way, important content can be recorded in detail by customizing the presentation method based on the speaker's position and expertise. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the speaker's position and expertise data into AI and have the AI ​​customize the presentation method of the materials.

[0089] When creating a document, the creation unit can automatically adjust the content of the document depending on the location and time of the meeting. For example, the creation unit automatically adjusts the content of the document taking into account the ambient noise in the conference room. The creation unit can also automatically adjust the content of the document depending on the time of the meeting. The creation unit can also automatically adjust the content of the document to be optimal depending on the location and time of the meeting. In this way, optimal documents are created by adjusting the content of the document depending on the location and time of the meeting. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the location and time of the meeting into AI and have the AI ​​automatically adjust the content of the document.

[0090] When creating materials, the creation unit can customize the presentation method of the materials based on the speaker's position and expertise. For example, the creation unit records in detail the statements of speakers with high positions. The creation unit can also record in detail the statements of speakers with extensive expertise. The creation unit can also customize the presentation method of the materials taking into consideration both the position and expertise. In this way, important content can be recorded in detail by customizing the presentation method based on the speaker's position and expertise. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input the speaker's position and expertise data into AI and have the AI ​​customize the presentation method of the materials.

[0091] When creating a document, the creation unit can automatically adjust the content of the document depending on the location and time of the meeting. For example, the creation unit automatically adjusts the content of the document taking into account the ambient noise in the conference room. The creation unit can also automatically adjust the content of the document depending on the time of the meeting. The creation unit can also automatically adjust the content of the document to be optimal depending on the location and time of the meeting. In this way, optimal documents are created by adjusting the content of the document depending on the location and time of the meeting. Some or all of the above-described processing in the creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the creation unit can input data on the location and time of the meeting into AI and have the AI ​​automatically adjust the content of the document. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, and creation unit described above may be realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit may collect audio data of a meeting using the microphone 38B of the smart device 14. For example, the analysis unit may convert the audio data into text data by the specific processing unit 290 of the data processing device 12. For example, the creation unit may automatically create materials based on the minutes generated by the specific processing unit 290 of the data processing device 12. For example, each of the collection unit, analysis unit, and creation unit may also be realized by the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, and creation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect audio data of a meeting using the microphone 238 of the smart glasses 214. For example, the analysis unit can convert the audio data into text data by the specific processing unit 290 of the data processing device 12. For example, the creation unit can automatically create materials based on the minutes generated by the specific processing unit 290 of the data processing device 12. For example, each of the collection unit, analysis unit, and creation unit can also be realized by the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, and creation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit can collect audio data of a conference using the microphone 238 of the headset type terminal 314. For example, the analysis unit can convert the audio data into text data by the specific processing unit 290 of the data processing device 12. For example, the creation unit can automatically create materials based on the minutes generated by the specific processing unit 290 of the data processing device 12. For example, each of the collection unit, analysis unit, and creation unit can also be realized by the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned collection unit, analysis unit, and creation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect audio data of a meeting using the microphone 238 of the robot 414. For example, the analysis unit can convert the audio data into text data by the specific processing unit 290 of the data processing device 12. For example, the creation unit can automatically create materials based on the minutes generated by the specific processing unit 290 of the data processing device 12. For example, each of the collection unit, analysis unit, and creation unit can also be realized by the control unit 46A of the robot 414.

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

[0093] The collection unit can translate statements made by meeting participants in real time and record them in multiple languages. For example, the collection unit can translate statements made in English into Japanese and reflect them in the minutes. The collection unit can also translate statements made in French into English and reflect them in the minutes. If meeting participants speak different languages, the collection unit can also translate each language and reflect them in the minutes. This makes it possible to create accurate minutes even for meetings with participants speaking different languages. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input voice data into AI and have the AI ​​perform the translation.

[0094] The collection unit can summarize the statements made by meeting participants in real time and record only the important points. For example, the collection unit can summarize long statements in short sentences and reflect them in the minutes. The collection unit can also summarize multiple statements together and reflect them in the minutes. The collection unit can also summarize important points in real time as the meeting progresses and reflect them in the minutes. This makes it possible to efficiently record important points even in long meetings. Some or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can input audio data into AI and have the AI ​​perform the summarization.

[0095] The analysis unit can perform emotional analysis of the speech content of meeting participants and record the tone and emotions of the speech. For example, if a speech contains anger, the analysis unit can reflect that emotion in the minutes. Furthermore, if a speech contains joy, the analysis unit can also reflect that emotion in the minutes. Furthermore, if a speech contains sadness, the analysis unit can also reflect that emotion in the minutes. By recording the emotions of speech, the atmosphere of the meeting and the emotions of the participants can be accurately grasped. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input voice data into an AI and have the AI ​​perform emotion analysis.

[0096] The analysis unit can classify the content of comments made by meeting participants in real time and organize the minutes by theme. For example, the analysis unit can classify technical comments into a technology category and reflect this in the minutes. The analysis unit can also classify comments related to management into a management category and reflect this in the minutes. The analysis unit can also classify comments related to project progress into a project category and reflect this in the minutes. In this way, organizing the minutes by theme makes them easier to search and refer to later. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the classification.

[0097] The analysis unit can evaluate the content of statements made by meeting participants in real time and record the reliability of the statements. For example, if a statement is based on a reliable source, the analysis unit can reflect the reliability in the minutes. If a statement is based on uncertain information, the analysis unit can also reflect the reliability in the minutes. If a statement is consistent with past data, the analysis unit can also reflect the reliability in the minutes. By recording the reliability of statements, this makes it easier to verify and reference them later. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the evaluation.

[0098] The analysis unit can perform emotional analysis of the speech of meeting participants in real time and record the tone and emotions of the speech. For example, if a speech contains anger, the analysis unit can reflect that emotion in the minutes. Furthermore, if a speech contains joy, the analysis unit can also reflect that emotion in the minutes. Furthermore, if a speech contains sadness, the analysis unit can also reflect that emotion in the minutes. By recording the emotions of speech, the atmosphere of the meeting and the emotions of the participants can be accurately grasped. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input voice data into an AI and have the AI ​​perform emotion analysis.

[0099] The analysis unit can summarize the statements made by meeting participants in real time and record only the important points. For example, the analysis unit can summarize long statements in shorter form and reflect them in the minutes. The analysis unit can also summarize multiple statements together and reflect them in the minutes. The analysis unit can also summarize important points in real time as the meeting progresses and reflect them in the minutes. This makes it possible to efficiently record important points even in long meetings. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input audio data into AI and have the AI ​​perform the summarization.

[0100] The analysis unit can classify the content of comments made by meeting participants in real time and organize the minutes by theme. For example, the analysis unit can classify technical comments into a technology category and reflect this in the minutes. The analysis unit can also classify comments related to management into a management category and reflect this in the minutes. The analysis unit can also classify comments related to project progress into a project category and reflect this in the minutes. In this way, organizing the minutes by theme makes them easier to search and refer to later. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the classification.

[0101] The analysis unit can evaluate the content of statements made by meeting participants in real time and record the reliability of the statements. For example, if a statement is based on a reliable source, the analysis unit can reflect the reliability in the minutes. If a statement is based on uncertain information, the analysis unit can also reflect the reliability in the minutes. If a statement is consistent with past data, the analysis unit can also reflect the reliability in the minutes. By recording the reliability of statements, this makes it easier to verify and reference them later. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input voice data into AI and have the AI ​​perform the evaluation.

[0102] The analysis unit can perform emotional analysis of the speech of meeting participants in real time and record the tone and emotions of the speech. For example, if a speech contains anger, the analysis unit can reflect that emotion in the minutes. Furthermore, if a speech contains joy, the analysis unit can also reflect that emotion in the minutes. Furthermore, if a speech contains sadness, the analysis unit can also reflect that emotion in the minutes. By recording the emotions of speech, the atmosphere of the meeting and the emotions of the participants can be accurately grasped. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input voice data into an AI and have the AI ​​perform emotion analysis.

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

[0104] Step 1: The collection unit collects audio data of the meeting. For example, the collection unit collects audio data of the meeting using a microphone installed in the meeting room. The collection unit can also record what the participants in the meeting say and save it as audio data. Step 2: The analysis unit analyzes the voice data collected by the collection unit and automatically generates minutes. The analysis unit converts the voice data into text data, for example, using voice recognition technology. For example, the analysis unit extracts the names of speakers and the content of their remarks as text and formats it into minutes. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. Step 3: The creation unit automatically creates materials based on the minutes generated by the analysis unit. The creation unit automatically creates, for example, presentation materials or reports based on the contents of the minutes. Some or all of the above-mentioned processing in the creation unit may be performed using, for example, AI, or may be performed without using AI.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (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.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0159] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0160] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0161] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0162] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0163] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0164] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0165] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0166] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0167] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0168] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

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

[0170] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0171] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0172] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0173] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0174] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0175] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects audio data of the conference; an analysis unit that analyzes the voice data collected by the collection unit and automatically generates minutes; a creation unit that automatically creates materials based on the minutes generated by the analysis unit; Equipped with A system characterized by:

2. The collecting unit Collect audio data from the meeting using microphones installed in the meeting room 2. The system of claim 1.

3. The analysis unit Converting voice data into text data using voice recognition technology 2. The system of claim 1.

4. The analysis unit Extract the speaker's name and the content of the speech as text and format it into minutes.

2. The system of claim 1.

5. The creation unit Automatically create presentation materials and reports based on the contents of meeting minutes 2. The system of claim 1.

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

2. The system of claim 1.

7. The collecting unit Analyze the frequency of speech by meeting participants and prioritize collection of important speech 2. The system of claim 1.

8. The collecting unit Dynamically change the collection method for audio data collection depending on the progress of the meeting.

2. The system of claim 1.

Images