system

Abstract

The system according to this embodiment aims to generate meeting minutes that visually capture the participants' emotions along with the content of the meeting. [Solution] The system according to the embodiment comprises a collection unit, an emotion analysis unit, and a meeting minutes generation unit. The collection unit collects audio data of the meeting. The emotion analysis unit analyzes the audio data collected by the collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. The meeting minutes generation unit generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to visually grasp the warmth of conversation and the emotions of participants in the minutes of a meeting.

[0005] The system according to the embodiment aims to generate minutes that can visually grasp the emotions of participants together with the content of a meeting.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, an emotion analysis unit, and a meeting minutes generation unit. The data collection unit collects audio data of the meeting. The emotion analysis unit analyzes the audio data collected by the data collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. The meeting minutes generation unit generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can generate meeting minutes that visually capture the participants' emotions along with the content of the meeting. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that automatically generates manga-style meeting minutes that visualize the emotions of meeting participants using a generation AI. This system collects audio data from meetings, and the generation AI analyzes this audio data to automatically create meeting minutes. In this process, the generation AI analyzes not only the content of the conversation but also the tone of the conversation and the emotions of the participants. Next, the generation AI generates meeting minutes in manga format based on the emotion data it has analyzed. These manga-style meeting minutes visually represent not only the content of the conversation but also the emotions of the participants and the tone of the conversation. This mechanism makes the meeting minutes extremely easy to understand and visualizes the tone of the conversation and the emotions of the participants. As a result, the content of the meeting can be grasped more accurately, and all participants can have the same understanding. In addition, since the creation of meeting minutes is automated, time is saved and meeting records can be kept efficiently. For example, audio data from meetings is collected. In this process, detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their speech are collected. For example, if a speaker says, "I think this proposal is wonderful," the tone of their voice and the speed of their speech are collected along with the content of that statement. Next, the generating AI analyzes the collected audio data. The generating AI determines emotions not only from the content of what is said, but also from the tone and speed of the speaker's voice and word choice. For example, if the speaker is happy, the generating AI will determine that emotion as "joy." Furthermore, based on the emotion data analyzed by the generating AI, it generates meeting minutes in a manga format. The generating AI draws a character that visually represents the speaker's emotions along with the content of what was said. For example, if the speaker says, "I think this proposal is wonderful," and the generating AI determines that emotion as "joy," a character with a joyful expression will be drawn and displayed along with the content of what was said. This system makes meeting minutes extremely easy to understand, and the tone of the conversation and the emotions of the participants are made visible. As a result, the content of the meeting can be grasped more accurately, and all participants can share the same understanding. In addition, since the creation of meeting minutes is automated, time is saved, and meeting records can be kept efficiently.

[0029] The system according to this embodiment comprises a data collection unit, an emotion analysis unit, and a meeting minutes generation unit. The data collection unit collects audio data of the meeting. The data collection unit can collect detailed data such as the content of what is said during the meeting, the tone of the speaker's voice, and the speed of their speech. For example, the data collection unit collects the content of what is said during the meeting using a high-precision microphone. The data collection unit can also use speech analysis technology to analyze the tone of the speaker's voice and the speed of their speech. For example, the data collection unit can analyze changes in the tone of the speaker's voice in real time and detect changes in emotion. The emotion analysis unit analyzes the audio data collected by the data collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. For example, the emotion analysis unit can determine emotions from the tone of the speaker's voice, the speed of their speech, and their choice of words. For example, the emotion analysis unit can determine that the speaker's voice tone is high, indicating an emotion of joy. The emotion analysis unit can also determine that the speaker's voice speed is fast, indicating an emotion of excitement. Furthermore, the emotion analysis unit can also determine emotions from the speaker's choice of words. For example, the emotion analysis unit determines that a speaker who uses many positive words is feeling joyful. The minutes generation unit generates minutes in manga format based on the emotion data determined by the emotion analysis unit. The minutes generation unit can, for example, draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, the minutes generation unit draws a character with a joyful expression. It can also draw a character with a surprised expression if the speaker is surprised. Furthermore, it can draw a character with a sad expression if the speaker is sad. This allows the system to visually represent the tone of the conversation and the emotions of the participants. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can generate minutes using a generation AI model that takes emotion data determined by the emotion analysis unit as input and outputs minutes in manga format. This allows the system to visually represent the tone of the conversation and the emotions of the participants.

[0030] The data collection unit collects audio data from meetings. The unit can collect detailed data, such as the content of speech during meetings, the tone of the speaker's voice, and their speaking speed. Specifically, the unit uses high-precision microphones to clearly capture the content of speech during meetings. This allows for accurate capture of even the subtle nuances and intonation of the speaker's voice. Furthermore, the unit uses speech analysis technology to analyze the tone and speed of the speaker's voice in real time. For example, speech analysis technology can analyze the frequency components of the speaker's voice and detect changes in tone. Additionally, to analyze the speed of the speaker's voice, the unit measures the temporal fluctuations of the audio data to understand the speed and rhythm of speech. This enables the data collection unit to detect changes in the speaker's emotions and level of tension in real time. The data collection unit has an interface for centrally managing this data and providing it to the emotion analysis unit and the meeting minutes generation unit. For example, the collected audio data is stored on a cloud server and can be linked with other systems and departments as needed. The data collection unit can also adjust the frequency and accuracy of data collection, allowing for flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0031] The emotion analysis unit analyzes the audio data collected by the collection unit to determine the tone of the conversation and the emotions of the participants, along with the content of the conversation. Specifically, the emotion analysis unit can determine emotions from the tone and speed of the speaker's voice and word choice. For example, a high tone of voice indicates joy, and a fast speaking speed indicates excitement. The emotion analysis unit analyzes the frequency components and temporal fluctuations of the audio data to detect changes in the speaker's emotions in real time. Furthermore, the emotion analysis unit can also determine emotions from the speaker's word choice. For example, a speaker who uses many positive words can be judged as happy, and a speaker who uses many negative words can be judged as sad. Based on these analysis results, the emotion analysis unit generates data to visually represent the tone of the conversation and the emotions of the participants. The emotion analysis unit can improve the accuracy of audio data analysis using AI technology. For example, it can train a speech recognition model using deep learning to determine the speaker's emotions with high accuracy. This allows the sentiment analysis unit to quickly and accurately analyze collected audio data, enabling it to grasp the tone of the conversation and the emotions of the participants in real time. Furthermore, the sentiment analysis unit can also utilize historical data and statistical information to analyze long-term emotional trends and patterns. As a result, the sentiment analysis unit can handle not only real-time sentiment analysis but also long-term emotional fluctuations and trend analysis, improving the reliability and accuracy of the entire system.

[0032] The meeting minutes generation unit generates meeting minutes in manga format based on emotional data determined by the emotion analysis unit. Specifically, the meeting minutes generation unit can draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, it can draw a character with a happy expression; if a speaker is surprised, it can draw a character with a surprised expression. The meeting minutes generation unit can generate meeting minutes using a generation AI model that takes emotional data provided by the emotion analysis unit as input and outputs meeting minutes in manga format. The generation AI model automatically generates appropriate characters and scenes based on the content of the statements and emotional data, creating visually easy-to-understand meeting minutes. For example, if a speaker is sad, it can draw a character with a sad expression and generate a scene corresponding to the content of the statement. Furthermore, the meeting minutes generation unit provides an interface for editing the generated manga-style meeting minutes, allowing users to make corrections and additions as needed. This enables the meeting minutes generation unit to visually represent the tone of the conversation and the emotions of the participants, making the content of the meeting easier to understand. The meeting minutes generation unit, by utilizing generation AI, automates the meeting minutes generation process, enabling efficient and rapid creation of meeting minutes. This allows the system to visually represent the nuances of the conversation and the emotions of the participants, making the meeting content easier to understand. Furthermore, the meeting minutes generation unit can save the generated minutes to the cloud and share them with other systems and departments as needed. This allows the meeting minutes generation unit to generate minutes efficiently and effectively, improving the overall system performance.

[0033] The data collection unit can collect detailed data such as the content of speech during meetings, the tone of voice of the speakers, and their speaking speed. For example, the data collection unit can collect the content of speech during meetings using a high-precision microphone. The data collection unit can use speech analysis technology to analyze the tone of voice and speaking speed of the speakers. For example, the data collection unit can analyze changes in the tone of voice of the speakers in real time to detect changes in emotion. The data collection unit can also analyze the speed of the speakers' voices to grasp the tempo of their speech. For example, the data collection unit can determine that a fast speaking speed indicates excitement. Based on changes in the tone of voice and speaking speed of the speakers, the data collection unit can detect changes in emotion in real time. As a result, by collecting detailed data such as the content of speech during meetings, the tone of voice of the speakers, and their speaking speed, the data collection unit can perform more accurate emotion analysis. Detailed data includes, but is not limited to, the content of speech, tone of voice, speaking speed, and pauses. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their voice into an AI model, allowing the AI ​​model to perform data collection and analysis.

[0034] The emotion analysis unit can determine emotions from the speaker's tone of voice, speed, and word choice. For example, if the speaker's tone of voice is high, the emotion analysis unit will determine that the speaker is feeling joy. If the speaker's speed is fast, the emotion analysis unit can also determine that the speaker is feeling excitement. The emotion analysis unit can also determine emotions from the speaker's word choice. For example, if the emotion analysis unit uses many positive words, it will determine that the speaker is feeling joy. If the speaker uses many negative words, it will determine that the speaker is feeling sadness. The emotion analysis unit can determine emotions by comprehensively analyzing the speaker's tone of voice, speed, and word choice. This allows the emotion analysis unit to perform more accurate emotion analysis by determining emotions from the speaker's tone of voice, speed, and word choice. Word choice includes, but is not limited to, positive words, negative words, and the use of technical terms. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's tone of voice, speed, and word choice into an AI model, and have the AI ​​model perform an emotion determination.

[0035] The minutes generation unit can create a character that visually represents the speaker's emotions along with the content of their remarks. For example, if the speaker is happy, the minutes generation unit will create a character with a happy expression. If the speaker is surprised, the minutes generation unit can also create a character with a surprised expression. If the speaker is sad, the minutes generation unit can also create a character with a sad expression. The minutes generation unit can devise the character's facial expression and pose to visually represent the speaker's emotions. For example, if the speaker is happy, the minutes generation unit will create a smiling character. Also, if the speaker is surprised, the minutes generation unit can create a character with a surprised expression. Furthermore, if the speaker is sad, the minutes generation unit can create a character that is shedding tears. In this way, the minutes generation unit makes the minutes easier to understand by creating a character that visually represents the speaker's emotions along with the content of their remarks. Visual representations of characters include, but are not limited to, facial expressions, poses, and clothing to express emotions. Some or all of the above-described processes in the minutes generation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the minutes generation unit can input the content of the speeches and emotional data into a generation AI model and have the generation AI model draw the characters.

[0036] The meeting minutes generation unit can generate meeting minutes in manga format based on emotional data analyzed by the generation AI. For example, the meeting minutes generation unit can draw characters that visually represent the speaker's emotions along with the content of their statements. If the speaker is happy, the meeting minutes generation unit will draw a character with a happy expression. If the speaker is surprised, the meeting minutes generation unit can also draw a character with a surprised expression. If the speaker is sad, the meeting minutes generation unit can also draw a character with a sad expression. The meeting minutes generation unit can devise the character's expression and pose to visually represent the speaker's emotions. For example, if the speaker is happy, the meeting minutes generation unit will draw a smiling character. Also, if the speaker is surprised, the meeting minutes generation unit can draw a character with a surprised expression. Furthermore, if the speaker is sad, the meeting minutes generation unit can draw a character shedding tears. This allows the minutes generation unit to visually represent the tone of the conversation and the emotions of the participants by generating minutes in manga format based on the emotion data analyzed by the generation AI. The generation AI includes, but is not limited to, deep learning, natural language processing, and image generation technologies. Some or all of the above-described processes in the minutes generation unit may be performed using the generation AI or not. For example, the minutes generation unit can input the content of the statements and emotion data into a generation AI model and have the generation AI model generate minutes in manga format.

[0037] The emotion analysis unit can determine that a speaker is happy if that emotion is "joyful." For example, the emotion analysis unit can determine joyfulness if the speaker's voice tone is high. The emotion analysis unit can also determine excitement if the speaker's voice speed is fast. The emotion analysis unit can also determine emotions from the speaker's word choices. For example, the emotion analysis unit will determine joyfulness if the speaker uses many positive words. The emotion analysis unit can also determine sadness if the speaker uses many negative words. The emotion analysis unit can determine emotions by comprehensively analyzing the speaker's voice tone, speed, and word choices. As a result, the emotion analysis unit can improve the accuracy of emotion analysis by determining that a speaker is happy if that emotion is "joyful." The criteria for determining joy include, but are not limited to, an increase in voice tone, laughter, and the use of positive words. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's tone of voice, speed, and word choice into an AI model, and have the AI ​​model perform an emotion determination.

[0038] The data collection unit can collect not only the content of what is said during a meeting, but also the speaker's gestures and facial expressions. For example, if a speaker raises their hand, the data collection unit can capture that gesture with a camera and collect it along with the audio data. If a speaker is smiling, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. If a speaker is frowning, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. This allows the data collection unit to use more detailed data for analysis by also collecting the speaker's gestures and facial expressions. The collection of gestures and facial expressions includes, but is not limited to, the use of a camera and image analysis techniques. Some or all of the processing described above in the data collection unit may or may not be performed using AI. For example, the data collection unit can input the speaker's gesture and facial expression data into an AI model and have the AI ​​model perform data collection and analysis.

[0039] The data collection unit can simultaneously collect background and ambient sounds from a meeting when collecting audio data, and use them for analysis. For example, the data collection unit can collect background sounds from a meeting room and analyze them separately from the speaker's voice. The data collection unit can also collect noise from outside a window and analyze it separately from the speaker's voice. The data collection unit can also collect keyboard typing sounds during a meeting and analyze them separately from the speaker's voice. This allows the data collection unit to perform more accurate analysis by simultaneously collecting background and ambient sounds from the meeting. Examples of background and ambient sound collection include, but are not limited to, noise cancellation and audio filtering technologies. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on background and ambient sounds from a meeting into an AI model and have the AI ​​model perform data collection and analysis.

[0040] The data collection unit can filter audio data based on the job titles and areas of expertise of meeting participants. For example, the data collection unit may prioritize collecting statements from participants with higher job titles. It may also prioritize collecting statements from participants whose areas of expertise are relevant to the meeting agenda. The data collection unit may also postpone collecting statements from participants with lower job titles. In this way, the data collection unit can prioritize the collection of important data by filtering the data based on the job titles and areas of expertise of meeting participants. Data filtering may include, but is not limited to, the importance of job titles and the relevance of areas of expertise. Some or all of the processing described above in the data collection unit may be performed using AI or not. For example, the data collection unit may input data on the job titles and areas of expertise of meeting participants into an AI model and have the AI ​​model perform the data filtering.

[0041] The data collection unit can adjust the collection scope based on the meeting agenda and themes when collecting audio data. For example, the data collection unit can prioritize collecting statements related to the meeting agenda. The data collection unit can also postpone collecting statements unrelated to the meeting themes. The data collection unit can also collect statements related to the meeting agenda in detail. In this way, the data collection unit can collect highly relevant data by adjusting the collection scope based on the meeting agenda and themes. Adjustments to the collection scope include, but are not limited to, the importance of the agenda and the relevance of the themes. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input meeting agenda and theme data into an AI model and have the AI ​​model perform the adjustment of the collection scope.

[0042] The emotion analysis unit can analyze not only the tone and speed of the speaker's voice, but also their breathing pattern and heart rate. For example, if the speaker's breathing is rapid, the emotion analysis unit may analyze that the speaker is nervous. If the speaker's heart rate is high, the emotion analysis unit may analyze that the speaker is excited. If the speaker's breathing is slow, the emotion analysis unit may analyze that the speaker is relaxed. This allows the emotion analysis unit to perform a more detailed emotional analysis by also analyzing the speaker's breathing pattern and heart rate. The analysis of breathing patterns and heart rate may include, but is not limited to, the use of sensors or biosignal analysis techniques. Some or all of the processing described above in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input data on the speaker's breathing pattern and heart rate into an AI model and have the AI ​​model perform the data analysis.

[0043] The emotion analysis unit can determine changes in emotion by referring to the speaker's past statement history during emotion analysis. For example, if the speaker was happy in the past, the emotion analysis unit can determine changes in emotion by comparing it to the current statement. If the speaker was angry in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. If the speaker was sad in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. In this way, the emotion analysis unit can accurately determine changes in emotion by referring to the speaker's past statement history. Referencing the statement history includes, but is not limited to, past meeting records, frequency and content of statements. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's past statement history into an AI model and have the AI ​​model perform the determination of changes in emotion.

[0044] The sentiment analysis unit can perform sentiment analysis while considering the progress of the meeting and the progress of the agenda. For example, if the meeting is progressing quickly, the sentiment analysis unit can perform sentiment analysis quickly. If the meeting is progressing slowly, the sentiment analysis unit can also perform sentiment analysis in detail. The sentiment analysis unit can also adjust the accuracy of sentiment analysis according to the progress of the agenda. This allows the sentiment analysis unit to perform more accurate sentiment analysis by considering the progress of the meeting and the progress of the agenda. Consideration of the progress of the meeting and the progress of the agenda includes, but is not limited to, the stage of the agenda and the order of speeches. Some or all of the above processing in the sentiment analysis unit may be performed using AI or not. For example, the sentiment analysis unit can input data on the progress of the meeting and the progress of the agenda into an AI model and have the AI ​​model perform the adjustment of the analysis.

[0045] The sentiment analysis unit can improve the accuracy of its analysis by considering the speaker's cultural background and linguistic characteristics during sentiment analysis. For example, the sentiment analysis unit adjusts the sentiment analysis algorithm by considering the speaker's cultural background. The sentiment analysis unit can also adjust the sentiment analysis algorithm by considering the speaker's linguistic characteristics. The sentiment analysis unit can also improve the accuracy of sentiment analysis based on the speaker's cultural background and linguistic characteristics. As a result, the sentiment analysis unit improves its analysis accuracy by considering the speaker's cultural background and linguistic characteristics. Consideration of cultural background and linguistic characteristics includes, but is not limited to, culture-specific expressions and linguistic nuances. Some or all of the above processing in the sentiment analysis unit may be performed using AI or not. For example, the sentiment analysis unit can input data on the speaker's cultural background and linguistic characteristics into an AI model and have the AI ​​model perform the adjustment of the analysis.

[0046] The minutes generation unit can highlight important points and decisions made during the generation of meeting minutes. For example, the minutes generation unit can display important points in bold. The minutes generation unit can also display decisions made in color. The minutes generation unit can also display important points and decisions made in the meeting using icons. This makes the minutes easier to understand by highlighting important points and decisions made in the meeting. Highlighting important points and decisions includes, but is not limited to, changing the color or font size. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on important points and decisions made in the meeting into a generation AI model and have the generation AI model execute the highlighting method.

[0047] The minutes generation unit can update the minutes in real time according to the progress of the meeting when generating the minutes. For example, the minutes generation unit updates the minutes in real time in accordance with the progress of the meeting. The minutes generation unit can also update the minutes in real time if the meeting is progressing quickly. The minutes generation unit can also update the minutes in real time if the meeting is progressing slowly. As a result, the minutes generation unit updates the minutes in real time according to the progress of the meeting, so that the latest information is immediately reflected. Methods for updating the minutes in real time include, but are not limited to, automatic update timing and update triggers. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can input data on the progress of the meeting into a generation AI model and have the generation AI model execute the real-time update method.

[0048] The minutes generation unit can customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. For example, the minutes generation unit can generate concise minutes for participants with higher job titles. It can also generate detailed minutes for participants whose areas of expertise are relevant to the meeting agenda. It can also generate brief minutes for participants with lower job titles. In this way, the minutes generation unit generates optimal minutes for each participant by customizing the content based on the job titles and areas of expertise of the meeting participants. Customization of the content of the minutes includes, but is not limited to, key points for each job title and detailed explanations for each area of ​​expertise. Some or all of the above processing in the minutes generation unit may be performed using or without a generation AI. For example, the minutes generation unit can input data on the job titles and areas of expertise of the meeting participants into a generation AI model and have the generation AI model perform the content customization.

[0049] The minutes generation unit can adjust the structure of the minutes based on the meeting agenda and themes when generating them. For example, the minutes generation unit can prioritize including content related to the meeting agenda in the minutes. The minutes generation unit can also postpone including content unrelated to the meeting themes. The minutes generation unit can also include detailed content related to the meeting agenda in the minutes. In this way, the minutes generation unit generates highly relevant minutes by adjusting the structure of the minutes based on the meeting agenda and themes. Adjustments to the structure of the minutes include, but are not limited to, dividing the minutes into sections by agenda item and summarizing by theme. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on the meeting agenda and themes into a generation AI model and have the generation AI model perform the adjustment of the structure.

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

[0051] The data collection unit can collect not only the content of what is said during a meeting, but also the speaker's gestures and facial expressions. For example, if a speaker raises their hand, the data collection unit can capture that gesture with a camera and collect it along with the audio data. If a speaker is smiling, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. If a speaker is frowning, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. This allows the data collection unit to use more detailed data for analysis by also collecting the speaker's gestures and facial expressions. The collection of gestures and facial expressions includes, but is not limited to, the use of a camera and image analysis techniques. Some or all of the processing described above in the data collection unit may or may not be performed using AI. For example, the data collection unit can input the speaker's gesture and facial expression data into an AI model and have the AI ​​model perform data collection and analysis.

[0052] The emotion analysis unit can analyze not only the tone and speed of the speaker's voice, but also their breathing pattern and heart rate. For example, if the speaker's breathing is rapid, the emotion analysis unit may analyze that the speaker is nervous. If the speaker's heart rate is high, the emotion analysis unit may analyze that the speaker is excited. If the speaker's breathing is slow, the emotion analysis unit may analyze that the speaker is relaxed. This allows the emotion analysis unit to perform a more detailed emotional analysis by also analyzing the speaker's breathing pattern and heart rate. The analysis of breathing patterns and heart rate may include, but is not limited to, the use of sensors or biosignal analysis techniques. Some or all of the processing described above in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input data on the speaker's breathing pattern and heart rate into an AI model and have the AI ​​model perform the data analysis.

[0053] The data collection unit can simultaneously collect background and ambient sounds from a meeting when collecting audio data, and use them for analysis. For example, the data collection unit can collect background sounds from a meeting room and analyze them separately from the speaker's voice. The data collection unit can also collect noise from outside a window and analyze it separately from the speaker's voice. The data collection unit can also collect keyboard typing sounds during a meeting and analyze them separately from the speaker's voice. This allows the data collection unit to perform more accurate analysis by simultaneously collecting background and ambient sounds from the meeting. Examples of background and ambient sound collection include, but are not limited to, noise cancellation and audio filtering technologies. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on background and ambient sounds from a meeting into an AI model and have the AI ​​model perform data collection and analysis.

[0054] The emotion analysis unit can determine changes in emotion by referring to the speaker's past statement history during emotion analysis. For example, if the speaker was happy in the past, the emotion analysis unit can determine changes in emotion by comparing it to the current statement. If the speaker was angry in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. If the speaker was sad in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. In this way, the emotion analysis unit can accurately determine changes in emotion by referring to the speaker's past statement history. Referencing the statement history includes, but is not limited to, past meeting records, frequency and content of statements. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's past statement history into an AI model and have the AI ​​model perform the determination of changes in emotion.

[0055] The minutes generation unit can highlight important points and decisions made during the generation of meeting minutes. For example, the minutes generation unit can display important points in bold. The minutes generation unit can also display decisions made in color. The minutes generation unit can also display important points and decisions made in the meeting using icons. This makes the minutes easier to understand by highlighting important points and decisions made in the meeting. Highlighting important points and decisions includes, but is not limited to, changing the color or font size. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on important points and decisions made in the meeting into a generation AI model and have the generation AI model execute the highlighting method.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The collection unit collects audio data from the meeting. The collection unit can collect detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their speech. For example, the collection unit can collect the content of what was said during the meeting using a high-precision microphone. The collection unit can also use speech analysis technology to analyze the tone of the speaker's voice and the speed of their speech. For example, the collection unit can analyze changes in the tone of the speaker's voice in real time and detect changes in emotion. Step 2: The emotion analysis unit analyzes the audio data collected by the collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. The emotion analysis unit can determine emotions from, for example, the tone and speed of the speaker's voice and the choice of words. For example, if the speaker's voice tone is high, the emotion analysis unit will determine that the emotion is joy. The emotion analysis unit can also determine that if the speaker's voice speed is fast, the emotion is excitement. Furthermore, the emotion analysis unit can also determine emotions from the speaker's choice of words. For example, the emotion analysis unit will determine that the emotion of a speaker who uses many positive words is joy. Step 3: The minutes generation unit generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The minutes generation unit can, for example, draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, the minutes generation unit will draw a character with a happy expression. If a speaker is surprised, the minutes generation unit can also draw a character with a surprised expression. Furthermore, if a speaker is sad, the minutes generation unit can also draw a character with a sad expression. In this way, the system can visually represent the tone of the conversation and the emotions of the participants. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can generate meeting minutes using a generation AI model that takes emotion data determined by the emotion analysis unit as input and outputs meeting minutes in manga format.

[0058] (Example of form 2) The system according to an embodiment of the present invention is a system that automatically generates manga-style meeting minutes that visualize the emotions of meeting participants using a generation AI. This system collects audio data from meetings, and the generation AI analyzes this audio data to automatically create meeting minutes. In this process, the generation AI analyzes not only the content of the conversation but also the tone of the conversation and the emotions of the participants. Next, the generation AI generates meeting minutes in manga format based on the emotion data it has analyzed. These manga-style meeting minutes visually represent not only the content of the conversation but also the emotions of the participants and the tone of the conversation. This mechanism makes the meeting minutes extremely easy to understand and visualizes the tone of the conversation and the emotions of the participants. As a result, the content of the meeting can be grasped more accurately, and all participants can have the same understanding. In addition, since the creation of meeting minutes is automated, time is saved and meeting records can be kept efficiently. For example, audio data from meetings is collected. In this process, detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their speech are collected. For example, if a speaker says, "I think this proposal is wonderful," the tone of their voice and the speed of their speech are collected along with the content of that statement. Next, the generating AI analyzes the collected audio data. The generating AI determines emotions not only from the content of what is said, but also from the tone and speed of the speaker's voice and word choice. For example, if the speaker is happy, the generating AI will determine that emotion as "joy." Furthermore, based on the emotion data analyzed by the generating AI, it generates meeting minutes in a manga format. The generating AI draws a character that visually represents the speaker's emotions along with the content of what was said. For example, if the speaker says, "I think this proposal is wonderful," and the generating AI determines that emotion as "joy," a character with a joyful expression will be drawn and displayed along with the content of what was said. This system makes meeting minutes extremely easy to understand, and the tone of the conversation and the emotions of the participants are made visible. As a result, the content of the meeting can be grasped more accurately, and all participants can share the same understanding. In addition, since the creation of meeting minutes is automated, time is saved, and meeting records can be kept efficiently.

[0059] The system according to this embodiment comprises a data collection unit, an emotion analysis unit, and a meeting minutes generation unit. The data collection unit collects audio data of the meeting. The data collection unit can collect detailed data such as the content of what is said during the meeting, the tone of the speaker's voice, and the speed of their speech. For example, the data collection unit collects the content of what is said during the meeting using a high-precision microphone. The data collection unit can also use speech analysis technology to analyze the tone of the speaker's voice and the speed of their speech. For example, the data collection unit can analyze changes in the tone of the speaker's voice in real time and detect changes in emotion. The emotion analysis unit analyzes the audio data collected by the data collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. For example, the emotion analysis unit can determine emotions from the tone of the speaker's voice, the speed of their speech, and their choice of words. For example, the emotion analysis unit can determine that the speaker's voice tone is high, indicating an emotion of joy. The emotion analysis unit can also determine that the speaker's voice speed is fast, indicating an emotion of excitement. Furthermore, the emotion analysis unit can also determine emotions from the speaker's choice of words. For example, the emotion analysis unit determines that a speaker who uses many positive words is feeling joyful. The minutes generation unit generates minutes in manga format based on the emotion data determined by the emotion analysis unit. The minutes generation unit can, for example, draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, the minutes generation unit draws a character with a joyful expression. It can also draw a character with a surprised expression if the speaker is surprised. Furthermore, it can draw a character with a sad expression if the speaker is sad. This allows the system to visually represent the tone of the conversation and the emotions of the participants. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can generate minutes using a generation AI model that takes emotion data determined by the emotion analysis unit as input and outputs minutes in manga format. This allows the system to visually represent the tone of the conversation and the emotions of the participants.

[0060] The data collection unit collects audio data from meetings. The unit can collect detailed data, such as the content of speech during meetings, the tone of the speaker's voice, and their speaking speed. Specifically, the unit uses high-precision microphones to clearly capture the content of speech during meetings. This allows for accurate capture of even the subtle nuances and intonation of the speaker's voice. Furthermore, the unit uses speech analysis technology to analyze the tone and speed of the speaker's voice in real time. For example, speech analysis technology can analyze the frequency components of the speaker's voice and detect changes in tone. Additionally, to analyze the speed of the speaker's voice, the unit measures the temporal fluctuations of the audio data to understand the speed and rhythm of speech. This enables the data collection unit to detect changes in the speaker's emotions and level of tension in real time. The data collection unit has an interface for centrally managing this data and providing it to the emotion analysis unit and the meeting minutes generation unit. For example, the collected audio data is stored on a cloud server and can be linked with other systems and departments as needed. The data collection unit can also adjust the frequency and accuracy of data collection, allowing for flexible responses to specific situations and conditions. This allows the data collection unit to collect data efficiently and effectively, improving the overall performance of the system.

[0061] The emotion analysis unit analyzes the audio data collected by the collection unit to determine the tone of the conversation and the emotions of the participants, along with the content of the conversation. Specifically, the emotion analysis unit can determine emotions from the tone and speed of the speaker's voice and word choice. For example, a high tone of voice indicates joy, and a fast speaking speed indicates excitement. The emotion analysis unit analyzes the frequency components and temporal fluctuations of the audio data to detect changes in the speaker's emotions in real time. Furthermore, the emotion analysis unit can also determine emotions from the speaker's word choice. For example, a speaker who uses many positive words can be judged as happy, and a speaker who uses many negative words can be judged as sad. Based on these analysis results, the emotion analysis unit generates data to visually represent the tone of the conversation and the emotions of the participants. The emotion analysis unit can improve the accuracy of audio data analysis using AI technology. For example, it can train a speech recognition model using deep learning to determine the speaker's emotions with high accuracy. This allows the sentiment analysis unit to quickly and accurately analyze collected audio data, enabling it to grasp the tone of the conversation and the emotions of the participants in real time. Furthermore, the sentiment analysis unit can also utilize historical data and statistical information to analyze long-term emotional trends and patterns. As a result, the sentiment analysis unit can handle not only real-time sentiment analysis but also long-term emotional fluctuations and trend analysis, improving the reliability and accuracy of the entire system.

[0062] The meeting minutes generation unit generates meeting minutes in manga format based on emotional data determined by the emotion analysis unit. Specifically, the meeting minutes generation unit can draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, it can draw a character with a happy expression; if a speaker is surprised, it can draw a character with a surprised expression. The meeting minutes generation unit can generate meeting minutes using a generation AI model that takes emotional data provided by the emotion analysis unit as input and outputs meeting minutes in manga format. The generation AI model automatically generates appropriate characters and scenes based on the content of the statements and emotional data, creating visually easy-to-understand meeting minutes. For example, if a speaker is sad, it can draw a character with a sad expression and generate a scene corresponding to the content of the statement. Furthermore, the meeting minutes generation unit provides an interface for editing the generated manga-style meeting minutes, allowing users to make corrections and additions as needed. This enables the meeting minutes generation unit to visually represent the tone of the conversation and the emotions of the participants, making the content of the meeting easier to understand. The meeting minutes generation unit, by utilizing generation AI, automates the meeting minutes generation process, enabling efficient and rapid creation of meeting minutes. This allows the system to visually represent the nuances of the conversation and the emotions of the participants, making the meeting content easier to understand. Furthermore, the meeting minutes generation unit can save the generated minutes to the cloud and share them with other systems and departments as needed. This allows the meeting minutes generation unit to generate minutes efficiently and effectively, improving the overall system performance.

[0063] The data collection unit can collect detailed data such as the content of speech during meetings, the tone of voice of the speakers, and their speaking speed. For example, the data collection unit can collect the content of speech during meetings using a high-precision microphone. The data collection unit can use speech analysis technology to analyze the tone of voice and speaking speed of the speakers. For example, the data collection unit can analyze changes in the tone of voice of the speakers in real time to detect changes in emotion. The data collection unit can also analyze the speed of the speakers' voices to grasp the tempo of their speech. For example, the data collection unit can determine that a fast speaking speed indicates excitement. Based on changes in the tone of voice and speaking speed of the speakers, the data collection unit can detect changes in emotion in real time. As a result, by collecting detailed data such as the content of speech during meetings, the tone of voice of the speakers, and their speaking speed, the data collection unit can perform more accurate emotion analysis. Detailed data includes, but is not limited to, the content of speech, tone of voice, speaking speed, and pauses. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their voice into an AI model, allowing the AI ​​model to perform data collection and analysis.

[0064] The emotion analysis unit can determine emotions from the speaker's tone of voice, speed, and word choice. For example, if the speaker's tone of voice is high, the emotion analysis unit will determine that the speaker is feeling joy. If the speaker's speed is fast, the emotion analysis unit can also determine that the speaker is feeling excitement. The emotion analysis unit can also determine emotions from the speaker's word choice. For example, if the emotion analysis unit uses many positive words, it will determine that the speaker is feeling joy. If the speaker uses many negative words, it will determine that the speaker is feeling sadness. The emotion analysis unit can determine emotions by comprehensively analyzing the speaker's tone of voice, speed, and word choice. This allows the emotion analysis unit to perform more accurate emotion analysis by determining emotions from the speaker's tone of voice, speed, and word choice. Word choice includes, but is not limited to, positive words, negative words, and the use of technical terms. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's tone of voice, speed, and word choice into an AI model, and have the AI ​​model perform an emotion determination.

[0065] The minutes generation unit can create a character that visually represents the speaker's emotions along with the content of their remarks. For example, if the speaker is happy, the minutes generation unit will create a character with a happy expression. If the speaker is surprised, the minutes generation unit can also create a character with a surprised expression. If the speaker is sad, the minutes generation unit can also create a character with a sad expression. The minutes generation unit can devise the character's facial expression and pose to visually represent the speaker's emotions. For example, if the speaker is happy, the minutes generation unit will create a smiling character. Also, if the speaker is surprised, the minutes generation unit can create a character with a surprised expression. Furthermore, if the speaker is sad, the minutes generation unit can create a character that is shedding tears. In this way, the minutes generation unit makes the minutes easier to understand by creating a character that visually represents the speaker's emotions along with the content of their remarks. Visual representations of characters include, but are not limited to, facial expressions, poses, and clothing to express emotions. Some or all of the above-described processes in the minutes generation unit may be performed using a generation AI, or they may not be performed using a generation AI. For example, the minutes generation unit can input the content of the speeches and emotional data into a generation AI model and have the generation AI model draw the characters.

[0066] The meeting minutes generation unit can generate meeting minutes in manga format based on emotional data analyzed by the generation AI. For example, the meeting minutes generation unit can draw characters that visually represent the speaker's emotions along with the content of their statements. If the speaker is happy, the meeting minutes generation unit will draw a character with a happy expression. If the speaker is surprised, the meeting minutes generation unit can also draw a character with a surprised expression. If the speaker is sad, the meeting minutes generation unit can also draw a character with a sad expression. The meeting minutes generation unit can devise the character's expression and pose to visually represent the speaker's emotions. For example, if the speaker is happy, the meeting minutes generation unit will draw a smiling character. Also, if the speaker is surprised, the meeting minutes generation unit can draw a character with a surprised expression. Furthermore, if the speaker is sad, the meeting minutes generation unit can draw a character shedding tears. This allows the minutes generation unit to visually represent the tone of the conversation and the emotions of the participants by generating minutes in manga format based on the emotion data analyzed by the generation AI. The generation AI includes, but is not limited to, deep learning, natural language processing, and image generation technologies. Some or all of the above-described processes in the minutes generation unit may be performed using the generation AI or not. For example, the minutes generation unit can input the content of the statements and emotion data into a generation AI model and have the generation AI model generate minutes in manga format.

[0067] The emotion analysis unit can determine that a speaker is happy if that emotion is "joyful." For example, the emotion analysis unit can determine joyfulness if the speaker's voice tone is high. The emotion analysis unit can also determine excitement if the speaker's voice speed is fast. The emotion analysis unit can also determine emotions from the speaker's word choices. For example, the emotion analysis unit will determine joyfulness if the speaker uses many positive words. The emotion analysis unit can also determine sadness if the speaker uses many negative words. The emotion analysis unit can determine emotions by comprehensively analyzing the speaker's voice tone, speed, and word choices. As a result, the emotion analysis unit can improve the accuracy of emotion analysis by determining that a speaker is happy if that emotion is "joyful." The criteria for determining joy include, but are not limited to, an increase in voice tone, laughter, and the use of positive words. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's tone of voice, speed, and word choice into an AI model, and have the AI ​​model perform an emotion determination.

[0068] The data collection unit can estimate the user's emotions and adjust the timing of audio data collection based on the estimated emotions. For example, if the user is excited, the frequency of speech increases, so the data collection unit can set the collection timing to be shorter. If the user is relaxed, the intervals between speeches increase, so the data collection unit can also set the collection timing to be longer. If the user is nervous, the data collection unit can set the collection timing more precisely, as there are more important speeches. In this way, the data collection unit can collect data at a more appropriate time by adjusting the timing of audio data collection based on the user's emotions. Examples of audio data collection timing include, but are not limited to, moments of significant emotional change or immediately after a specific speech. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​model adjust the timing of data collection.

[0069] The data collection unit can collect not only the content of what is said during a meeting, but also the speaker's gestures and facial expressions. For example, if a speaker raises their hand, the data collection unit can capture that gesture with a camera and collect it along with the audio data. If a speaker is smiling, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. If a speaker is frowning, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. This allows the data collection unit to use more detailed data for analysis by also collecting the speaker's gestures and facial expressions. The collection of gestures and facial expressions includes, but is not limited to, the use of a camera and image analysis techniques. Some or all of the processing described above in the data collection unit may or may not be performed using AI. For example, the data collection unit can input the speaker's gesture and facial expression data into an AI model and have the AI ​​model perform data collection and analysis.

[0070] The data collection unit can simultaneously collect background and ambient sounds from a meeting when collecting audio data, and use them for analysis. For example, the data collection unit can collect background sounds from a meeting room and analyze them separately from the speaker's voice. The data collection unit can also collect noise from outside a window and analyze it separately from the speaker's voice. The data collection unit can also collect keyboard typing sounds during a meeting and analyze them separately from the speaker's voice. This allows the data collection unit to perform more accurate analysis by simultaneously collecting background and ambient sounds from the meeting. Examples of background and ambient sound collection include, but are not limited to, noise cancellation and audio filtering technologies. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on background and ambient sounds from a meeting into an AI model and have the AI ​​model perform data collection and analysis.

[0071] The data collection unit can estimate the user's emotions and determine the priority of audio data to collect based on the estimated emotions. For example, if the user is excited, the data collection unit will prioritize collecting their statements. If the user is relaxed, the data collection unit may postpone collecting their statements. If the user is nervous, the data collection unit may also prioritize collecting their statements. In this way, the data collection unit can prioritize the collection of important data by prioritizing audio data based on the user's emotions. Prioritization of audio data includes, but is not limited to, the intensity of emotion and the importance of the statements. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​model perform the determination of audio data prioritization.

[0072] The data collection unit can filter audio data based on the job titles and areas of expertise of meeting participants. For example, the data collection unit may prioritize collecting statements from participants with higher job titles. It may also prioritize collecting statements from participants whose areas of expertise are relevant to the meeting agenda. The data collection unit may also postpone collecting statements from participants with lower job titles. In this way, the data collection unit can prioritize the collection of important data by filtering the data based on the job titles and areas of expertise of meeting participants. Data filtering may include, but is not limited to, the importance of job titles and the relevance of areas of expertise. Some or all of the processing described above in the data collection unit may be performed using AI or not. For example, the data collection unit may input data on the job titles and areas of expertise of meeting participants into an AI model and have the AI ​​model perform the data filtering.

[0073] The data collection unit can adjust the collection scope based on the meeting agenda and themes when collecting audio data. For example, the data collection unit can prioritize collecting statements related to the meeting agenda. The data collection unit can also postpone collecting statements unrelated to the meeting themes. The data collection unit can also collect statements related to the meeting agenda in detail. In this way, the data collection unit can collect highly relevant data by adjusting the collection scope based on the meeting agenda and themes. Adjustments to the collection scope include, but are not limited to, the importance of the agenda and the relevance of the themes. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input meeting agenda and theme data into an AI model and have the AI ​​model perform the adjustment of the collection scope.

[0074] The emotion analysis unit can estimate the user's emotions and adjust the emotion analysis algorithm based on the estimated user emotions. For example, if the user is excited, the emotion analysis unit can set the emotion analysis algorithm to be sensitive. If the user is relaxed, the emotion analysis unit can also set the emotion analysis algorithm to be less sensitive. If the user is tense, the emotion analysis unit can also set the emotion analysis algorithm to be finer. In this way, the emotion analysis unit improves the accuracy of the analysis by adjusting the emotion analysis algorithm based on the user's emotions. Adjustments to the emotion analysis algorithm include, but are not limited to, changing weights or adding features. Some or all of the above processes in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input user emotion data into an AI model and have the AI ​​model perform the algorithm adjustments.

[0075] The emotion analysis unit can analyze not only the tone and speed of the speaker's voice, but also their breathing pattern and heart rate. For example, if the speaker's breathing is rapid, the emotion analysis unit may analyze that the speaker is nervous. If the speaker's heart rate is high, the emotion analysis unit may analyze that the speaker is excited. If the speaker's breathing is slow, the emotion analysis unit may analyze that the speaker is relaxed. This allows the emotion analysis unit to perform a more detailed emotional analysis by also analyzing the speaker's breathing pattern and heart rate. The analysis of breathing patterns and heart rate may include, but is not limited to, the use of sensors or biosignal analysis techniques. Some or all of the processing described above in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input data on the speaker's breathing pattern and heart rate into an AI model and have the AI ​​model perform the data analysis.

[0076] The emotion analysis unit can determine changes in emotion by referring to the speaker's past statement history during emotion analysis. For example, if the speaker was happy in the past, the emotion analysis unit can determine changes in emotion by comparing it to the current statement. If the speaker was angry in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. If the speaker was sad in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. In this way, the emotion analysis unit can accurately determine changes in emotion by referring to the speaker's past statement history. Referencing the statement history includes, but is not limited to, past meeting records, frequency and content of statements. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's past statement history into an AI model and have the AI ​​model perform the determination of changes in emotion.

[0077] The emotion analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is excited, the emotion analysis unit can highlight the analysis results. If the user is relaxed, the emotion analysis unit can also display the analysis results calmly. If the user is tense, the emotion analysis unit can also display the analysis results in detail. This allows the emotion analysis unit to provide a more appropriate display by adjusting how the analysis results are displayed based on the user's emotions. Adjustments to the display method of the analysis results include, but are not limited to, graph displays, text displays, and animation displays. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the user's emotion data into an AI model and have the AI ​​model perform the adjustment of the display method.

[0078] The sentiment analysis unit can perform sentiment analysis while considering the progress of the meeting and the progress of the agenda. For example, if the meeting is progressing quickly, the sentiment analysis unit can perform sentiment analysis quickly. If the meeting is progressing slowly, the sentiment analysis unit can also perform sentiment analysis in detail. The sentiment analysis unit can also adjust the accuracy of sentiment analysis according to the progress of the agenda. This allows the sentiment analysis unit to perform more accurate sentiment analysis by considering the progress of the meeting and the progress of the agenda. Consideration of the progress of the meeting and the progress of the agenda includes, but is not limited to, the stage of the agenda and the order of speeches. Some or all of the above processing in the sentiment analysis unit may be performed using AI or not. For example, the sentiment analysis unit can input data on the progress of the meeting and the progress of the agenda into an AI model and have the AI ​​model perform the adjustment of the analysis.

[0079] The sentiment analysis unit can improve the accuracy of its analysis by considering the speaker's cultural background and linguistic characteristics during sentiment analysis. For example, the sentiment analysis unit adjusts the sentiment analysis algorithm by considering the speaker's cultural background. The sentiment analysis unit can also adjust the sentiment analysis algorithm by considering the speaker's linguistic characteristics. The sentiment analysis unit can also improve the accuracy of sentiment analysis based on the speaker's cultural background and linguistic characteristics. As a result, the sentiment analysis unit improves its analysis accuracy by considering the speaker's cultural background and linguistic characteristics. Consideration of cultural background and linguistic characteristics includes, but is not limited to, culture-specific expressions and linguistic nuances. Some or all of the above processing in the sentiment analysis unit may be performed using AI or not. For example, the sentiment analysis unit can input data on the speaker's cultural background and linguistic characteristics into an AI model and have the AI ​​model perform the adjustment of the analysis.

[0080] The minutes generation unit can estimate the user's emotions and adjust the way the manga-style minutes are presented based on the estimated emotions. For example, if the user is excited, the minutes generation unit will emphasize the characters' facial expressions. If the user is relaxed, the minutes generation unit may also depict the characters' facial expressions more gently. If the user is tense, the minutes generation unit may also depict the characters' facial expressions in more detail. In this way, the minutes generation unit can produce more appropriate minutes by adjusting the way the manga-style minutes are presented based on the user's emotions. Adjustments to the presentation of the manga-style minutes include, but are not limited to, changes to character facial expressions and panel layouts. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is 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 processing in the minutes generation unit may be performed using a generative AI or not. For example, the meeting minutes generation unit can input user emotion data into a generation AI model and have the generation AI model adjust the expression method.

[0081] The minutes generation unit can highlight important points and decisions made during the generation of meeting minutes. For example, the minutes generation unit can display important points in bold. The minutes generation unit can also display decisions made in color. The minutes generation unit can also display important points and decisions made in the meeting using icons. This makes the minutes easier to understand by highlighting important points and decisions made in the meeting. Highlighting important points and decisions includes, but is not limited to, changing the color or font size. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on important points and decisions made in the meeting into a generation AI model and have the generation AI model execute the highlighting method.

[0082] The minutes generation unit can update the minutes in real time according to the progress of the meeting when generating the minutes. For example, the minutes generation unit updates the minutes in real time in accordance with the progress of the meeting. The minutes generation unit can also update the minutes in real time if the meeting is progressing quickly. The minutes generation unit can also update the minutes in real time if the meeting is progressing slowly. As a result, the minutes generation unit updates the minutes in real time according to the progress of the meeting, so that the latest information is immediately reflected. Methods for updating the minutes in real time include, but are not limited to, automatic update timing and update triggers. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can input data on the progress of the meeting into a generation AI model and have the generation AI model execute the real-time update method.

[0083] The minutes generation unit can estimate the user's emotions and adjust the length and level of detail of the minutes based on the estimated emotions. For example, if the user is excited, the minutes generation unit may shorten the length and make the content concise. If the user is relaxed, the minutes generation unit may lengthen the length and make the content more detailed. If the user is tense, the minutes generation unit may adjust the length and make the content more detailed. In this way, the minutes generation unit can generate more appropriate minutes by adjusting the length and level of detail of the minutes based on the user's emotions. Adjustments to the length and level of detail of the minutes include, but are not limited to, adjusting the level of summary or adding detailed explanations. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the minutes generation unit may be performed using or without a generative AI. For example, the meeting minutes generation unit can input user sentiment data into a generation AI model and have the generation AI model perform adjustments to the length and level of detail.

[0084] The minutes generation unit can customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. For example, the minutes generation unit can generate concise minutes for participants with higher job titles. It can also generate detailed minutes for participants whose areas of expertise are relevant to the meeting agenda. It can also generate brief minutes for participants with lower job titles. In this way, the minutes generation unit generates optimal minutes for each participant by customizing the content based on the job titles and areas of expertise of the meeting participants. Customization of the content of the minutes includes, but is not limited to, key points for each job title and detailed explanations for each area of ​​expertise. Some or all of the above processing in the minutes generation unit may be performed using or without a generation AI. For example, the minutes generation unit can input data on the job titles and areas of expertise of the meeting participants into a generation AI model and have the generation AI model perform the content customization.

[0085] The minutes generation unit can adjust the structure of the minutes based on the meeting agenda and themes when generating them. For example, the minutes generation unit can prioritize including content related to the meeting agenda in the minutes. The minutes generation unit can also postpone including content unrelated to the meeting themes. The minutes generation unit can also include detailed content related to the meeting agenda in the minutes. In this way, the minutes generation unit generates highly relevant minutes by adjusting the structure of the minutes based on the meeting agenda and themes. Adjustments to the structure of the minutes include, but are not limited to, dividing the minutes into sections by agenda item and summarizing by theme. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on the meeting agenda and themes into a generation AI model and have the generation AI model perform the adjustment of the structure.

[0086] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0087] The data collection unit can collect not only the content of what is said during a meeting, but also the speaker's gestures and facial expressions. For example, if a speaker raises their hand, the data collection unit can capture that gesture with a camera and collect it along with the audio data. If a speaker is smiling, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. If a speaker is frowning, the data collection unit can also capture that facial expression with a camera and collect it along with the audio data. This allows the data collection unit to use more detailed data for analysis by also collecting the speaker's gestures and facial expressions. The collection of gestures and facial expressions includes, but is not limited to, the use of a camera and image analysis techniques. Some or all of the processing described above in the data collection unit may or may not be performed using AI. For example, the data collection unit can input the speaker's gesture and facial expression data into an AI model and have the AI ​​model perform data collection and analysis.

[0088] The emotion analysis unit can analyze not only the tone and speed of the speaker's voice, but also their breathing pattern and heart rate. For example, if the speaker's breathing is rapid, the emotion analysis unit may analyze that the speaker is nervous. If the speaker's heart rate is high, the emotion analysis unit may analyze that the speaker is excited. If the speaker's breathing is slow, the emotion analysis unit may analyze that the speaker is relaxed. This allows the emotion analysis unit to perform a more detailed emotional analysis by also analyzing the speaker's breathing pattern and heart rate. The analysis of breathing patterns and heart rate may include, but is not limited to, the use of sensors or biosignal analysis techniques. Some or all of the processing described above in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input data on the speaker's breathing pattern and heart rate into an AI model and have the AI ​​model perform the data analysis.

[0089] The data collection unit can simultaneously collect background and ambient sounds from a meeting when collecting audio data, and use them for analysis. For example, the data collection unit can collect background sounds from a meeting room and analyze them separately from the speaker's voice. The data collection unit can also collect noise from outside a window and analyze it separately from the speaker's voice. The data collection unit can also collect keyboard typing sounds during a meeting and analyze them separately from the speaker's voice. This allows the data collection unit to perform more accurate analysis by simultaneously collecting background and ambient sounds from the meeting. Examples of background and ambient sound collection include, but are not limited to, noise cancellation and audio filtering technologies. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input data on background and ambient sounds from a meeting into an AI model and have the AI ​​model perform data collection and analysis.

[0090] The emotion analysis unit can determine changes in emotion by referring to the speaker's past statement history during emotion analysis. For example, if the speaker was happy in the past, the emotion analysis unit can determine changes in emotion by comparing it to the current statement. If the speaker was angry in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. If the speaker was sad in the past, the emotion analysis unit can also determine changes in emotion by comparing it to the current statement. In this way, the emotion analysis unit can accurately determine changes in emotion by referring to the speaker's past statement history. Referencing the statement history includes, but is not limited to, past meeting records, frequency and content of statements. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the speaker's past statement history into an AI model and have the AI ​​model perform the determination of changes in emotion.

[0091] The minutes generation unit can highlight important points and decisions made during the generation of meeting minutes. For example, the minutes generation unit can display important points in bold. The minutes generation unit can also display decisions made in color. The minutes generation unit can also display important points and decisions made in the meeting using icons. This makes the minutes easier to understand by highlighting important points and decisions made in the meeting. Highlighting important points and decisions includes, but is not limited to, changing the color or font size. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or not. For example, the minutes generation unit can input data on important points and decisions made in the meeting into a generation AI model and have the generation AI model execute the highlighting method.

[0092] The data collection unit can estimate the user's emotions and adjust the timing of audio data collection based on the estimated emotions. For example, if the user is excited, the frequency of speech increases, so the data collection unit can set the collection timing to be shorter. If the user is relaxed, the intervals between speeches increase, so the data collection unit can also set the collection timing to be longer. If the user is nervous, the data collection unit can set the collection timing more precisely, as there are more important speeches. In this way, the data collection unit can collect data at a more appropriate time by adjusting the timing of audio data collection based on the user's emotions. Examples of audio data collection timing include, but are not limited to, moments of significant emotional change or immediately after a specific speech. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​model adjust the timing of data collection.

[0093] The emotion analysis unit can estimate the user's emotions and adjust the emotion analysis algorithm based on the estimated user emotions. For example, if the user is excited, the emotion analysis unit can set the emotion analysis algorithm to be sensitive. If the user is relaxed, the emotion analysis unit can also set the emotion analysis algorithm to be less sensitive. If the user is tense, the emotion analysis unit can also set the emotion analysis algorithm to be finer. In this way, the emotion analysis unit improves the accuracy of the analysis by adjusting the emotion analysis algorithm based on the user's emotions. Adjustments to the emotion analysis algorithm include, but are not limited to, changing weights or adding features. Some or all of the above processes in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input user emotion data into an AI model and have the AI ​​model perform the algorithm adjustments.

[0094] The minutes generation unit can estimate the user's emotions and adjust the way the manga-style minutes are presented based on the estimated emotions. For example, if the user is excited, the minutes generation unit will emphasize the characters' facial expressions. If the user is relaxed, the minutes generation unit may also depict the characters' facial expressions more gently. If the user is tense, the minutes generation unit may also depict the characters' facial expressions in more detail. In this way, the minutes generation unit can produce more appropriate minutes by adjusting the way the manga-style minutes are presented based on the user's emotions. Adjustments to the presentation of the manga-style minutes include, but are not limited to, changes to character facial expressions and panel layouts. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is 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 processing in the minutes generation unit may be performed using a generative AI or not. For example, the meeting minutes generation unit can input user emotion data into a generation AI model and have the generation AI model adjust the expression method.

[0095] The data collection unit can estimate the user's emotions and determine the priority of audio data to collect based on the estimated emotions. For example, if the user is excited, the data collection unit will prioritize collecting their statements. If the user is relaxed, the data collection unit may postpone collecting their statements. If the user is nervous, the data collection unit may also prioritize collecting their statements. In this way, the data collection unit can prioritize the collection of important data by prioritizing audio data based on the user's emotions. Prioritization of audio data includes, but is not limited to, the intensity of emotion and the importance of the statements. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into an AI model and have the AI ​​model perform the determination of audio data prioritization.

[0096] The emotion analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is excited, the emotion analysis unit can highlight the analysis results. If the user is relaxed, the emotion analysis unit can also display the analysis results calmly. If the user is tense, the emotion analysis unit can also display the analysis results in detail. This allows the emotion analysis unit to provide a more appropriate display by adjusting how the analysis results are displayed based on the user's emotions. Adjustments to the display method of the analysis results include, but are not limited to, graph displays, text displays, and animation displays. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the emotion analysis unit may be performed using AI or not. For example, the emotion analysis unit can input the user's emotion data into an AI model and have the AI ​​model perform the adjustment of the display method.

[0097] The following briefly describes the processing flow for example form 2.

[0098] Step 1: The collection unit collects audio data from the meeting. The collection unit can collect detailed data such as the content of what was said during the meeting, the tone of the speaker's voice, and the speed of their speech. For example, the collection unit can collect the content of what was said during the meeting using a high-precision microphone. The collection unit can also use speech analysis technology to analyze the tone of the speaker's voice and the speed of their speech. For example, the collection unit can analyze changes in the tone of the speaker's voice in real time and detect changes in emotion. Step 2: The emotion analysis unit analyzes the audio data collected by the collection unit and determines the tone of the conversation and the emotions of the participants, along with the content of the conversation. The emotion analysis unit can determine emotions from, for example, the tone and speed of the speaker's voice and the choice of words. For example, if the speaker's voice tone is high, the emotion analysis unit will determine that the emotion is joy. The emotion analysis unit can also determine that if the speaker's voice speed is fast, the emotion is excitement. Furthermore, the emotion analysis unit can also determine emotions from the speaker's choice of words. For example, the emotion analysis unit will determine that the emotion of a speaker who uses many positive words is joy. Step 3: The minutes generation unit generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The minutes generation unit can, for example, draw characters that visually represent the speaker's emotions along with the content of their statements. For example, if a speaker is happy, the minutes generation unit will draw a character with a happy expression. If a speaker is surprised, the minutes generation unit can also draw a character with a surprised expression. Furthermore, if a speaker is sad, the minutes generation unit can also draw a character with a sad expression. In this way, the system can visually represent the tone of the conversation and the emotions of the participants. Some or all of the above processing in the minutes generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the minutes generation unit can generate meeting minutes using a generation AI model that takes emotion data determined by the emotion analysis unit as input and outputs meeting minutes in manga format.

[0099] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0100] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0101] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] Each of the multiple elements described above, including the data collection unit, emotion analysis unit, and meeting minutes generation unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data collection unit collects audio data of the meeting using the microphone 38B of the smart device 14, and the control unit 46A collects detailed data such as the content of speech, tone of voice, and speed. The emotion analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, and analyzes the collected audio data to determine the tone of the conversation and the emotions of the participants. The meeting minutes generation unit is implemented in the specific processing unit 290 of the data processing unit 12, and generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The meeting minutes generation unit may be implemented in the control unit 46A of the smart device 14, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0103] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0104] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0105] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0106] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0107] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0109] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0110] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0111] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0112] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0113] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0114] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0115] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0116] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0117] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0118] Each of the multiple elements described above, including the data collection unit, emotion analysis unit, and meeting minutes generation unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data collection unit collects audio data of the meeting using the microphone 238 of the smart glasses 214, and the control unit 46A collects detailed data such as the content of speech, tone of voice, and speed. The emotion analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, and analyzes the collected audio data to determine the tone of the conversation and the emotions of the participants. The meeting minutes generation unit is implemented in the specific processing unit 290 of the data processing unit 12, and generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The meeting minutes generation unit may be implemented in the control unit 46A of the smart glasses 214, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0119] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0120] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0121] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0122] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0123] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0124] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0125] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0126] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0127] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0128] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0129] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0130] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0131] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0132] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0133] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0134] Each of the multiple elements described above, including the data collection unit, emotion analysis unit, and meeting minutes generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data collection unit collects audio data of the meeting using the microphone 238 of the headset terminal 314, and the control unit 46A collects detailed data such as the content of speech, tone of voice, and speed. The emotion analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, and analyzes the collected audio data to determine the tone of the conversation and the emotions of the participants. The meeting minutes generation unit is implemented in the specific processing unit 290 of the data processing unit 12, and generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The meeting minutes generation unit may also be implemented in the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0135] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0136] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0138] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0139] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0141] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0142] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0143] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0144] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0145] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0146] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0148] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0149] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0150] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the data collection unit, emotion analysis unit, and meeting minutes generation unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the data collection unit uses the microphone 238 of the robot 414 to collect audio data of the meeting, and the control unit 46A collects detailed data such as the content of speech, tone of voice, and speed. The emotion analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, and analyzes the collected audio data to determine the tone of the conversation and the emotions of the participants. The meeting minutes generation unit is implemented in the specific processing unit 290 of the data processing unit 12, and generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. The meeting minutes generation unit may be implemented in the control unit 46A of the robot 414, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0152] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0154] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0155] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0156] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0160] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0161] 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.

[0162] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0163] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0164] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0165] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0167] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0168] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0169] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0170] (Note 1) The collection unit collects audio data from meetings, The collection unit analyzes the audio data collected by the collection unit and determines the content of the conversation, as well as the tone of the conversation and the emotions of the participants. The system includes a meeting minutes generation unit that generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect detailed data such as the content of what is said during the meeting, the tone of voice of the speaker, and the speed of their speech. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned emotion analysis unit, Emotions can be determined from the speaker's tone of voice, speaking speed, and word choice. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned minutes generation unit, Along with the content of the statement, a character is created that visually represents the speaker's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned minutes generation unit, Based on emotional data analyzed by the generation AI, a manga-style meeting minutes document is created. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned emotion analysis unit, If the speaker is happy, that emotion will be judged as "joy." The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of audio data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is In addition to the content of what is said during the meeting, the speaker's gestures and facial expressions are also collected. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting audio data, background noise and ambient sounds from the meeting are also collected and used for analysis. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates the user's emotions and determines the priority of audio data to collect based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When collecting audio data, the data is filtered based on the job title and area of ​​expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When collecting audio data, adjust the collection scope based on the meeting agenda and theme. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned emotion analysis unit, The system estimates the user's emotions and adjusts the emotion analysis algorithm based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned emotion analysis unit, In addition to the speaker's tone and speed of voice, the system also analyzes the speaker's breathing pattern and heart rate. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned emotion analysis unit, During sentiment analysis, changes in emotion are determined by referring to the speaker's past statement history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned emotion analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned emotion analysis unit, When performing sentiment analysis, the analysis takes into account the progress of the meeting and the status of the agenda items. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned emotion analysis unit, When analyzing emotions, we improve the accuracy of the analysis by considering the speaker's cultural background and linguistic characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned minutes generation unit, The system estimates the user's emotions and adjusts the presentation of the manga-style meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned minutes generation unit, When generating meeting minutes, highlight important points and decisions made during the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned minutes generation unit, When generating meeting minutes, the minutes are updated in real time according to the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned minutes generation unit, It estimates the user's emotions and adjusts the length and level of detail of the meeting minutes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned minutes generation unit, When generating meeting minutes, customize the content of the minutes based on the roles and areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned minutes generation unit, When generating meeting minutes, adjust the structure of the minutes based on the meeting agenda and themes. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection unit collects audio data from meetings, The collection unit analyzes the audio data collected by the collection unit and determines the content of the conversation, as well as the tone of the conversation and the emotions of the participants. The system includes a meeting minutes generation unit that generates meeting minutes in manga format based on the emotion data determined by the emotion analysis unit. A system characterized by the following features.

2. The aforementioned collection unit is Collect detailed data such as the content of what is said during the meeting, the tone of voice of the speaker, and the speed of their speech. The system according to feature 1.

3. The aforementioned emotion analysis unit, Emotions can be determined from the speaker's tone of voice, speaking speed, and word choice. The system according to feature 1.

4. The aforementioned minutes generation unit, Along with the content of the statement, a character is created that visually represents the speaker's emotions. The system according to feature 1.

5. The aforementioned minutes generation unit, Based on emotional data analyzed by the generation AI, a manga-style meeting minutes document is created. The system according to feature 1.

6. The aforementioned emotion analysis unit, If the speaker is happy, that emotion will be judged as happiness. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the user's emotions and adjusts the timing of audio data collection based on the estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is In addition to the content of what is said during the meeting, the speaker's gestures and facial expressions are also collected. The system according to feature 1.

9. The aforementioned collection unit is When collecting audio data, background noise and ambient sounds from the meeting are also collected and used for analysis. The system according to feature 1.

10. The aforementioned collection unit is It estimates the user's emotions and determines the priority of audio data to collect based on the estimated user emotions. The system according to feature 1.

Images