System

Abstract

An object of a system according to an embodiment is to accurately and quickly summarize contents of a meeting and automatically create minutes.SOLUTION: A system includes a speech recognition part, an analysis part, a summarization part, and a minutes creation part. The speech recognizer receives speech data of the meeting as input and converts the speech data into text using speech recognition techniques. The analysis unit analyzes the text data converted by the voice recognition unit in real time and extracts an important point. The summarization unit summarizes the important points extracted by the analysis unit. The minutes creating section automatically creates minutes based on the information summarized by the summarizing section.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional techniques have had the problem of making it difficult to accurately and quickly summarize the contents of a meeting and create minutes.

[0005] The system according to the embodiment aims to accurately and quickly summarize the contents of a meeting and automatically create minutes. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, an analysis unit, a summarization unit, and a minutes creation unit. The speech recognition unit receives audio data of a meeting as input and converts it into text using speech recognition technology. The analysis unit analyzes the text data converted by the speech recognition unit in real time and extracts important points. The summarization unit summarizes the important points extracted by the analysis unit. The minutes creation unit automatically creates minutes based on the information summarized by the summarization unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately and quickly summarize the contents of a meeting and automatically create minutes. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The minutes-taking system according to an embodiment of the present invention is a system that automatically summarizes the contents of a meeting and takes minutes of the meeting, thereby efficiently recording the contents of the meeting and making them useful for later reference.

[0029] A minutes-taking system according to an embodiment includes a speech recognition unit, an analysis unit, a summarization unit, and a minutes-taking unit. The speech recognition unit receives audio data of a meeting as input and converts it into text using speech recognition technology. For example, the speech recognition unit receives audio data in MP3 format and converts it into text using deep learning-based speech recognition technology. The speech recognition unit can also receive audio data in WAV format and convert it into text using a hidden Markov model (HMM). The speech recognition unit can also receive real-time streaming audio data and convert it into text in real time. The analysis unit analyzes the text data converted by the speech recognition unit in real time and extracts important points. For example, the analysis unit analyzes the frequency of keywords in the text data and extracts important points. The analysis unit can also analyze the importance of the context of the text data and extract important points. The analysis unit can also refer to related background information or a topic model to understand the context of the text data. The summarization unit summarizes the important points extracted by the analysis unit. For example, the summarization unit concisely summarizes the important points of the text data. The summarization unit can also adjust the length of sentences based on important points in the text data when summarizing. The summarization unit can also evaluate the importance of the information to be summarized based on important points in the text data when summarizing. The minutes-taking unit automatically creates minutes based on the information summarized by the summarization unit. For example, the minutes-taking unit creates minutes in a format that includes the start time of the meeting, participants, agenda, content of discussions, decisions made, and next action items. The minutes-taking unit can also organize the summarized information and generate minutes in an easy-to-read format. The minutes-taking unit can also distribute the minutes to specified recipients. In this way, the minutes-taking system can efficiently record the contents of the meeting and make them useful for future reference.

[0030] The analysis unit can analyze video data in addition to audio data and convert the data into text based on the speaker's facial expressions and gestures. The analysis unit, for example, analyzes video data of a meeting in real time and reflects the speaker's facial expressions and gestures in the text. For example, if a speaker is smiling while speaking, that emotion is recorded in the text. The analysis unit also analyzes the speaker's movements from the video data and converts important gestures into text. For example, if there is a pointing motion, the direction of that motion is recorded in the text. The analysis unit also analyzes changes in the speaker's facial expression in real time and reflects the intensity of the emotion in the text. For example, if there is a surprised expression, that emotion is emphasized and recorded in the text. This enables more accurate text conversion by taking the speaker's facial expressions and gestures into account.

[0031] The analysis unit can incorporate technology that automatically removes background sounds or noise to more clearly analyze what is being said. For example, the analysis unit can filter background sounds and noise during a meeting in real time to clarify what is being said. For example, it can remove the sound of an air conditioner or other external noise. The analysis unit can also use noise-canceling technology to build a system that emphasizes only the speaker's voice. For example, it can use multiple microphones to cancel noise. The analysis unit can also incorporate an algorithm that automatically identifies and removes background sounds and noise when analyzing what is being said. For example, it can filter specific frequency bands. This can remove background sounds and noise, allowing for more clear analysis of what is being said.

[0032] The analysis unit can use a multilingual generation AI that can handle meetings in different languages. For example, the analysis unit uses a multilingual generation AI to analyze the content of meetings in different languages ​​in real time and convert it into text. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese. The analysis unit also automatically detects different languages ​​spoken during a meeting, and the generation AI performs analysis corresponding to that language. For example, it can handle cases where a speaker switches from English to Japanese. The analysis unit also uses multilingual speech recognition technology to convert utterances in different languages ​​into text in real time, which the generation AI then analyzes. For example, it can handle cases where multiple languages ​​are used during a meeting. This makes it possible to handle meetings in different languages.

[0033] The analysis unit develops a dashboard that visually displays the results of real-time analysis of the meeting, allowing participants to check the content in real time. For example, the analysis unit displays the results of real-time analysis of the meeting on the dashboard, allowing participants to visually check important points. For example, keywords and summaries are displayed in graphs and charts. The analysis unit also displays analysis results that are updated in real time on the dashboard, allowing participants to understand the progress of the meeting. For example, the name of the speaker and the content of the comments are displayed in real time. The analysis unit also displays the results of emotion analysis on the dashboard, allowing participants to visually check changes in the speaker's emotions. For example, emotion scores are displayed in different colors. This allows participants to check the content of the meeting in real time.

[0034] The summarization unit can dynamically reevaluate important points based on the frequency or importance of statements, thereby improving the accuracy of the summary. For example, the summarization unit builds a system that analyzes the frequency and importance of statements in real time and dynamically reevaluates important points. For example, it extracts frequently mentioned keywords as important points. The summarization unit also develops an algorithm that analyzes the importance of statements and dynamically reevaluates important points. For example, it evaluates importance based on the speaker's job title or expertise. The summarization unit also builds a system in which the generation AI analyzes the frequency and importance of statements and improves the accuracy of the summary. For example, it prioritizes including important statements in the summary. This makes it possible to dynamically reevaluate important points based on the frequency and importance of statements, thereby improving the accuracy of the summary.

[0035] The summarization unit can apply a different summarization algorithm to each meeting agenda item to generate a summary that is optimal for that agenda item. For example, the summarization unit builds a system that applies a different summarization algorithm to each meeting agenda item to generate an optimal summary. For example, a technical-specialized summarization algorithm is applied to technical agenda items. The summarization unit also applies a different summarization algorithm to each agenda item to improve the accuracy of the summarization. For example, a marketing-specialized summarization algorithm is applied to marketing agenda items. The summarization unit also develops a system that dynamically switches summarization algorithms depending on the meeting agenda item. For example, when the agenda item changes, the optimal summarization algorithm is automatically applied. This allows the accuracy of the summarization to be improved by generating an optimal summary for each agenda item.

[0036] The summarization unit can add a function to display the summarized content in different formats. For example, the summarization unit adds a function to display the summarized content in a visual note format. For example, important points are shown using diagrams or icons. The summarization unit also adds a function to display the summarized content in an infographic format. For example, data or statistical information is visually displayed. The summarization unit also builds a system to display the summarized content in different formats. For example, the summary is displayed in a format selected by the user. This makes it easier to understand visually by displaying the summarized content in different formats.

[0037] The summarization unit can have experts from different industries and fields review the summarized content and improve the accuracy of the summarization based on the feedback. For example, the summarization unit builds a system that has experts from different industries and fields review the summarized content and collects feedback. For example, technical experts and marketing experts are asked to review the summaries. The summarization unit also develops an algorithm that improves the accuracy of the summarization based on the experts' feedback. For example, the summarization unit modifies the summaries to reflect the experts' opinions. The summarization unit also builds a system that has experts from different industries and fields review the summaries and improves the accuracy of the summaries based on the feedback. For example, the summaries are improved based on the experts' evaluation scores. This makes it possible to improve the accuracy of the summaries based on the feedback from experts from different industries and fields.

[0038] The minutes-taking unit allows the format of minutes to be customized, and can automatically create minutes in a format that meets the user's needs. The minutes-taking unit, for example, allows the format of minutes to be customized, and builds a system that automatically creates minutes in a format selected by the user. For example, it allows the user to select a format such as a bulleted list format or a table format. The minutes-taking unit also adds a function to dynamically change the format of minutes to meet the user's needs. For example, it changes the format depending on the type of meeting and the purpose. The minutes-taking unit also provides a customizable minutes format, and builds a system that allows the user to freely set the format. For example, it adds a function to create and save templates. This makes it possible to automatically create minutes in a format that meets the user's needs.

[0039] The minutes-taking department will enable the generation AI to automatically add annotations and supplementary information to the contents of the minutes. For example, the minutes-taking department will build a system in which the generation AI automatically adds annotations to the contents of the minutes. For example, automatic explanations for technical terms and abbreviations will be added. The minutes-taking department will also introduce a function in which the generation AI adds supplementary information to the contents of the minutes. For example, automatic addition of links to related past meeting contents and reference materials. The minutes-taking department will also develop a system in which the generation AI analyzes the contents of the minutes and automatically adds necessary annotations and supplementary information. For example, adding background information on the discussion and related data. This will make it possible to automatically add annotations and supplementary information to the contents of the minutes, thereby helping to make the minutes easier to understand.

[0040] The minutes-taking department will automatically translate minutes into different languages, making it possible to handle international conferences. For example, the minutes-taking department will use generative AI to build a system that automatically translates minutes into different languages. For example, it will support multiple languages ​​such as English, Japanese, and Chinese. The minutes-taking department will also automatically translate the contents of minutes, making it possible to handle international conferences. For example, it will distribute automatically translated minutes after the conference ends. The minutes-taking department will also develop a system that translates minutes in real time using a multilingual translation algorithm. For example, it will translate what is said during the conference in real time and reflect this in the minutes. This will allow the minutes to be automatically translated into different languages, making it possible to handle international conferences.

[0041] The minutes-taking section can add a function to visualize minutes and display them in infographic or mind map format. For example, the minutes-taking section can add a function to display the contents of minutes in infographic format. For example, important points can be shown using diagrams or icons. The minutes-taking section can also add a function to display the contents of minutes in mind map format. For example, the minutes-taking section can visually organize agenda items and decisions. The minutes-taking section can also build a system to visualize minutes, allowing them to be displayed in a format selected by the user. For example, infographics or mind maps can be automatically generated. In this way, visualizing minutes can make them easier to understand visually.

[0042] The minutes-taking department can introduce a function that automatically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, the minutes-taking department can build a system that automatically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, the distribution destinations can be automatically set based on the list of meeting participants. The minutes-taking department can also develop an optimization algorithm for the distribution destinations and ensure that minutes are delivered to all parties involved. For example, email addresses and messenger app accounts can be automatically obtained. The minutes-taking department can also build a system that dynamically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, this can also handle cases where the participants in a meeting change. In this way, the distribution destinations of minutes can be automatically optimized, ensuring that they are delivered to all parties involved.

[0043] The minutes-taking department will build a system in which the generation AI automatically sets reminders when minutes are distributed, thereby promoting follow-up. For example, the generation AI will remind people of the next meeting or the deadline for an action item. The minutes-taking department will also add a reminder setting function to automatically promote follow-up when minutes are distributed. For example, regular reminders of the progress of action items. The minutes-taking department will also develop a system in which the generation AI will analyze the contents of the minutes and automatically set necessary reminders. For example, reminders of important decisions and deadlines for action items. This will promote follow-up by automatically setting reminders.

[0044] The minutes-taking department can automatically save minutes in cloud storage and distribute them by sharing a link. For example, the minutes-taking department will build a system that automatically saves minutes in cloud storage and distributes them by sharing a link. For example, it will automatically save them in Google Drive or Dropbox. The minutes-taking department will also add a function that automatically generates links to minutes saved in cloud storage and distributes them to relevant parties. For example, it will share the link via email or a messenger app. The minutes-taking department will also develop a system that automatically saves minutes in cloud storage and distributes them by sharing a link. For example, it will make it possible to access the minutes by simply clicking a link. This will make it easier to access the minutes by automatically saving them in cloud storage and distributing them by sharing a link.

[0045] The minutes-taking department will have the generation AI automatically create a summary when distributing minutes, allowing both a summary and a detailed version to be distributed. For example, the minutes-taking department will build a system in which the generation AI automatically generates a summary of minutes and distributes both a summary and a detailed version. For example, the summary version will be distributed by email and the detailed version will be shared via a link. The minutes-taking department will also add a function to automatically generate a summary of minutes and distribute both a summary and a detailed version. For example, the summary version will be distributed in short text format and the detailed version will be distributed in PDF format. The minutes-taking department will also develop a system in which the generation AI automatically generates a summary of minutes and distributes both a summary and a detailed version. For example, the summary version will be concise and the detailed version will include all the content of what was said. In this way, by distributing both the summary and the detailed version, recipients will be able to select and refer to the information they need.

[0046] The minutes-taking department will build a system in which the generation AI automatically suggests related past meeting contents when searching for meeting contents. For example, the minutes-taking department will suggest related minutes based on keywords or topics. The minutes-taking department will also add a function to automatically suggest past meeting contents, allowing users to easily access related information. For example, by displaying links to related meetings. The minutes-taking department will also develop a system in which the generation AI analyzes meeting contents and automatically suggests related past meeting contents. For example, by suggesting past meeting contents related to the same agenda or topic. This will allow users to quickly access the information they need by automatically suggesting related past meeting contents.

[0047] The minutes-taking unit can add a function that allows the search results of meeting contents to be filtered by speaker or agenda. For example, the minutes-taking unit adds a function that allows the search results of meeting contents to be filtered by speaker. For example, only the remarks of a specific speaker are displayed. The minutes-taking unit also adds a function that allows the search results to be filtered by agenda, allowing users to easily access the information they need. For example, only the remarks related to a specific agenda are displayed. The minutes-taking unit also builds a system that filters search results by speaker or agenda, allowing users to search for information efficiently. For example, it provides a filtering option. This allows users to quickly access the information they need by filtering the search results by speaker or agenda.

[0048] The minutes-taking unit can add a function to display search results for meeting content in different formats. For example, the minutes-taking unit adds a function to display search results for meeting content in visual note format. For example, important points are shown using diagrams or icons. The minutes-taking unit also adds a function to display search results for meeting content in infographic format. For example, data or statistical information is visually displayed. The minutes-taking unit also builds a system to display search results in different formats, allowing the user to display search results in a format selected by the user. For example, visual notes or infographics are automatically generated. In this way, displaying search results in different formats makes them easier to understand visually.

[0049] The minutes-taking department can have experts from different industries and fields review search results for meeting content and improve the search algorithm based on the feedback. For example, the minutes-taking department builds a system that has experts from different industries and fields review search results for meeting content and collects feedback. For example, it has technical experts and marketing experts review the search results. The minutes-taking department also develops a system that improves the search algorithm based on the experts' feedback. For example, it adjusts the search results by reflecting the experts' opinions. The minutes-taking department also builds a system that has experts from different industries and fields review the search results and improves the search algorithm based on that feedback. For example, it improves the search results based on the experts' evaluation scores. This makes it possible to improve the search algorithm based on the feedback from experts from different industries and fields.

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

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The speech recognition unit receives the conference audio data as input and converts it into text using speech recognition technology. For example, the speech recognition unit can receive MP3 format audio data and convert it into text using deep learning-based speech recognition technology. It can also receive WAV format audio data and convert it into text using an HMM (hidden Markov model). It can also receive real-time streaming audio data and convert it into text in real time. Step 2: The analysis unit analyzes the text data converted by the speech recognition unit in real time and extracts important points. For example, the analysis unit analyzes the frequency of keywords in the text data and extracts important points. It can also analyze the importance of the context of the text data and extract important points. It can also understand the context by referring to related background information and topic models and extract important points. Step 3: The summarization unit summarizes the key points extracted by the analysis unit. For example, the summarization unit briefly summarizes the key points of the text data. It can also adjust the length of the text based on the key points of the text data. It can also evaluate the importance of the information to be summarized. Step 4: The minutes-taking unit automatically creates minutes based on the information summarized by the summarizing unit. For example, the minutes-taking unit creates minutes in a format that includes the meeting start time, participants, agenda, discussion content, decisions, and next action items. It can also organize the summarized information and generate minutes in an easy-to-read format. It can also distribute the minutes to specified recipients.

[0053] (Example 2) The minutes-taking system according to an embodiment of the present invention is a system that automatically summarizes the contents of a meeting and takes minutes of the meeting, thereby efficiently recording the contents of the meeting and making them useful for later reference.

[0054] A minutes-taking system according to an embodiment includes a speech recognition unit, an analysis unit, a summarization unit, and a minutes-taking unit. The speech recognition unit receives audio data of a meeting as input and converts it into text using speech recognition technology. For example, the speech recognition unit receives audio data in MP3 format and converts it into text using deep learning-based speech recognition technology. The speech recognition unit can also receive audio data in WAV format and convert it into text using a hidden Markov model (HMM). The speech recognition unit can also receive real-time streaming audio data and convert it into text in real time. The analysis unit analyzes the text data converted by the speech recognition unit in real time and extracts important points. For example, the analysis unit analyzes the frequency of keywords in the text data and extracts important points. The analysis unit can also analyze the importance of the context of the text data and extract important points. The analysis unit can also refer to related background information or a topic model to understand the context of the text data. The summarization unit summarizes the important points extracted by the analysis unit. For example, the summarization unit concisely summarizes the important points of the text data. The summarization unit can also adjust the length of sentences based on important points in the text data when summarizing. The summarization unit can also evaluate the importance of the information to be summarized based on important points in the text data when summarizing. The minutes-taking unit automatically creates minutes based on the information summarized by the summarization unit. For example, the minutes-taking unit creates minutes in a format that includes the start time of the meeting, participants, agenda, content of discussions, decisions made, and next action items. The minutes-taking unit can also organize the summarized information and generate minutes in an easy-to-read format. The minutes-taking unit can also distribute the minutes to specified recipients. In this way, the minutes-taking system can efficiently record the contents of the meeting and make them useful for future reference.

[0055] The analysis unit analyzes the speaker's emotions in real time and can highlight important statements based on changes in emotion. For example, the analysis unit analyzes the speaker's tone of voice and language during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, that statement is emphasized as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI performs facial analysis to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes those movements to grasp changes in emotion. For example, if the speaker frequently waves their hands, that statement is emphasized as an important point. This makes it possible to clarify the important points of a meeting by highlighting important statements based on changes in emotion.

[0056] The analysis unit can analyze video data in addition to audio data and convert the data into text based on the speaker's facial expressions and gestures. The analysis unit, for example, analyzes video data of a meeting in real time and reflects the speaker's facial expressions and gestures in the text. For example, if a speaker is smiling while speaking, that emotion is recorded in the text. The analysis unit also analyzes the speaker's movements from the video data and converts important gestures into text. For example, if there is a pointing motion, the direction of that motion is recorded in the text. The analysis unit also analyzes changes in the speaker's facial expression in real time and reflects the intensity of the emotion in the text. For example, if there is a surprised expression, that emotion is emphasized and recorded in the text. This enables more accurate text conversion by taking the speaker's facial expressions and gestures into account.

[0057] The analysis unit can incorporate technology that automatically removes background sounds or noise to more clearly analyze what is being said. For example, the analysis unit can filter background sounds and noise during a meeting in real time to clarify what is being said. For example, it can remove the sound of an air conditioner or other external noise. The analysis unit can also use noise-canceling technology to build a system that emphasizes only the speaker's voice. For example, it can use multiple microphones to cancel noise. The analysis unit can also incorporate an algorithm that automatically identifies and removes background sounds and noise when analyzing what is being said. For example, it can filter specific frequency bands. This can remove background sounds and noise, allowing for more clear analysis of what is being said.

[0058] The analysis unit can use a multilingual generation AI that can handle meetings in different languages. For example, the analysis unit uses a multilingual generation AI to analyze the content of meetings in different languages ​​in real time and convert it into text. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese. The analysis unit also automatically detects different languages ​​spoken during a meeting, and the generation AI performs analysis corresponding to that language. For example, it can handle cases where a speaker switches from English to Japanese. The analysis unit also uses multilingual speech recognition technology to convert utterances in different languages ​​into text in real time, which the generation AI then analyzes. For example, it can handle cases where multiple languages ​​are used during a meeting. This makes it possible to handle meetings in different languages.

[0059] The analysis unit develops a dashboard that visually displays the results of real-time analysis of the meeting, allowing participants to check the content in real time. For example, the analysis unit displays the results of real-time analysis of the meeting on the dashboard, allowing participants to visually check important points. For example, keywords and summaries are displayed in graphs and charts. The analysis unit also displays analysis results that are updated in real time on the dashboard, allowing participants to understand the progress of the meeting. For example, the name of the speaker and the content of the comments are displayed in real time. The analysis unit also displays the results of emotion analysis on the dashboard, allowing participants to visually check changes in the speaker's emotions. For example, emotion scores are displayed in different colors. This allows participants to check the content of the meeting in real time.

[0060] The analysis unit uses an emotion estimation function to analyze the speaker's emotions in real time and can highlight important statements based on changes in emotion. For example, the analysis unit analyzes the speaker's tone of voice and language during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, that statement is emphasized as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI performs facial analysis to detect changes in emotion. For example, smiling and surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes those movements to grasp changes in emotion. For example, if the speaker frequently waves their hands, that statement is emphasized as an important point. This makes it possible to clarify the important points of a meeting by highlighting important statements based on changes in emotion.

[0061] The summarization unit can dynamically reevaluate important points based on the frequency or importance of statements, thereby improving the accuracy of the summary. For example, the summarization unit builds a system that analyzes the frequency and importance of statements in real time and dynamically reevaluates important points. For example, it extracts frequently mentioned keywords as important points. The summarization unit also develops an algorithm that analyzes the importance of statements and dynamically reevaluates important points. For example, it evaluates importance based on the speaker's job title or expertise. The summarization unit also builds a system in which the generation AI analyzes the frequency and importance of statements and improves the accuracy of the summary. For example, it prioritizes including important statements in the summary. This makes it possible to dynamically reevaluate important points based on the frequency and importance of statements, thereby improving the accuracy of the summary.

[0062] The summarization unit can apply a different summarization algorithm to each meeting agenda item to generate a summary that is optimal for that agenda item. For example, the summarization unit builds a system that applies a different summarization algorithm to each meeting agenda item to generate an optimal summary. For example, a technical-specialized summarization algorithm is applied to technical agenda items. The summarization unit also applies a different summarization algorithm to each agenda item to improve the accuracy of the summarization. For example, a marketing-specialized summarization algorithm is applied to marketing agenda items. The summarization unit also develops a system that dynamically switches summarization algorithms depending on the meeting agenda item. For example, when the agenda item changes, the optimal summarization algorithm is automatically applied. This allows the accuracy of the summarization to be improved by generating an optimal summary for each agenda item.

[0063] The summarization unit can analyze the speaker's emotions and emphasize emotionally important points. The summarization unit, for example, analyzes the speaker's emotions and builds a system that reflects emotionally important points in the summary. For example, it includes in the summary a statement in which the speaker expresses strong emotions. The summarization unit also uses emotion analysis to develop a summarization algorithm that emphasizes emotionally important points. For example, it reflects statements with high emotion scores in the summary. The summarization unit also analyzes the speaker's emotional changes in real time and builds a system that includes emotionally important points in the summary. For example, it reflects statements with large emotional changes in the summary. This allows the accuracy of the summary to be improved by emphasizing emotionally important points.

[0064] The summarization unit can add a function to display the summarized content in different formats. For example, the summarization unit adds a function to display the summarized content in a visual note format. For example, important points are shown using diagrams or icons. The summarization unit also adds a function to display the summarized content in an infographic format. For example, data or statistical information is visually displayed. The summarization unit also builds a system to display the summarized content in different formats. For example, the summary is displayed in a format selected by the user. This makes it easier to understand visually by displaying the summarized content in different formats.

[0065] The summarization unit can have experts from different industries and fields review the summarized content and improve the accuracy of the summarization based on the feedback. For example, the summarization unit builds a system that has experts from different industries and fields review the summarized content and collects feedback. For example, technical experts and marketing experts are asked to review the summaries. The summarization unit also develops an algorithm that improves the accuracy of the summarization based on the experts' feedback. For example, the summarization unit modifies the summaries to reflect the experts' opinions. The summarization unit also builds a system that has experts from different industries and fields review the summaries and improves the accuracy of the summaries based on the feedback. For example, the summaries are improved based on the experts' evaluation scores. This makes it possible to improve the accuracy of the summaries based on the feedback from experts from different industries and fields.

[0066] The summarization unit uses the emotion estimation function to collect users' emotional reactions to the summarized content and can improve the accuracy of the summary based on that. The summarization unit, for example, collects users' emotional reactions to the summarized content in real time and builds a system that improves the accuracy of the summary based on that data. For example, it prioritizes the adoption of summaries with a high number of positive reactions. The summarization unit also uses the emotion estimation function to collect feedback on the summarized content and develops a system that regenerates the summary if there are a high number of negative reactions. The summarization unit also analyzes users' emotional reaction data and builds a system that identifies areas to improve the summary based on the results. For example, it makes suggestions to correct parts with low emotional scores. This makes it possible to improve the accuracy of the summary based on users' emotional reactions.

[0067] The minutes-taking unit allows the format of minutes to be customized, and can automatically create minutes in a format that meets the user's needs. The minutes-taking unit, for example, allows the format of minutes to be customized, and builds a system that automatically creates minutes in a format selected by the user. For example, it allows the user to select a format such as a bulleted list format or a table format. The minutes-taking unit also adds a function to dynamically change the format of minutes to meet the user's needs. For example, it changes the format depending on the type of meeting and the purpose. The minutes-taking unit also provides a customizable minutes format, and builds a system that allows the user to freely set the format. For example, it adds a function to create and save templates. This makes it possible to automatically create minutes in a format that meets the user's needs.

[0068] The minutes-taking department will enable the generation AI to automatically add annotations and supplementary information to the contents of the minutes. For example, the minutes-taking department will build a system in which the generation AI automatically adds annotations to the contents of the minutes. For example, automatic explanations for technical terms and abbreviations will be added. The minutes-taking department will also introduce a function in which the generation AI adds supplementary information to the contents of the minutes. For example, automatic addition of links to related past meeting contents and reference materials. The minutes-taking department will also develop a system in which the generation AI analyzes the contents of the minutes and automatically adds necessary annotations and supplementary information. For example, adding background information on the discussion and related data. This will make it possible to automatically add annotations and supplementary information to the contents of the minutes, thereby helping to make the minutes easier to understand.

[0069] The minutes-taking section can analyze the emotions of the speaker and emphasize emotionally important points. The minutes-taking section, for example, analyzes the emotions of the speaker and builds a system that reflects emotionally important points in the minutes. For example, statements in which the speaker expresses strong emotions are highlighted. The minutes-taking section also uses emotion analysis to develop a minutes-taking algorithm that highlights emotionally important points. For example, statements with high emotion scores are displayed in bold or color. The minutes-taking section also builds a system that analyzes the speaker's emotional changes in real time and includes emotionally important points in the minutes. For example, statements with large emotional changes are highlighted. This allows the accuracy of the minutes to be improved by highlighting emotionally important points.

[0070] The minutes-taking department will automatically translate minutes into different languages, making it possible to handle international conferences. For example, the minutes-taking department will use generative AI to build a system that automatically translates minutes into different languages. For example, it will support multiple languages ​​such as English, Japanese, and Chinese. The minutes-taking department will also automatically translate the contents of minutes, making it possible to handle international conferences. For example, it will distribute automatically translated minutes after the conference ends. The minutes-taking department will also develop a system that translates minutes in real time using a multilingual translation algorithm. For example, it will translate what is said during the conference in real time and reflect this in the minutes. This will allow the minutes to be automatically translated into different languages, making it possible to handle international conferences.

[0071] The minutes-taking section can add a function to visualize minutes and display them in infographic or mind map format. For example, the minutes-taking section can add a function to display the contents of minutes in infographic format. For example, important points can be shown using diagrams or icons. The minutes-taking section can also add a function to display the contents of minutes in mind map format. For example, the minutes-taking section can visually organize agenda items and decisions. The minutes-taking section can also build a system to visualize minutes, allowing them to be displayed in a format selected by the user. For example, infographics or mind maps can be automatically generated. In this way, visualizing minutes can make them easier to understand visually.

[0072] The minutes-taking unit uses the emotion estimation function to collect users' emotional reactions to the content of the minutes, and can improve the content of the minutes based on that. For example, the minutes-taking unit collects users' emotional reactions to the content of the minutes in real time and builds a system to improve the content of the minutes based on that data. For example, it emphasizes parts that have a lot of positive reactions. The minutes-taking unit also uses the emotion estimation function to collect feedback on the content of the minutes, and develops a system that regenerates the minutes if there are a lot of negative reactions. The minutes-taking unit also analyzes users' emotional reaction data and builds a system that identifies areas to improve the minutes based on the results. For example, it makes suggestions to correct parts with low emotion scores. This makes it possible to improve the content of the minutes based on the users' emotional reactions.

[0073] The minutes-taking department can introduce a function that automatically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, the minutes-taking department can build a system that automatically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, the distribution destinations can be automatically set based on the list of meeting participants. The minutes-taking department can also develop an optimization algorithm for the distribution destinations and ensure that minutes are delivered to all parties involved. For example, email addresses and messenger app accounts can be automatically obtained. The minutes-taking department can also build a system that dynamically optimizes the distribution destinations of minutes and ensures that they are delivered to all parties involved. For example, this can also handle cases where the participants in a meeting change. In this way, the distribution destinations of minutes can be automatically optimized, ensuring that they are delivered to all parties involved.

[0074] The minutes-taking department will build a system in which the generation AI automatically sets reminders when minutes are distributed, thereby promoting follow-up. For example, the generation AI will remind people of the next meeting or the deadline for an action item. The minutes-taking department will also add a reminder setting function to automatically promote follow-up when minutes are distributed. For example, regular reminders of the progress of action items. The minutes-taking department will also develop a system in which the generation AI will analyze the contents of the minutes and automatically set necessary reminders. For example, reminders of important decisions and deadlines for action items. This will promote follow-up by automatically setting reminders.

[0075] The minutes-taking department can analyze the emotions of recipients when distributing minutes and attach a message that elicits an emotionally positive response. For example, the minutes-taking department builds a system that analyzes the emotions of recipients when distributing minutes and attaches a message that elicits an emotionally positive response. For example, it attaches a message of encouragement or words of gratitude. The minutes-taking department also adds a function that analyzes the emotions of recipients and automatically generates a message that elicits a positive response. For example, it generates a message based on the recipient's past emotional data. The minutes-taking department also develops a system that uses emotion analysis to automatically generate a message that matches the recipient's emotions and attaches it when distributing minutes. For example, it attaches a message that elicits positive emotions. In this way, by analyzing the recipient's emotions and attaching a message that elicits a positive response, it is possible to improve recipient satisfaction.

[0076] The minutes-taking department can automatically save minutes in cloud storage and distribute them by sharing a link. For example, the minutes-taking department will build a system that automatically saves minutes in cloud storage and distributes them by sharing a link. For example, it will automatically save them in Google Drive or Dropbox. The minutes-taking department will also add a function that automatically generates links to minutes saved in cloud storage and distributes them to relevant parties. For example, it will share the link via email or a messenger app. The minutes-taking department will also develop a system that automatically saves minutes in cloud storage and distributes them by sharing a link. For example, it will make it possible to access the minutes by simply clicking a link. This will make it easier to access the minutes by automatically saving them in cloud storage and distributing them by sharing a link.

[0077] The minutes-taking department will have the generation AI automatically create a summary when distributing minutes, allowing both a summary and a detailed version to be distributed. For example, the minutes-taking department will build a system in which the generation AI automatically generates a summary of minutes and distributes both a summary and a detailed version. For example, the summary version will be distributed by email and the detailed version will be shared via a link. The minutes-taking department will also add a function to automatically generate a summary of minutes and distribute both a summary and a detailed version. For example, the summary version will be distributed in short text format and the detailed version will be distributed in PDF format. The minutes-taking department will also develop a system in which the generation AI automatically generates a summary of minutes and distributes both a summary and a detailed version. For example, the summary version will be concise and the detailed version will include all the content of what was said. In this way, by distributing both the summary and the detailed version, recipients will be able to select and refer to the information they need.

[0078] The minutes-taking department can use the emotion estimation function to analyze the emotions of recipients when distributing minutes and attach a message that elicits an emotionally positive response. For example, the minutes-taking department builds a system that analyzes the emotions of recipients when distributing minutes and attaches a message that elicits an emotionally positive response. For example, it attaches a message of encouragement or words of gratitude. The minutes-taking department also adds a function that analyzes the emotions of recipients and automatically generates a message that elicits a positive response. For example, it generates a message based on the recipient's past emotional data. The minutes-taking department also develops a system that uses emotion analysis to automatically generate a message that matches the recipient's emotions and attaches it when distributing minutes. For example, it attaches a message that elicits positive emotions. In this way, by analyzing the recipient's emotions and attaching a message that elicits a positive response, it is possible to improve recipient satisfaction.

[0079] The minutes-taking department will build a system in which the generation AI automatically suggests related past meeting contents when searching for meeting contents. For example, the minutes-taking department will suggest related minutes based on keywords or topics. The minutes-taking department will also add a function to automatically suggest past meeting contents, allowing users to easily access related information. For example, by displaying links to related meetings. The minutes-taking department will also develop a system in which the generation AI analyzes meeting contents and automatically suggests related past meeting contents. For example, by suggesting past meeting contents related to the same agenda or topic. This will allow users to quickly access the information they need by automatically suggesting related past meeting contents.

[0080] The minutes-taking unit can add a function that allows the search results of meeting contents to be filtered by speaker or agenda. For example, the minutes-taking unit adds a function that allows the search results of meeting contents to be filtered by speaker. For example, only the remarks of a specific speaker are displayed. The minutes-taking unit also adds a function that allows the search results to be filtered by agenda, allowing users to easily access the information they need. For example, only the remarks related to a specific agenda are displayed. The minutes-taking unit also builds a system that filters search results by speaker or agenda, allowing users to search for information efficiently. For example, it provides a filtering option. This allows users to quickly access the information they need by filtering the search results by speaker or agenda.

[0081] The minutes-taking department can analyze the emotions of speakers and emphasize emotionally important points when searching for meeting content. The minutes-taking department, for example, builds a system that analyzes the emotions of speakers and emphasizes emotionally important points when searching for meeting content. For example, statements with high emotional scores are highlighted in the search results. The minutes-taking department also uses emotion analysis to develop a search algorithm that emphasizes emotionally important points. For example, statements with large emotional changes are displayed prominently in the search results. The minutes-taking department also builds a system that analyzes the emotional changes of speakers in real time and reflects emotionally important points in the search results. For example, statements are displayed in different colors depending on the intensity of the emotion. This allows the accuracy of search results to be improved by emphasizing emotionally important points.

[0082] The minutes-taking unit can add a function to display search results for meeting content in different formats. For example, the minutes-taking unit adds a function to display search results for meeting content in visual note format. For example, important points are shown using diagrams or icons. The minutes-taking unit also adds a function to display search results for meeting content in infographic format. For example, data or statistical information is visually displayed. The minutes-taking unit also builds a system to display search results in different formats, allowing the user to display search results in a format selected by the user. For example, visual notes or infographics are automatically generated. In this way, displaying search results in different formats makes them easier to understand visually.

[0083] The minutes-taking department can have experts from different industries and fields review search results for meeting content and improve the search algorithm based on the feedback. For example, the minutes-taking department builds a system that has experts from different industries and fields review search results for meeting content and collects feedback. For example, it has technical experts and marketing experts review the search results. The minutes-taking department also develops a system that improves the search algorithm based on the experts' feedback. For example, it adjusts the search results by reflecting the experts' opinions. The minutes-taking department also builds a system that has experts from different industries and fields review the search results and improves the search algorithm based on that feedback. For example, it improves the search results based on the experts' evaluation scores. This makes it possible to improve the search algorithm based on the feedback from experts from different industries and fields.

[0084] The minutes-taking department can use the emotion estimation function to collect users' emotional reactions to search results for meeting content and improve the search algorithm based on that. For example, the minutes-taking department collects users' emotional reactions to search results for meeting content in real time and builds a system to improve the search algorithm based on that data. For example, search results with a high number of positive reactions are preferentially displayed. The minutes-taking department also uses the emotion estimation function to collect feedback on the search results and develops a system to readjust the search algorithm if there are a high number of negative reactions. The minutes-taking department also analyzes users' emotional reaction data and builds a system to identify areas for improvement in the search algorithm based on the results. For example, it makes suggestions to improve search results with low emotion scores. This makes it possible to improve the search algorithm based on users' emotional reactions.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0087] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0088] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0089] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0090] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0091] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0092] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0093] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0094] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0095] The analysis unit analyzes the speaker's tone of voice and vocabulary during a meeting to detect changes in emotion in real time. For example, if the speaker is excited, it will emphasize that statement as an important point. The analysis unit also captures the speaker's facial expression with a camera, and the generation AI analyzes the expression to detect changes in emotion. For example, smiling or surprised expressions are used as indicators of important statements. The analysis unit also detects the speaker's gestures with a motion sensor, and the generation AI analyzes these movements to grasp changes in emotion. For example, if there is a lot of hand waving, it will emphasize that statement as an important point. This makes it possible to clarify the key points of a meeting by emphasizing important statements based on changes in emotion.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The speech recognition unit receives the conference audio data as input and converts it into text using speech recognition technology. For example, the speech recognition unit can receive MP3 format audio data and convert it into text using deep learning-based speech recognition technology. It can also receive WAV format audio data and convert it into text using an HMM (hidden Markov model). It can also receive real-time streaming audio data and convert it into text in real time. Step 2: The analysis unit analyzes the text data converted by the speech recognition unit in real time and extracts important points. For example, the analysis unit analyzes the frequency of keywords in the text data and extracts important points. It can also analyze the importance of the context of the text data and extract important points. It can also understand the context by referring to related background information and topic models and extract important points. Step 3: The summarization unit summarizes the key points extracted by the analysis unit. For example, the summarization unit briefly summarizes the key points of the text data. It can also adjust the length of the text based on the key points of the text data. It can also evaluate the importance of the information to be summarized. Step 4: The minutes-taking unit automatically creates minutes based on the information summarized by the summarizing unit. For example, the minutes-taking unit creates minutes in a format that includes the meeting start time, participants, agenda, discussion content, decisions, and next action items. It can also organize the summarized information and generate minutes in an easy-to-read format. It can also distribute the minutes to specified recipients.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 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.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0139] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0142] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0148] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0149] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0150] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0152] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0153] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0154] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0155] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0156] 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.

[0157] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0158] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0159] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0160] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0161] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0162] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0163] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0164] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a speech recognition unit that receives conference audio data as input and converts it into text using speech recognition technology; an analysis unit that analyzes the text data converted by the speech recognition unit in real time and extracts important points; a summarizing unit that summarizes the important points extracted by the analyzing unit; a minutes creation unit that automatically creates minutes based on the information summarized by the summarization unit. A system characterized by:

2. The analysis unit In addition to the audio data, video data is also analyzed and converted into text based on the speaker's facial expressions and gestures.

2. The system of claim 1.

3. The analysis unit Uses multilingual generation AI to handle meetings in different languages 2. The system of claim 1.

4. The summary section Dynamically re-evaluate key points based on frequency or importance of statements to improve the accuracy of the summary 2. The system of claim 1.

5. The minutes-taking department The format of the minutes can be customized and automatically created in a format that meets the user's needs.

2. The system of claim 1.

6. The minutes-taking department When distributing the minutes, analyze the emotions of the recipients and attach a message that elicits a positive emotional response.

2. The system of claim 1.

7. The minutes-taking department Collecting users' emotional responses to meeting content search results and using them to improve search algorithms 2. The system of claim 1.

Images