system

Abstract

The system according to the embodiment aims to quickly and accurately create minutes after a meeting. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects meeting conversation data. The analysis unit analyzes the conversation data collected by the collection unit and extracts the main points of the discussion. The generation unit generates meeting minutes based on the main points extracted by the analysis unit. The provision unit provides the meeting minutes generated by the generation unit.

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] With conventional technology, creating meeting minutes after a meeting can take time, hindering productive work.

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

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects conversation data from a meeting. The analysis unit analyzes the conversation data collected by the collection unit and extracts key points of the discussion. The generation unit generates minutes based on the key points extracted by the analysis unit. The provision unit provides the minutes generated by the generation unit. [Effects of the Invention]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) A minutes-generation system according to an embodiment of the present invention collects meeting conversation data, analyzes it using a generation AI, extracts key points from the discussion, and generates accurate minutes. This minutes-generation system transmits the conversation data to the cloud in real time, where the cloud-based generation AI analyzes the conversation data, extracts key points, and generates accurate minutes. For example, when using an online conferencing tool such as Zoom, the conversation data is automatically uploaded to the cloud. The cloud-based generation AI then analyzes the conversation data and extracts key points from the discussion. The generation AI understands the content of the conversation and accurately grasps key points and the intent of the comments. For example, it extracts ideas proposed by the speaker and decisions made. The generation AI then generates accurate minutes based on the extracted key points. In this process, the generation AI accurately reflects the intent of the comments, preventing misunderstandings or records with different meanings. For example, it generates a summary that accurately reflects the speaker's intent. Finally, the generated minutes are provided to participants immediately after the meeting. This significantly reduces the time required to create minutes, allowing participants to focus on productive work. For example, the minutes can be sent by email immediately after the meeting ends. This system not only reduces the time required to create minutes, but also generates accurate minutes that accurately reflect the intent of those who spoke, ensuring that the content of the meeting is accurately recorded. This improves meeting efficiency and allows participants to focus on productive work. This enables the minutes-generation system to efficiently collect, analyze, extract key points, generate, and provide meeting conversation data.

[0029] The meeting minutes generation system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects meeting conversation data. Meeting conversation data includes, but is not limited to, audio data and text data. The collection unit transmits the meeting conversation data to the cloud in real time. For example, if an online meeting tool such as Zoom is used, the conversation data is automatically uploaded to the cloud. The analysis unit uses a generation AI to analyze the conversation data collected by the collection unit and extract the main points of the discussion. The analysis unit, for example, understands the content of the conversation and accurately grasps the important points and the intent of the statements. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to analyze the conversation data. The generation AI, for example, understands the content of the conversation and accurately grasps the important points and the intent of the statements. The generation unit uses the generation AI to generate meeting minutes based on the main points extracted by the analysis unit. The generation unit generates, for example, a summary that accurately reflects the intent of the speaker. The provisioning unit provides the meeting minutes generated by the generation unit. The provisioning unit provides the meeting minutes to participants immediately after the meeting ends, for example. For example, the meeting minutes are sent by email immediately after the meeting ends. This enables the meeting minutes generation system according to the embodiment to efficiently collect, analyze, extract key points from meeting conversation data, generate meeting minutes, and provide them.

[0030] The data collection unit can transmit meeting conversation data to the cloud in real time. For example, the data collection unit transmits meeting conversation data to the cloud in real time. Specific definitions and criteria of "real time" include, but are not limited to, acceptable latency. For example, by transmitting meeting conversation data to the cloud in real time, the data collection unit enables rapid data processing. For example, by transmitting meeting conversation data to the cloud in real time, the data collection unit can analyze the data and extract key points of the discussion while the meeting is in progress. This enables rapid data processing by transmitting meeting conversation data to the cloud in real time.

[0031] The analysis unit can understand the content of a conversation and accurately grasp the key points and intent of the statements. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. Specific methods and criteria for understanding the content of a conversation include, but are not limited to, natural language processing techniques and contextual analysis. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. Specific definitions and extraction methods for key points include, but are not limited to, frequently occurring keywords and intent of statements. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. As a result, the analysis unit accurately understands the content of the conversation and grasps the key points and intent of the statements, thereby generating accurate meeting minutes.

[0032] The generation unit can generate a summary that accurately reflects the speaker's intent. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. Specific methods and criteria for accurately reflecting the speaker's intent include, but are not limited to, contextual analysis and sentiment analysis. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. Specific forms and content of the summary include, but are not limited to, short summaries and detailed summaries. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. As a result, the generation unit provides meeting minutes that are free from misunderstandings by generating a summary that accurately reflects the speaker's intent.

[0033] The providing unit can provide the minutes to the participants immediately after the end of the meeting. The providing unit, for example, provides the minutes to the participants immediately after the end of the meeting. A specific time range of immediately after the end of the meeting includes, but is not limited to, for example, within a few minutes or within a few hours. For example, the providing unit provides the minutes to the participants immediately after the end of the meeting. As a result, the providing unit provides the minutes immediately after the end of the meeting, enabling rapid information sharing. For example, the providing unit sends the minutes by email immediately after the end of the meeting. For example, the providing unit shares the minutes using a chat tool immediately after the end of the meeting. For example, the providing unit uploads the minutes to cloud storage immediately after the end of the meeting and shares a link. As a result, the providing unit provides the minutes immediately after the end of the meeting, enabling rapid information sharing.

[0034] The collection unit can determine the priority of data to be collected based on the speech frequency and speech content of the conference participants. The collection unit determines the priority of data to be collected based on, for example, the speech frequency and speech content of the conference participants. Specific measurement methods and criteria for speech frequency include, for example, but are not limited to, the number of speeches and speech duration. Specific analysis methods and criteria for speech content include, for example, but are not limited to, keyword extraction and context analysis. For example, the collection unit prioritizes collecting data from participants who speak frequently. For example, the collection unit prioritizes collecting data containing important speech content. For example, the collection unit performs optimal data collection by taking into consideration both speech frequency and content. As a result, the collection unit can efficiently collect important data by determining the priority of data based on speech frequency and content.

[0035] The data collection unit can prioritize collecting conversation data on specific agenda items according to the progress of the meeting. For example, the data collection unit prioritizes collecting conversation data on specific agenda items according to the progress of the meeting. Specific methods and criteria for understanding the progress of the meeting include, but are not limited to, the progress of agenda items and the frequency of comments. Specific definitions and scopes of specific agenda items include, but are not limited to, main agenda items and sub-agenda items. For example, when an agenda item is changed, the data collection unit prioritizes collecting conversation data on that agenda item. For example, the data collection unit prioritizes collecting data on important agenda items according to the progress of the meeting. For example, the data collection unit collects data on specific agenda items in real time in accordance with the progress of the meeting. This allows the data collection unit to efficiently collect information on important agenda items by collecting data according to the progress of the meeting.

[0036] The data collection unit can adjust the scope of data collected based on the job titles and areas of expertise of the meeting participants. For example, the data collection unit can adjust the scope of data collected based on the job titles and areas of expertise of the meeting participants. Specific definitions and scopes of job titles include, but are not limited to, management positions and general staff positions. Specific definitions and scopes of areas of expertise include, but are not limited to, technical fields and business fields. For example, the data collection unit may prioritize collecting statements from participants with higher job titles. The data collection unit may, for example, focus on collecting statements related to areas of expertise. The data collection unit may, for example, consider both job titles and areas of expertise to perform optimal data collection. This allows the data collection unit to efficiently collect important data by adjusting the scope of data based on job titles and areas of expertise.

[0037] The collection unit can change the format of data to be collected based on the location and time of the conference. The collection unit changes the format of data to be collected, for example, based on the location and time of the conference. Specific definitions and ranges of the location include, for example, office, remote, etc., but are not limited to these examples. Specific definitions and ranges of the time period include, for example, morning, afternoon, night, etc., but are not limited to these examples. For example, if the conference is held online, the collection unit prioritizes collecting audio data. For example, if the conference is held offline, the collection unit prioritizes collecting video data. The collection unit adjusts the data collection format according to, for example, the time of the conference. In this way, the collection unit can optimally collect data by changing the data format based on the location and time of the conference.

[0038] The analysis unit can introduce an analysis method for more accurately grasping important points and the intention of utterances by taking into account the context of the conversation data. The analysis unit introduces an analysis method for more accurately grasping important points and the intention of utterances by taking into account the context of the conversation data, for example, using a generative AI. Specific definitions of context and analysis methods include, for example, preceding and following utterances, related topics, etc., but are not limited to such examples. For example, the analysis unit extracts important points by taking into account the context before and after the conversation. For example, the analysis unit performs context analysis to accurately grasp the intention of utterances. For example, the analysis unit accurately grasps important points by taking into account the flow of the conversation. In this way, the analysis unit can accurately grasp important points and the intention of utterances by taking into account the context.

[0039] The analysis unit can apply a different analysis algorithm to each meeting agenda item and extract the key points of the discussion. The analysis unit, for example, uses a generative AI to apply a different analysis algorithm to each meeting agenda item and extract the key points of the discussion. Specific types and standards of analysis algorithms applied to each agenda item include, but are not limited to, deep learning and natural language processing. For example, the analysis unit selects the optimal analysis algorithm for each agenda item and extracts the key points. For example, the analysis unit applies a different analysis method depending on the content of the agenda item. For example, the analysis unit applies a different algorithm to each agenda item and extracts the key points. This allows the analysis unit to efficiently extract the key points by applying the optimal analysis algorithm to each agenda item.

[0040] The analysis unit analyzes the voice tone and speed of the conversation data to more accurately grasp the intention of the speech. The analysis unit, for example, uses a generative AI to analyze the voice tone and speed of the conversation data to more accurately grasp the intention of the speech. Specific analysis methods and criteria for voice tone include, for example, but are not limited to, voice pitch and strength. Specific analysis methods and criteria for speed include, for example, but are not limited to, speech speed and pauses. For example, the analysis unit analyzes voice tone to grasp the emotion of the speech. For example, the analysis unit analyzes speech speed to determine urgency and importance. For example, the analysis unit analyzes both voice tone and speed to accurately grasp the intention of the speech. In this way, the analysis unit can accurately grasp the intention of the speech by analyzing voice tone and speed.

[0041] The analysis unit can analyze the intention of a statement by referring to the past statement history of the meeting participants. The analysis unit, for example, uses a generation AI to analyze the intention of a statement by referring to the past statement history of the meeting participants. Specific methods for collecting and analyzing the past statement history include, for example, past meeting records and frequency of statements, but are not limited to these examples. For example, the analysis unit analyzes the intention of a statement based on the past statement history of the participants. For example, the analysis unit understands the intention of a current statement by referring to the content of past statements. For example, the analysis unit analyzes the statement history of the participants and accurately analyzes the intention of the statement. As a result, the analysis unit can accurately analyze the intention of a statement by referring to the past statement history.

[0042] The generation unit can adjust the level of detail in the minutes based on the importance of the meeting. The generation unit adjusts the level of detail in the minutes based on the importance of the meeting, for example, using a generation AI. Specific evaluation criteria and adjustment methods for the importance of the meeting include, for example, the positions of the participants and the importance of the agenda, but are not limited to these examples. For example, the generation unit generates detailed minutes for an important meeting. For example, the generation unit generates minutes that focus on the main points for an ordinary meeting. The generation unit adjusts the level of detail in the minutes based on the importance, for example. In this way, the generation unit can efficiently provide important information by adjusting the level of detail in the minutes based on the importance of the meeting.

[0043] The generation unit can apply different summarization algorithms to each meeting agenda item to generate summaries that accurately reflect the speaker's intent. For example, the generation unit uses generational AI to apply different summarization algorithms to each meeting agenda item to generate summaries that accurately reflect the speaker's intent. Specific types and application methods of summarization algorithms include, but are not limited to, abstract summarization and extractive summarization. For example, the generation unit selects the optimal summarization algorithm for each agenda item and generates a summary. The generation unit applies different summarization methods depending on the content of the agenda item. For example, the generation unit applies different algorithms to each agenda item to generate summaries that accurately reflect the speaker's intent. Thus, by applying the optimal summarization algorithm for each agenda item, the generation unit can generate summaries that accurately reflect the speaker's intent.

[0044] The generation unit can determine the priority of meeting minutes based on the progress of the meeting. For example, the generation unit uses generation AI to determine the priority of meeting minutes based on the progress of the meeting. Specific methods and criteria for determining priority include, but are not limited to, the importance of the agenda items and the frequency of their remarks. For example, the generation unit prioritizes generating minutes for important agenda items according to the progress of the meeting. For example, the generation unit adjusts the priority of meeting minutes in accordance with the progress of the meeting. For example, the generation unit generates optimal meeting minutes considering the progress of the meeting. In this way, the generation unit can efficiently provide important information by determining the priority of meeting minutes according to the progress of the meeting.

[0045] The generation unit can customize the content of the minutes based on the positions and areas of expertise of the meeting participants. The generation unit, for example, uses a generation AI to customize the content of the minutes based on the positions and areas of expertise of the meeting participants. Specific methods and criteria for customization include, for example, information for each position and information for each area of ​​expertise, but are not limited to these examples. For example, the generation unit generates detailed minutes for participants with higher positions. For example, the generation unit generates minutes that include information related to the area of ​​expertise. For example, the generation unit generates optimal minutes by taking into account both the position and the area of ​​expertise. In this way, the generation unit can provide optimal information to participants by customizing the content of the minutes based on the position and the area of ​​expertise.

[0046] The providing unit can optimize the notification method for providing minutes immediately after the end of the meeting. The providing unit, for example, uses AI to optimize the notification method for providing minutes immediately after the end of the meeting. Specific types of notification methods and optimization methods include, for example, push notification and email notification, but are not limited to these examples. For example, the providing unit sends the minutes by email immediately after the end of the meeting. For example, the providing unit shares the minutes via a chat tool immediately after the end of the meeting. For example, the providing unit uploads the minutes to cloud storage immediately after the end of the meeting and shares a link. This allows the providing unit to provide the minutes immediately after the end of the meeting, enabling rapid information sharing.

[0047] The minutes providing unit can collect feedback from meeting participants and improve the method for providing minutes. The minutes providing unit, for example, uses AI to collect feedback from meeting participants and improve the method for providing minutes. Specific methods for collecting and improving feedback include, but are not limited to, questionnaire surveys and direct opinion collection. For example, the minutes providing unit collects feedback from participants after the meeting and improves the method for providing minutes. For example, the minutes providing unit adjusts the format for providing minutes based on the feedback. For example, the minutes providing unit reflects the opinions of participants and introduces the optimal method for providing minutes. In this way, the minutes providing unit improves the method for providing minutes based on the feedback from participants, enabling the optimal minutes to be provided.

[0048] The providing unit can provide minutes in an optimal format by taking into account device information of the meeting participants. The providing unit, for example, uses AI to provide minutes in an optimal format by taking into account device information of the meeting participants. Specific types of device information and methods of consideration include, but are not limited to, smartphones, tablets, and PCs. For example, the providing unit provides minutes in a mobile-friendly format to participants using smartphones. For example, the providing unit provides minutes in a format optimized for large screens to participants using tablets. For example, the providing unit provides minutes in a format including detailed information to participants using desktops. In this way, the providing unit can provide minutes with high visibility by providing the minutes in an optimal format based on device information.

[0049] The service provider can customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. For example, the service provider can use AI to customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. Specific methods and criteria for customizing the content include, but are not limited to, information specific to each job title or area of ​​expertise. For example, the service provider can provide detailed minutes for participants with higher job titles. The service provider can provide minutes that focus on information relevant to each participant's area of ​​expertise. The service provider can provide optimal minutes considering both job title and area of ​​expertise. This allows the service provider to provide participants with the most relevant information by customizing the content of the meeting minutes based on their job title and area of ​​expertise.

[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 analysis unit can analyze the frequency of appearance of specific keywords in conversation data and extract important points based on that frequency. For example, the analysis unit can identify keywords that frequently appear in conversations and focus its analysis on statements related to those keywords. The analysis unit can also analyze the timing of appearance of specific keywords and extract important points based on that timing. The analysis unit can combine keyword frequency with context to extract more accurate key points. This allows the analysis unit to efficiently extract important points based on keyword frequency.

[0052] The providing unit can provide the minutes in an optimal format taking into account device information of the meeting participants. For example, the providing unit provides the minutes in a mobile-friendly format for participants using smartphones. For example, the providing unit provides the minutes in a format optimized for large screens for participants using tablets. For example, the providing unit provides the minutes in a format including detailed information for participants using desktops. In this way, the providing unit can provide minutes with high visibility by providing the minutes in an optimal format based on device information.

[0053] The collection unit can adjust the range of data to be collected based on the job titles and areas of expertise of the meeting participants. For example, the collection unit prioritizes collecting comments from participants with higher job titles. For example, the collection unit focuses on collecting comments related to areas of expertise. For example, the collection unit performs optimal data collection by taking into account both job titles and areas of expertise. This allows the collection unit to efficiently collect important data by adjusting the range of data based on job titles and areas of expertise.

[0054] The generation unit can apply a different summarization algorithm to each agenda item of the meeting to generate a summary that accurately reflects the speaker's intention. For example, the generation unit selects the optimal summarization algorithm for each agenda item to generate a summary. The generation unit applies a different summarization method depending on, for example, the content of the agenda item. The generation unit applies a different algorithm to each agenda item to generate a summary that accurately reflects the speaker's intention. In this way, the generation unit can generate a summary that accurately reflects the speaker's intention by applying the optimal summarization algorithm to each agenda item.

[0055] The collection unit can focus on collecting conversation data related to a specific agenda item according to the progress of the meeting. For example, when an agenda item is changed, the collection unit focuses on collecting conversation data related to that agenda item. For example, the collection unit prioritizes collecting data related to important agenda items according to the progress of the meeting. For example, the collection unit collects data related to specific agenda items in real time according to the progress of the meeting. In this way, the collection unit can efficiently collect information related to important agenda items by collecting data according to the progress of the meeting.

[0056] The analysis unit analyzes the voice tone and speed of the conversation data, and can grasp the intention of the utterance more accurately. For example, the analysis unit analyzes the voice tone to grasp the emotion of the utterance. For example, the analysis unit analyzes the speed of the utterance to determine the urgency and importance. For example, the analysis unit analyzes both the voice tone and speed to grasp the intention of the utterance. In this way, the analysis unit can accurately grasp the intention of the utterance by analyzing the voice tone and speed.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The collection unit collects meeting conversation data. The meeting conversation data includes, for example, audio data and text data. The collection unit transmits the meeting conversation data to the cloud in real time. For example, if an online meeting tool such as Zoom is used, the conversation data is automatically uploaded to the cloud. Step 2: The analysis unit uses the generation AI to analyze the conversation data collected by the collection unit and extract the key points of the discussion. The analysis unit understands the content of the conversation and accurately grasps the important points and intentions of the remarks. The generation AI analyzes the conversation data using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The generation unit uses AI to generate minutes based on the key points extracted by the analysis unit. The generation unit generates a summary that accurately reflects the speaker's intentions. Step 4: The providing unit provides the minutes generated by the generating unit. The providing unit provides the minutes to the participants immediately after the end of the meeting. For example, the minutes are sent by email immediately after the end of the meeting.

[0059] (Example 2) A minutes-generation system according to an embodiment of the present invention collects meeting conversation data, analyzes it using a generation AI, extracts key points from the discussion, and generates accurate minutes. This minutes-generation system transmits the conversation data to the cloud in real time, where the cloud-based generation AI analyzes the conversation data, extracts key points, and generates accurate minutes. For example, when using an online conferencing tool such as Zoom, the conversation data is automatically uploaded to the cloud. The cloud-based generation AI then analyzes the conversation data and extracts key points from the discussion. The generation AI understands the content of the conversation and accurately grasps key points and the intent of the comments. For example, it extracts ideas proposed by the speaker and decisions made. The generation AI then generates accurate minutes based on the extracted key points. In this process, the generation AI accurately reflects the intent of the comments, preventing misunderstandings or records with different meanings. For example, it generates a summary that accurately reflects the speaker's intent. Finally, the generated minutes are provided to participants immediately after the meeting. This significantly reduces the time required to create minutes, allowing participants to focus on productive work. For example, the minutes can be sent by email immediately after the meeting ends. This system not only reduces the time required to create minutes, but also generates accurate minutes that accurately reflect the intent of those who spoke, ensuring that the content of the meeting is accurately recorded. This improves meeting efficiency and allows participants to focus on productive work. This enables the minutes-generation system to efficiently collect, analyze, extract key points, generate, and provide meeting conversation data.

[0060] The meeting minutes generation system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, and a provision unit. The collection unit collects meeting conversation data. Meeting conversation data includes, but is not limited to, audio data and text data. The collection unit transmits the meeting conversation data to the cloud in real time. For example, if an online meeting tool such as Zoom is used, the conversation data is automatically uploaded to the cloud. The analysis unit uses a generation AI to analyze the conversation data collected by the collection unit and extract the main points of the discussion. The analysis unit, for example, understands the content of the conversation and accurately grasps the important points and the intent of the statements. The generation AI uses a text generation AI (e.g., LLM) or a multimodal generation AI to analyze the conversation data. The generation AI, for example, understands the content of the conversation and accurately grasps the important points and the intent of the statements. The generation unit uses the generation AI to generate meeting minutes based on the main points extracted by the analysis unit. The generation unit generates, for example, a summary that accurately reflects the intent of the speaker. The provisioning unit provides the meeting minutes generated by the generation unit. The provisioning unit provides the meeting minutes to participants immediately after the meeting ends, for example. For example, the meeting minutes are sent by email immediately after the meeting ends. This enables the meeting minutes generation system according to the embodiment to efficiently collect, analyze, extract key points from meeting conversation data, generate meeting minutes, and provide them.

[0061] The data collection unit can transmit meeting conversation data to the cloud in real time. For example, the data collection unit transmits meeting conversation data to the cloud in real time. Specific definitions and criteria of "real time" include, but are not limited to, acceptable latency. For example, by transmitting meeting conversation data to the cloud in real time, the data collection unit enables rapid data processing. For example, by transmitting meeting conversation data to the cloud in real time, the data collection unit can analyze the data and extract key points of the discussion while the meeting is in progress. This enables rapid data processing by transmitting meeting conversation data to the cloud in real time.

[0062] The analysis unit can understand the content of a conversation and accurately grasp the key points and intent of the statements. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. Specific methods and criteria for understanding the content of a conversation include, but are not limited to, natural language processing techniques and contextual analysis. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. Specific definitions and extraction methods for key points include, but are not limited to, frequently occurring keywords and intent of statements. For example, the analysis unit uses generative AI to understand the content of a conversation and accurately grasp the key points and intent of the statements. As a result, the analysis unit accurately understands the content of the conversation and grasps the key points and intent of the statements, thereby generating accurate meeting minutes.

[0063] The generation unit can generate a summary that accurately reflects the speaker's intent. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. Specific methods and criteria for accurately reflecting the speaker's intent include, but are not limited to, contextual analysis and sentiment analysis. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. Specific forms and content of the summary include, but are not limited to, short summaries and detailed summaries. For example, the generation unit uses a generation AI to generate a summary that accurately reflects the speaker's intent. As a result, the generation unit provides meeting minutes that are free from misunderstandings by generating a summary that accurately reflects the speaker's intent.

[0064] The providing unit can provide the minutes to the participants immediately after the end of the meeting. The providing unit, for example, provides the minutes to the participants immediately after the end of the meeting. A specific time range of immediately after the end of the meeting includes, but is not limited to, for example, within a few minutes or within a few hours. For example, the providing unit provides the minutes to the participants immediately after the end of the meeting. As a result, the providing unit provides the minutes immediately after the end of the meeting, enabling rapid information sharing. For example, the providing unit sends the minutes by email immediately after the end of the meeting. For example, the providing unit shares the minutes using a chat tool immediately after the end of the meeting. For example, the providing unit uploads the minutes to cloud storage immediately after the end of the meeting and shares a link. As a result, the providing unit provides the minutes immediately after the end of the meeting, enabling rapid information sharing.

[0065] The data collection unit can estimate the user's emotions and adjust the timing of conversation data collection based on the estimated emotions. For example, the data collection unit can estimate the user's emotions and adjust the timing of conversation data collection based on the estimated emotions. Specific methods and criteria for estimating user emotions include, but are not limited to, voice tone analysis and facial expression recognition. Specific methods and criteria for adjusting the timing of collection include, but are not limited to, the frequency of speech and changes in emotion. For example, if the user is nervous, the data collection unit will prioritize collecting important parts of the conversation. If the user is relaxed, for example, the data collection unit will collect the entire conversation data evenly. If the user is in a hurry, for example, the data collection unit will quickly collect concise conversation data. This allows the data collection unit to efficiently collect important data by adjusting the timing of conversation data collection according to the user's emotions.

[0066] The collection unit can determine the priority of data to be collected based on the speech frequency and speech content of the conference participants. The collection unit determines the priority of data to be collected based on, for example, the speech frequency and speech content of the conference participants. Specific measurement methods and criteria for speech frequency include, for example, but are not limited to, the number of speeches and speech duration. Specific analysis methods and criteria for speech content include, for example, but are not limited to, keyword extraction and context analysis. For example, the collection unit prioritizes collecting data from participants who speak frequently. For example, the collection unit prioritizes collecting data containing important speech content. For example, the collection unit performs optimal data collection by taking into consideration both speech frequency and content. As a result, the collection unit can efficiently collect important data by determining the priority of data based on speech frequency and content.

[0067] The data collection unit can prioritize collecting conversation data on specific agenda items according to the progress of the meeting. For example, the data collection unit prioritizes collecting conversation data on specific agenda items according to the progress of the meeting. Specific methods and criteria for understanding the progress of the meeting include, but are not limited to, the progress of agenda items and the frequency of comments. Specific definitions and scopes of specific agenda items include, but are not limited to, main agenda items and sub-agenda items. For example, when an agenda item is changed, the data collection unit prioritizes collecting conversation data on that agenda item. For example, the data collection unit prioritizes collecting data on important agenda items according to the progress of the meeting. For example, the data collection unit collects data on specific agenda items in real time in accordance with the progress of the meeting. This allows the data collection unit to efficiently collect information on important agenda items by collecting data according to the progress of the meeting.

[0068] The data collection unit can estimate the user's emotions and filter the collected conversation data based on those estimated emotions. For example, the data collection unit can estimate the user's emotions and filter the collected conversation data based on those estimated emotions. Specific filtering methods and criteria include, but are not limited to, statements of high importance or strong emotions. For example, if the user is tense, the data collection unit will prioritize filtering important statements. If the user is relaxed, the data collection unit will filter the entire conversation data evenly. If the user is in a hurry, the data collection unit will quickly filter for key points. This allows the data collection unit to efficiently collect important data by filtering conversation data according to the user's emotions.

[0069] The data collection unit can adjust the scope of data collected based on the job titles and areas of expertise of the meeting participants. For example, the data collection unit can adjust the scope of data collected based on the job titles and areas of expertise of the meeting participants. Specific definitions and scopes of job titles include, but are not limited to, management positions and general staff positions. Specific definitions and scopes of areas of expertise include, but are not limited to, technical fields and business fields. For example, the data collection unit may prioritize collecting statements from participants with higher job titles. The data collection unit may, for example, focus on collecting statements related to areas of expertise. The data collection unit may, for example, consider both job titles and areas of expertise to perform optimal data collection. This allows the data collection unit to efficiently collect important data by adjusting the scope of data based on job titles and areas of expertise.

[0070] The collection unit can change the format of data to be collected based on the location and time of the conference. The collection unit changes the format of data to be collected, for example, based on the location and time of the conference. Specific definitions and ranges of the location include, for example, office, remote, etc., but are not limited to these examples. Specific definitions and ranges of the time period include, for example, morning, afternoon, night, etc., but are not limited to these examples. For example, if the conference is held online, the collection unit prioritizes collecting audio data. For example, if the conference is held offline, the collection unit prioritizes collecting video data. The collection unit adjusts the data collection format according to, for example, the time of the conference. In this way, the collection unit can optimally collect data by changing the data format based on the location and time of the conference.

[0071] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. The analysis unit, for example, uses a generative AI to estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. Specific types and adjustment methods of the analysis algorithm include, but are not limited to, machine learning algorithms and rule-based analysis. For example, if the user is nervous, the analysis unit applies an algorithm that prioritizes analyzing important points. For example, if the user is relaxed, the analysis unit applies an algorithm that analyzes the overall conversation data evenly. For example, if the user is in a hurry, the analysis unit applies an algorithm that quickly analyzes the main points. In this way, the analysis unit can efficiently analyze important points by adjusting the analysis algorithm according to the user's emotions.

[0072] The analysis unit can introduce an analysis method for more accurately grasping important points and the intention of utterances by taking into account the context of the conversation data. The analysis unit introduces an analysis method for more accurately grasping important points and the intention of utterances by taking into account the context of the conversation data, for example, using a generative AI. Specific definitions of context and analysis methods include, for example, preceding and following utterances, related topics, etc., but are not limited to such examples. For example, the analysis unit extracts important points by taking into account the context before and after the conversation. For example, the analysis unit performs context analysis to accurately grasp the intention of utterances. For example, the analysis unit accurately grasps important points by taking into account the flow of the conversation. In this way, the analysis unit can accurately grasp important points and the intention of utterances by taking into account the context.

[0073] The analysis unit can apply a different analysis algorithm to each meeting agenda item and extract the key points of the discussion. The analysis unit, for example, uses a generative AI to apply a different analysis algorithm to each meeting agenda item and extract the key points of the discussion. Specific types and standards of analysis algorithms applied to each agenda item include, but are not limited to, deep learning and natural language processing. For example, the analysis unit selects the optimal analysis algorithm for each agenda item and extracts the key points. For example, the analysis unit applies a different analysis method depending on the content of the agenda item. For example, the analysis unit applies a different algorithm to each agenda item and extracts the key points. This allows the analysis unit to efficiently extract the key points by applying the optimal analysis algorithm to each agenda item.

[0074] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, the analysis unit uses generative AI to estimate the user's emotions and adjusts the display method of the analysis results based on the estimated emotions. Specific types of display methods and adjustment methods include, but are not limited to, graph displays and text displays. For example, if the user is tense, the analysis unit provides a simple and highly visible display method. If the user is relaxed, for example, the analysis unit provides a display method that includes detailed information. If the user is in a hurry, for example, the analysis unit provides a display method that gets straight to the point. In this way, the analysis unit can provide highly visible analysis results by adjusting the display method according to the user's emotions.

[0075] The analysis unit analyzes the voice tone and speed of the conversation data to more accurately grasp the intention of the speech. The analysis unit, for example, uses a generative AI to analyze the voice tone and speed of the conversation data to more accurately grasp the intention of the speech. Specific analysis methods and criteria for voice tone include, for example, but are not limited to, voice pitch and strength. Specific analysis methods and criteria for speed include, for example, but are not limited to, speech speed and pauses. For example, the analysis unit analyzes voice tone to grasp the emotion of the speech. For example, the analysis unit analyzes speech speed to determine urgency and importance. For example, the analysis unit analyzes both voice tone and speed to accurately grasp the intention of the speech. In this way, the analysis unit can accurately grasp the intention of the speech by analyzing voice tone and speed.

[0076] The analysis unit can analyze the intention of a statement by referring to the past statement history of the meeting participants. The analysis unit, for example, uses a generation AI to analyze the intention of a statement by referring to the past statement history of the meeting participants. Specific methods for collecting and analyzing the past statement history include, for example, past meeting records and frequency of statements, but are not limited to these examples. For example, the analysis unit analyzes the intention of a statement based on the past statement history of the participants. For example, the analysis unit understands the intention of a current statement by referring to the content of past statements. For example, the analysis unit analyzes the statement history of the participants and accurately analyzes the intention of the statement. As a result, the analysis unit can accurately analyze the intention of a statement by referring to the past statement history.

[0077] The generation unit can estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user's emotions. The generation unit, for example, uses a generation AI to estimate the user's emotions and adjust the presentation style of the minutes based on the estimated user's emotions. Specific types of presentation styles and adjustment methods for the minutes include, but are not limited to, formal and casual expressions. For example, if the user is nervous, the generation unit generates minutes that are simple and highly readable. For example, if the user is relaxed, the generation unit generates minutes that include detailed information. For example, if the user is in a hurry, the generation unit generates minutes that focus on the main points. In this way, the generation unit can provide highly readable minutes by adjusting the presentation style of the minutes according to the user's emotions.

[0078] The generation unit can adjust the level of detail in the minutes based on the importance of the meeting. The generation unit adjusts the level of detail in the minutes based on the importance of the meeting, for example, using a generation AI. Specific evaluation criteria and adjustment methods for the importance of the meeting include, for example, the positions of the participants and the importance of the agenda, but are not limited to these examples. For example, the generation unit generates detailed minutes for an important meeting. For example, the generation unit generates minutes that focus on the main points for an ordinary meeting. The generation unit adjusts the level of detail in the minutes based on the importance, for example. In this way, the generation unit can efficiently provide important information by adjusting the level of detail in the minutes based on the importance of the meeting.

[0079] The generation unit can apply different summarization algorithms to each meeting agenda item to generate summaries that accurately reflect the speaker's intent. For example, the generation unit uses generational AI to apply different summarization algorithms to each meeting agenda item to generate summaries that accurately reflect the speaker's intent. Specific types and application methods of summarization algorithms include, but are not limited to, abstract summarization and extractive summarization. For example, the generation unit selects the optimal summarization algorithm for each agenda item and generates a summary. The generation unit applies different summarization methods depending on the content of the agenda item. For example, the generation unit applies different algorithms to each agenda item to generate summaries that accurately reflect the speaker's intent. Thus, by applying the optimal summarization algorithm for each agenda item, the generation unit can generate summaries that accurately reflect the speaker's intent.

[0080] The generation unit can estimate the user's emotions and adjust the length of the meeting minutes based on those emotions. For example, the generation unit uses generation AI to estimate the user's emotions and adjust the length of the meeting minutes based on those emotions. Specific methods and criteria for adjusting the length of the meeting minutes include, but are not limited to, the number of pages and the number of characters. For example, if the user is nervous, the generation unit will generate short, concise minutes. If the user is relaxed, for example, the generation unit will generate longer minutes containing more detailed information. If the user is in a hurry, for example, the generation unit will generate short, concise minutes. In this way, the generation unit can provide highly readable meeting minutes by adjusting the length according to the user's emotions.

[0081] The generation unit can determine the priority of meeting minutes based on the progress of the meeting. For example, the generation unit uses generation AI to determine the priority of meeting minutes based on the progress of the meeting. Specific methods and criteria for determining priority include, but are not limited to, the importance of the agenda items and the frequency of their remarks. For example, the generation unit prioritizes generating minutes for important agenda items according to the progress of the meeting. For example, the generation unit adjusts the priority of meeting minutes in accordance with the progress of the meeting. For example, the generation unit generates optimal meeting minutes considering the progress of the meeting. In this way, the generation unit can efficiently provide important information by determining the priority of meeting minutes according to the progress of the meeting.

[0082] The generation unit can customize the content of the minutes based on the positions and areas of expertise of the meeting participants. The generation unit, for example, uses a generation AI to customize the content of the minutes based on the positions and areas of expertise of the meeting participants. Specific methods and criteria for customization include, for example, information for each position and information for each area of ​​expertise, but are not limited to these examples. For example, the generation unit generates detailed minutes for participants with higher positions. For example, the generation unit generates minutes that include information related to the area of ​​expertise. For example, the generation unit generates optimal minutes by taking into account both the position and the area of ​​expertise. In this way, the generation unit can provide optimal information to participants by customizing the content of the minutes based on the position and the area of ​​expertise.

[0083] The providing unit can estimate the user's emotions and adjust the method of providing the minutes based on the estimated user's emotions. The providing unit, for example, uses AI to estimate the user's emotions and adjust the method of providing the minutes based on the estimated user's emotions. Specific types of providing methods and adjustment methods include, but are not limited to, email delivery and cloud sharing. For example, if the user is nervous, the providing unit provides the minutes in a simple, highly visible format. For example, if the user is relaxed, the providing unit provides the minutes in a format including detailed information. For example, if the user is in a hurry, the providing unit provides the minutes in a format that focuses on the main points. In this way, the providing unit can provide highly visible minutes by adjusting the providing method according to the user's emotions.

[0084] The providing unit can optimize the notification method for providing minutes immediately after the end of the meeting. The providing unit, for example, uses AI to optimize the notification method for providing minutes immediately after the end of the meeting. Specific types of notification methods and optimization methods include, for example, push notification and email notification, but are not limited to these examples. For example, the providing unit sends the minutes by email immediately after the end of the meeting. For example, the providing unit shares the minutes via a chat tool immediately after the end of the meeting. For example, the providing unit uploads the minutes to cloud storage immediately after the end of the meeting and shares a link. This allows the providing unit to provide the minutes immediately after the end of the meeting, enabling rapid information sharing.

[0085] The minutes providing unit can collect feedback from meeting participants and improve the method for providing minutes. The minutes providing unit, for example, uses AI to collect feedback from meeting participants and improve the method for providing minutes. Specific methods for collecting and improving feedback include, but are not limited to, questionnaire surveys and direct opinion collection. For example, the minutes providing unit collects feedback from participants after the meeting and improves the method for providing minutes. For example, the minutes providing unit adjusts the format for providing minutes based on the feedback. For example, the minutes providing unit reflects the opinions of participants and introduces the optimal method for providing minutes. In this way, the minutes providing unit improves the method for providing minutes based on the feedback from participants, enabling the optimal minutes to be provided.

[0086] The providing unit can estimate the user's emotions and adjust the timing of providing the minutes based on the estimated user's emotions. The providing unit, for example, uses AI to estimate the user's emotions and adjust the timing of providing the minutes based on the estimated user's emotions. Specific methods and standards for adjusting the timing of providing the minutes include, but are not limited to, immediately after the end of the meeting or the next day. For example, if the user is nervous, the providing unit provides the minutes immediately after the end of the meeting. For example, if the user is relaxed, the providing unit provides the minutes a short time after the end of the meeting. For example, if the user is in a hurry, the providing unit quickly provides the minutes immediately after the end of the meeting. In this way, the providing unit can provide highly visible minutes by adjusting the timing of providing the minutes according to the user's emotions.

[0087] The providing unit can provide minutes in an optimal format by taking into account device information of the meeting participants. The providing unit, for example, uses AI to provide minutes in an optimal format by taking into account device information of the meeting participants. Specific types of device information and methods of consideration include, but are not limited to, smartphones, tablets, and PCs. For example, the providing unit provides minutes in a mobile-friendly format to participants using smartphones. For example, the providing unit provides minutes in a format optimized for large screens to participants using tablets. For example, the providing unit provides minutes in a format including detailed information to participants using desktops. In this way, the providing unit can provide minutes with high visibility by providing the minutes in an optimal format based on device information.

[0088] The service provider can customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. For example, the service provider can use AI to customize the content of meeting minutes based on the job titles and areas of expertise of the meeting participants. Specific methods and criteria for customizing the content include, but are not limited to, information specific to each job title or area of ​​expertise. For example, the service provider can provide detailed minutes for participants with higher job titles. The service provider can provide minutes that focus on information relevant to each participant's area of ​​expertise. The service provider can provide optimal minutes considering both job title and area of ​​expertise. This allows the service provider to provide participants with the most relevant information by customizing the content of the meeting minutes based on their job title and area of ​​expertise. === Hard Collateral 1-1 === Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and provision unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects meeting conversation data using the microphone 38B and camera 42 of the smart device 14 and transmits it to the cloud via the communication I / F 26 of the data processing unit 12. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the conversation data using generation AI and extracts the main points of the discussion. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which generates meeting minutes based on the extracted main points. The provision unit is implemented, for example, by the control unit 46A of the smart device 14, which provides the generated meeting minutes to the participants immediately after the meeting ends. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects meeting conversation data using the microphone 238 and camera 42 of the smart glasses 214 and transmits the data to the cloud via the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the conversation data using a generation AI and extracts key points of the discussion. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates minutes based on the extracted key points. The provision unit, realized, for example, by the control unit 46A of the smart glasses 214, provides the generated minutes to participants immediately after the end of the meeting. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, generation unit, and provision unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects conference conversation data using the microphone 238 and camera 42 of the headset-type terminal 314 and transmits the data to the cloud via the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the conversation data using a generation AI and extracts key points of the discussion. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, generates minutes based on the extracted key points. The provision unit, realized, for example, by the control unit 46A of the headset-type terminal 314, provides the generated minutes to participants immediately after the end of the conference. === Hard Collateral 1-4 === Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, and provision unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects meeting conversation data using the microphone 238 and camera 42 of the robot 414 and transmits it to the cloud via the communication I / F 26 of the data processing unit 12. The analysis unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which analyzes the conversation data using generation AI and extracts the main points of the discussion. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12, which generates meeting minutes based on the extracted main points. The provision unit is implemented, for example, by the control unit 46A of the robot 414, which provides the generated meeting minutes to the participants immediately after the meeting ends.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The data collection unit can analyze the emotional tone of participants' statements in real time and adjust the priority of data to collect according to changes in emotion. For example, if a participant is agitated, the unit will prioritize collecting their statements. If a participant is calm, the unit will collect overall conversation data evenly. If a participant is expressing dissatisfaction, the unit will pay particular attention to collecting their statements. This allows the unit to efficiently collect important data by adjusting data priority according to changes in emotion.

[0091] The analysis unit can analyze the frequency of appearance of specific keywords in conversation data and extract important points based on that frequency. For example, the analysis unit can identify keywords that frequently appear in conversations and focus its analysis on statements related to those keywords. The analysis unit can also analyze the timing of appearance of specific keywords and extract important points based on that timing. The analysis unit can combine keyword frequency with context to extract more accurate key points. This allows the analysis unit to efficiently extract important points based on keyword frequency.

[0092] The generation unit can analyze the emotional tone of the speech of the meeting participants and adjust the way the minutes are expressed based on the emotion. For example, if a participant is excited, the generation unit generates minutes using expressions that reflect the emotion. For example, if a participant is calm, the generation unit generates minutes using calm expressions. For example, if a participant is dissatisfied, the generation unit generates minutes using expressions that appropriately reflect the emotion. In this way, the generation unit can provide more accurate and empathetic minutes by adjusting the way the minutes are expressed based on the emotion.

[0093] The providing unit can provide the minutes in an optimal format taking into account device information of the meeting participants. For example, the providing unit provides the minutes in a mobile-friendly format for participants using smartphones. For example, the providing unit provides the minutes in a format optimized for large screens for participants using tablets. For example, the providing unit provides the minutes in a format including detailed information for participants using desktops. In this way, the providing unit can provide minutes with high visibility by providing the minutes in an optimal format based on device information.

[0094] The collection unit can adjust the range of data to be collected based on the job titles and areas of expertise of the meeting participants. For example, the collection unit prioritizes collecting comments from participants with higher job titles. For example, the collection unit focuses on collecting comments related to areas of expertise. For example, the collection unit performs optimal data collection by taking into account both job titles and areas of expertise. This allows the collection unit to efficiently collect important data by adjusting the range of data based on job titles and areas of expertise.

[0095] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user's emotions. For example, if the user is nervous, the analysis unit applies an algorithm that prioritizes analysis of important points. For example, if the user is relaxed, the analysis unit applies an algorithm that analyzes the entire conversation data evenly. For example, if the user is in a hurry, the analysis unit applies an algorithm that quickly analyzes the main points. In this way, the analysis unit can efficiently analyze important points by adjusting the analysis algorithm according to the user's emotions.

[0096] The generation unit can apply a different summarization algorithm to each agenda item of the meeting to generate a summary that accurately reflects the speaker's intention. For example, the generation unit selects the optimal summarization algorithm for each agenda item to generate a summary. The generation unit applies a different summarization method depending on, for example, the content of the agenda item. The generation unit applies a different algorithm to each agenda item to generate a summary that accurately reflects the speaker's intention. In this way, the generation unit can generate a summary that accurately reflects the speaker's intention by applying the optimal summarization algorithm to each agenda item.

[0097] The providing unit can estimate the user's emotions and adjust the method of providing the minutes based on the estimated user's emotions. For example, if the user is nervous, the providing unit provides the minutes in a simple, highly visible format. For example, if the user is relaxed, the providing unit provides the minutes in a format including detailed information. For example, if the user is in a hurry, the providing unit provides the minutes in a format that focuses on the main points. In this way, the providing unit can provide highly visible minutes by adjusting the method of providing them according to the user's emotions.

[0098] The collection unit can focus on collecting conversation data related to a specific agenda item according to the progress of the meeting. For example, when an agenda item is changed, the collection unit focuses on collecting conversation data related to that agenda item. For example, the collection unit prioritizes collecting data related to important agenda items according to the progress of the meeting. For example, the collection unit collects data related to specific agenda items in real time according to the progress of the meeting. In this way, the collection unit can efficiently collect information related to important agenda items by collecting data according to the progress of the meeting.

[0099] The analysis unit analyzes the voice tone and speed of the conversation data, and can grasp the intention of the utterance more accurately. For example, the analysis unit analyzes the voice tone to grasp the emotion of the utterance. For example, the analysis unit analyzes the speed of the utterance to determine the urgency and importance. For example, the analysis unit analyzes both the voice tone and speed to grasp the intention of the utterance. In this way, the analysis unit can accurately grasp the intention of the utterance by analyzing the voice tone and speed.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The collection unit collects meeting conversation data. The meeting conversation data includes, for example, audio data and text data. The collection unit transmits the meeting conversation data to the cloud in real time. For example, if an online meeting tool such as Zoom is used, the conversation data is automatically uploaded to the cloud. Step 2: The analysis unit uses the generation AI to analyze the conversation data collected by the collection unit and extract the key points of the discussion. The analysis unit understands the content of the conversation and accurately grasps the important points and intentions of the remarks. The generation AI analyzes the conversation data using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The generation unit uses AI to generate minutes based on the key points extracted by the analysis unit. The generation unit generates a summary that accurately reflects the speaker's intentions. Step 4: The providing unit provides the minutes generated by the generating unit. The providing unit provides the minutes to the participants immediately after the end of the meeting. For example, the minutes are sent by email immediately after the end of the meeting.

[0102] 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.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] 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.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0117] 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.

[0118] 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.

[0119] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] 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.

[0134] 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.

[0135] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

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

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

[0149] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

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

[0151] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] 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.

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

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects conversation data of the meeting; an analysis unit that analyzes the conversation data collected by the collection unit and extracts key points of the discussion; a generation unit that generates minutes based on the key points extracted by the analysis unit; a providing unit that provides the minutes generated by the generating unit; Equipped with A system characterized by:

2. The collecting unit Sending meeting conversation data to the cloud in real time 2. The system of claim 1.

3. The analysis unit Understand the content of the conversation and accurately grasp the key points and intentions of what is being said 2. The system of claim 1.

4. The generation unit Generate summaries that accurately reflect the speaker's intentions 2. The system of claim 1.

5. The providing unit Providing minutes to participants immediately after the meeting 2. The system of claim 1.

6. The collecting unit The system estimates the user's emotions and adjusts the timing of conversation data collection based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit Prioritize data collection based on how often and what meeting participants say 2. The system of claim 1.

8. The collecting unit Focus on collecting conversation data on specific topics as the meeting progresses 2. The system of claim 1.

Images