system

Abstract

The system according to this embodiment aims to record the contents of a meeting in real time, extract important statements and discussions, and generate and share summaries and action items. [Solution] The system according to the embodiment comprises a recording unit, an analysis unit, a generation unit, and a sharing unit. The recording unit records the audio data of the meeting in real time. The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The sharing unit shares the summary and action items generated by the generation unit with the members after the meeting.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is laborious to accurately record the content of a meeting, extract important remarks and discussions, and generate summaries and action items, and there is room for improvement in terms of improving the productivity of meetings.

[0005] The system according to the embodiment aims to record the content of a meeting in real time, extract important remarks and discussions, and generate and share summaries and action items.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, and a sharing unit. The recording unit records the audio data of the meeting in real time. The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The sharing unit shares the summary and action items generated by the generation unit with the members after the meeting. [Effects of the Invention]

[0007] The system according to this embodiment can record the contents of a meeting in real time, extract important statements and discussions, and generate and share summaries and action items. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The meeting recording agent system according to an embodiment of the present invention is a system that records meeting content in real time and automatically generates summaries and action items. This system records meeting audio data in real time, and a generating AI analyzes the recorded audio data to extract important statements and discussions. Furthermore, based on the extracted information, the generating AI automatically generates a meeting summary and action items, and shares the generated summary and action items with the members after the meeting. This mechanism improves meeting productivity and prevents important discussions and action items from being overlooked. For example, the meeting audio data is recorded in real time. At this time, it is important to accurately record what all participants in the meeting say. For example, the content spoken during the meeting is recorded word for word so that it can be analyzed later. Next, the generating AI analyzes the recorded audio data. The generating AI converts the audio data into text and extracts important statements and discussions. For example, it identifies important points and decisions discussed in the meeting and summarizes them. Furthermore, based on the extracted information, the generating AI automatically generates a meeting summary and action items. The generating AI organizes the extracted information and creates a meeting summary. Furthermore, specific action items decided upon during the meeting are listed as action items. Finally, the generated summary and action items are shared with members after the meeting. This ensures that all meeting participants understand the meeting's content and can move on to the next step. For example, sharing the summary and action items immediately after the meeting enables quick action. This mechanism improves meeting productivity. Even if the meeting is lengthy, important discussions and action items are not overlooked and are managed efficiently. In addition, rapid sharing after the meeting improves transparency and traceability. For example, by immediately sharing the meeting summary and action items, all participants have the same information and can move on to the next step. In this way, the meeting recording agent system can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0029] The meeting recording agent system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, and a sharing unit. The recording unit records the audio data of the meeting in real time. The recording unit, for example, records the content of what is said during the meeting so that it can be analyzed later. It is important for the recording unit to accurately record what all participants in the meeting say. The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The analysis unit, for example, converts the audio data into text and extracts important statements and discussions. The analysis unit uses generation AI to convert the audio data into text and extract important statements and discussions. The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The generation unit, for example, organizes the extracted information and creates a meeting summary. The generation unit uses generation AI to organize the extracted information and create a meeting summary. The generation unit lists the specific action items decided at the meeting as action items. The generation unit uses generation AI to list the specific action items decided at the meeting as action items. The sharing unit shares the summaries and action items generated by the generation unit with the members after the meeting. For example, the sharing unit shares the generated summaries and action items with the members after the meeting. The sharing unit uses generation AI to share the generated summaries and action items with the members after the meeting. As a result, the meeting recording agent system according to this embodiment can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0030] The recording unit records the meeting's audio data in real time. For example, it records every word spoken during the meeting so that it can be analyzed later. It is crucial for the recording unit to accurately record the words of all meeting participants. Specifically, the recording unit uses high-sensitivity microphones to clearly capture all speech in the meeting room. This ensures that speakers' voices are clearly recorded, enabling accurate text conversion during later analysis. Furthermore, the recording unit incorporates noise cancellation technology to improve the quality of the audio data by removing background noise and echoes. The recording unit digitizes the audio data in real time and saves it with a timestamp. This allows for accurate tracking of the order and timing of speeches. In addition, the recording unit can record multiple audio channels simultaneously, allowing for individual analysis of each speech even when multiple speeches overlap. The recording unit securely stores the audio data using cloud storage and makes it accessible as needed. This makes it easy to store and share data even after the meeting has ended. Furthermore, the recording unit has an encryption function for the audio data to ensure data confidentiality. This minimizes the risk of meeting content being leaked externally. The recording unit allows users to easily start and stop recording and manage audio data through the user interface. This enables users to intuitively operate the system and efficiently record meetings.

[0031] The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. For example, the analysis unit converts the audio data into text and extracts important statements and discussions. The analysis unit uses generative AI to convert the audio data into text and extract important statements and discussions. Specifically, the analysis unit uses speech recognition technology to convert the audio data into text with high accuracy. The generative AI uses a speech recognition model to accurately transcribe the content of statements into text and also identifies the speaker. This makes it possible to clearly record who said what. Furthermore, the analysis unit uses natural language processing technology to extract important keywords and phrases from the text data. The generative AI understands the context of the meeting and the flow of the discussion and automatically identifies important statements and discussions. For example, it can extract discussions on specific topics, decisions, action items, etc. The analysis unit organizes the extracted information and uses it to help create meeting summaries and minutes. Furthermore, the analysis unit can also refer to past meeting data and external information sources to provide background and relevant information on the discussions. This allows for a deeper understanding of the meeting content and supports effective decision-making. The analysis unit visually displays the analysis results through a user interface, allowing users to easily identify important information. This enables users to quickly grasp the key points of a meeting and move on to the next step.

[0032] The generation unit generates meeting summaries and action items based on the information extracted by the analysis unit. For example, the generation unit organizes the extracted information and creates a meeting summary. The generation unit uses generation AI to organize the extracted information and create a meeting summary. The generation unit lists the specific action items decided at the meeting as action items. The generation unit uses generation AI to list the specific action items decided at the meeting as action items. Specifically, the generation unit automatically creates a meeting summary based on important statements and discussion information provided by the analysis unit. The generation AI uses natural language generation technology to organize the extracted information and create a summary in an easy-to-understand format. For example, it concisely summarizes the main topics, points of discussion, and decisions made at the meeting. The generation unit also lists the specific action items decided at the meeting as action items and adds detailed information such as the person in charge and the deadline. The generation AI understands the content of statements and context and automatically extracts important action items. This makes post-meeting follow-up easier and enables efficient project management. The generation unit allows users to review and edit generated summaries and action items through a user interface. This enables users to modify content as needed and share accurate information. Furthermore, the generation unit supports meeting progress by referencing past meeting data and presenting similar discussions and action items. This improves meeting productivity and prevents important discussions and action items from being overlooked.

[0033] The sharing department shares the summaries and action items generated by the generation department with members after the meeting. Specifically, the sharing department quickly distributes the meeting summaries and action items created by the generation department to all meeting participants. The sharing department uses generation AI to share the generated summaries and action items with members after the meeting. The sharing department shares information using various communication methods, such as email, chat tools, and project management tools. The generation AI provides information in an appropriate format according to each member's role and interests. For example, it highlights the overall progress for project managers and specific action items for team members. The sharing department also monitors information distribution and sends reminders to members who haven't read the information. This ensures that important information reaches everyone and thorough follow-up after the meeting. Furthermore, the sharing department uses cloud storage to securely store the generated summaries and action items, making them accessible at any time. This allows for easy reference of past meeting records and quick retrieval of necessary information. The sharing section allows users to check the status of information sharing and feedback through the user interface. This allows users to understand how information has been received and provide additional explanations or follow-ups as needed. The sharing section can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0034] The analysis unit can convert audio data into text and extract important statements and discussions. For example, the analysis unit converts audio data into text and extracts important statements and discussions. The analysis unit uses generative AI to convert audio data into text and extract important statements and discussions. For example, the analysis unit uses speech recognition technology to convert audio data into text. The analysis unit uses generative AI to convert audio data into text and extract important statements and discussions. This improves the accuracy of meeting content summaries by converting audio data into text and extracting important statements and discussions.

[0035] The generation unit can organize the extracted information and create a meeting summary. For example, the generation unit organizes the extracted information and creates a meeting summary. The generation unit uses generational AI to organize the extracted information and create a meeting summary. For example, the generation unit organizes information based on information classification methods and prioritization. The generation unit uses generational AI to organize the extracted information and create a meeting summary. This deepens the understanding of the meeting content by organizing the extracted information and creating a meeting summary.

[0036] The generation unit can list specific action items decided at a meeting as action items. For example, the generation unit lists specific action items decided at a meeting as action items. The generation unit uses generation AI to list specific action items decided at a meeting as action items. For example, the generation unit lists action items based on feasible tasks and deadlines. The generation unit uses generation AI to list specific action items decided at a meeting as action items. By listing the specific action items decided at a meeting, the actions to be taken after the meeting become clear.

[0037] The sharing department can share the generated summaries and action items with members after the meeting. For example, the sharing department shares the generated summaries and action items with members after the meeting. The sharing department uses generative AI to share the generated summaries and action items with members after the meeting. For example, the sharing department shares the summaries and action items via email or chat tools. The sharing department uses generative AI to share the generated summaries and action items with members after the meeting. This improves meeting transparency and traceability by sharing the generated summaries and action items after the meeting.

[0038] The shared section can notify users of generated summaries and action items. For example, the shared section notifies users of generated summaries and action items. The shared section uses generational AI to notify users of generated summaries and action items. For example, the shared section notifies users of summaries and action items via email or push notifications. The shared section uses generational AI to notify users of generated summaries and action items. This enables quick responses after meetings by notifying users of generated summaries and action items.

[0039] The recording function can automatically highlight important statements as the meeting progresses. For example, it can highlight the moment the meeting agenda is changed. It can automatically highlight the moment important decisions are made. It can highlight the parts that speakers want to emphasize. This makes it easy to find important parts later by highlighting key statements.

[0040] The recording unit can analyze the speaker's voice characteristics during recording and apply different audio filters to each speaker. For example, if a speaker's voice is quiet, the recording unit will automatically apply a filter to increase the volume. If a speaker's voice is high-pitched, the recording unit will apply a filter to adjust the sound for easier listening. If a speaker's voice contains noise, the recording unit will apply a filter to remove the noise. By applying audio filters to each speaker, the content of their speech becomes easier to understand.

[0041] The recording unit can perform noise cancellation during recording, taking into account the meeting location and ambient noise. For example, the recording unit can perform noise cancellation to remove the sound of the air conditioner in a meeting room. The recording unit can perform noise cancellation to remove background noise in online meetings. The recording unit can perform noise cancellation to remove wind noise in outdoor meetings. By performing noise cancellation while considering the meeting location and ambient noise, the quality of the audio data is improved.

[0042] The recording unit can tag the content of a meeting's statements by referencing the profile information of the meeting participants during recording. For example, the recording unit can tag statements based on the speaker's job title, their area of ​​expertise, or their past speaking history. This makes it easier to categorize the content of a meeting by referencing the profile information of the meeting participants when tagging the statements.

[0043] The analysis unit can extract important statements by considering the context of the speech during the analysis of audio data. For example, the analysis unit analyzes the context before and after a statement to identify important statements. The analysis unit extracts emphasized parts of the speech. The analysis unit extracts points that are repeatedly mentioned in the speech as important statements. As a result, by extracting important statements while considering the context of the speech, the accuracy of summarizing the meeting content is improved.

[0044] The analysis unit can evaluate importance by referring to the speaker's past statement history during analysis. For example, the analysis unit evaluates importance based on how often the speaker has made important statements in the past. The analysis unit evaluates the importance of the current statement by referring to the content of the speaker's past statements. The analysis unit evaluates the importance of statements on a specific topic from the speaker's past statement history. In this way, important statements can be accurately extracted by evaluating importance by referring to the speaker's past statement history.

[0045] The analysis unit can switch analysis algorithms based on the meeting's theme and agenda during analysis. For example, in the case of a technical agenda, the analysis unit applies an analysis algorithm that emphasizes technical terms. In the case of a management agenda, the analysis unit applies an analysis algorithm that emphasizes statements related to decision-making. In the case of a project progress report, the analysis unit applies an analysis algorithm that emphasizes statements related to progress. By switching analysis algorithms based on the meeting's theme and agenda, the accuracy of the analysis is improved.

[0046] The analysis unit can classify the content of a meeting's statements by considering the participants' areas of expertise during the analysis process. For example, the analysis unit can classify a technical speaker's statements as technical content, a manager's statements as business-related content, and a project manager's statements as content related to progress management. By classifying the content of a meeting's statements by considering the participants' areas of expertise, the accuracy of the statement classification is improved.

[0047] The generation unit can adjust the level of detail in the summary based on the importance of the meeting. For example, it generates a detailed summary for important meetings, a concise summary of key points for regular meetings, and a brief summary for urgent meetings to allow for quick response. By adjusting the level of detail in the summary based on the importance of the meeting, it is possible to gain a detailed understanding of the content of important meetings.

[0048] The generation unit can apply different summarization algorithms depending on the meeting category when generating summaries. For example, in the case of a technical meeting, the generation unit applies a summarization algorithm that emphasizes technical content. In the case of a management meeting, the generation unit applies a summarization algorithm that emphasizes content related to decision-making. In the case of a project meeting, the generation unit applies a summarization algorithm that emphasizes content related to progress. By applying different summarization algorithms according to the meeting category, the most suitable summary for each category is generated.

[0049] The generation unit can determine the priority of summaries based on the progress of the meeting. For example, if important statements were made at the beginning of the meeting, the generation unit will prioritize summarizing those parts. If important decisions were made towards the end of the meeting, the generation unit will prioritize summarizing those parts. If the discussion became heated in the middle of the meeting, the generation unit will prioritize summarizing those parts. In this way, by determining the priority of summaries based on the progress of the meeting, the generation unit can prioritize summarizing the important parts.

[0050] The generation unit can improve the accuracy of the summary by referring to relevant meeting materials during summary generation. For example, the generation unit can improve the accuracy of the summary by referring to the meeting minutes. The generation unit can improve the accuracy of the summary by referring to the meeting presentation materials. The generation unit can improve the accuracy of the summary by referring to notes provided by meeting participants. As a result, a more accurate summary is generated by improving the accuracy of the summary by referring to relevant meeting materials.

[0051] The sharing function can provide customized summaries and action items for each meeting participant during the sharing process. For example, the sharing function can provide relevant summaries and action items based on the participant's job title, their area of ​​expertise, or their past speaking history. This ensures that each participant receives the most relevant information by providing customized summaries and action items for each meeting participant.

[0052] The shared department can prioritize notifications based on the importance of the meeting when sharing information. For example, the shared department will immediately notify users of important meetings. For regular meetings, the shared department will maintain the normal notification schedule. For emergency meetings, the shared department will immediately notify users so that they can respond quickly. This ensures that important information is shared quickly by prioritizing notifications based on the importance of the meeting.

[0053] The sharing function can share information in the most optimal format, taking into account the device information of meeting participants. For example, if a participant is using a smartphone, the sharing function provides a display method that matches the screen size. If a participant is using a tablet, the sharing function provides a display method optimized for larger screens. If a participant is using a smartwatch, the sharing function provides a concise and highly visible display method. In this way, by sharing information in the most optimal format, taking into account the device information of meeting participants, information optimized for each device is provided.

[0054] The sharing function can improve the accuracy of sharing by attaching relevant meeting materials during the sharing process. For example, it can improve the accuracy of sharing by attaching meeting minutes, meeting presentation materials, or notes provided by meeting participants. By attaching relevant meeting materials, more accurate information is shared.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The recording unit can analyze the tone and speed of speakers' voices when recording meeting audio data, and estimate the importance of what is said. For example, it can mark parts that a speaker emphasizes as important statements. Also, if a speaker speaks quickly, that part can be recorded as an important discussion. Furthermore, if a speaker speaks slowly, that part can be recorded as a detailed explanation. In this way, by estimating importance based on the tone and speed of speech, the content of the meeting can be understood more accurately.

[0057] The generation unit can adjust the format of the meeting summary according to the progress of the meeting. For example, at the beginning of the meeting, it can provide a concise summary of the agenda. In the middle of the meeting, it can generate a more detailed summary according to the progress of the discussion. Towards the end of the meeting, it can focus on summarizing decisions and action items. By adjusting the format of the summary according to the progress of the meeting, the content of the meeting can be effectively communicated.

[0058] The recording unit can classify the content of a meeting's audio data by referring to the speaker's background information. For example, it can classify the content of a meeting based on the speaker's job title, their area of ​​expertise, or their past speaking history. By classifying the content of a meeting based on the speaker's background information, the meeting's content can be organized more systematically.

[0059] The generation unit can apply different summarization algorithms depending on the meeting category when generating meeting summaries. For example, in the case of a technical meeting, a summarization algorithm that emphasizes technical content can be applied. In the case of a management meeting, a summarization algorithm that emphasizes decision-making content can be applied. In the case of a project meeting, a summarization algorithm that emphasizes progress status can be applied. By applying different summarization algorithms according to the meeting category, the system can generate summaries that are optimal for each category.

[0060] The recording unit can analyze the voice characteristics of speakers when recording meeting audio data and apply different audio filters to each speaker. For example, if a speaker's voice is quiet, a filter can be applied to automatically increase the volume. If a speaker's voice is high-pitched, a filter can be applied to adjust the sound to make it easier to hear. If a speaker's voice contains noise, a filter can be applied to remove the noise. By applying audio filters to each speaker, the content of their speech can be made easier to understand.

[0061] The analysis unit can extract important statements by considering the context of the statements when analyzing meeting audio data. For example, it can identify important statements by analyzing the context before and after a statement. It can extract emphasized parts of a statement. It can extract points that are repeatedly mentioned in a statement as important statements. In this way, by extracting important statements while considering the context of the statements, the accuracy of summarizing the meeting content can be improved.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The recording unit records the meeting audio data in real time. The recording unit records everything said during the meeting so that it can be analyzed later. It is important for the recording unit to accurately record what all participants in the meeting say. Step 2: The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The analysis unit converts the audio data into text and uses a generation AI to extract important statements and discussions. Step 3: The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The generation unit organizes the extracted information, uses generation AI to create a meeting summary, and lists the specific actions decided at the meeting as action items. Step 4: The sharing team shares the summaries and action items generated by the generation team with the members after the meeting. The sharing team shares the summaries and action items generated using the generation AI with the members after the meeting.

[0064] (Example of form 2) The meeting recording agent system according to an embodiment of the present invention is a system that records meeting content in real time and automatically generates summaries and action items. This system records meeting audio data in real time, and a generating AI analyzes the recorded audio data to extract important statements and discussions. Furthermore, based on the extracted information, the generating AI automatically generates a meeting summary and action items, and shares the generated summary and action items with the members after the meeting. This mechanism improves meeting productivity and prevents important discussions and action items from being overlooked. For example, the meeting audio data is recorded in real time. At this time, it is important to accurately record what all participants in the meeting say. For example, the content spoken during the meeting is recorded word for word so that it can be analyzed later. Next, the generating AI analyzes the recorded audio data. The generating AI converts the audio data into text and extracts important statements and discussions. For example, it identifies important points and decisions discussed in the meeting and summarizes them. Furthermore, based on the extracted information, the generating AI automatically generates a meeting summary and action items. The generating AI organizes the extracted information and creates a meeting summary. Furthermore, specific action items decided upon during the meeting are listed as action items. Finally, the generated summary and action items are shared with members after the meeting. This ensures that all meeting participants understand the meeting's content and can move on to the next step. For example, sharing the summary and action items immediately after the meeting enables quick action. This mechanism improves meeting productivity. Even if the meeting is lengthy, important discussions and action items are not overlooked and are managed efficiently. In addition, rapid sharing after the meeting improves transparency and traceability. For example, by immediately sharing the meeting summary and action items, all participants have the same information and can move on to the next step. In this way, the meeting recording agent system can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0065] The meeting recording agent system according to this embodiment comprises a recording unit, an analysis unit, a generation unit, and a sharing unit. The recording unit records the audio data of the meeting in real time. The recording unit, for example, records the content of what is said during the meeting so that it can be analyzed later. It is important for the recording unit to accurately record what all participants in the meeting say. The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The analysis unit, for example, converts the audio data into text and extracts important statements and discussions. The analysis unit uses generation AI to convert the audio data into text and extract important statements and discussions. The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The generation unit, for example, organizes the extracted information and creates a meeting summary. The generation unit uses generation AI to organize the extracted information and create a meeting summary. The generation unit lists the specific action items decided at the meeting as action items. The generation unit uses generation AI to list the specific action items decided at the meeting as action items. The sharing unit shares the summaries and action items generated by the generation unit with the members after the meeting. For example, the sharing unit shares the generated summaries and action items with the members after the meeting. The sharing unit uses generation AI to share the generated summaries and action items with the members after the meeting. As a result, the meeting recording agent system according to this embodiment can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0066] The recording unit records the meeting's audio data in real time. For example, it records every word spoken during the meeting so that it can be analyzed later. It is crucial for the recording unit to accurately record the words of all meeting participants. Specifically, the recording unit uses high-sensitivity microphones to clearly capture all speech in the meeting room. This ensures that speakers' voices are clearly recorded, enabling accurate text conversion during later analysis. Furthermore, the recording unit incorporates noise cancellation technology to improve the quality of the audio data by removing background noise and echoes. The recording unit digitizes the audio data in real time and saves it with a timestamp. This allows for accurate tracking of the order and timing of speeches. In addition, the recording unit can record multiple audio channels simultaneously, allowing for individual analysis of each speech even when multiple speeches overlap. The recording unit securely stores the audio data using cloud storage and makes it accessible as needed. This makes it easy to store and share data even after the meeting has ended. Furthermore, the recording unit has an encryption function for the audio data to ensure data confidentiality. This minimizes the risk of meeting content being leaked externally. The recording unit allows users to easily start and stop recording and manage audio data through the user interface. This enables users to intuitively operate the system and efficiently record meetings.

[0067] The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. For example, the analysis unit converts the audio data into text and extracts important statements and discussions. The analysis unit uses generative AI to convert the audio data into text and extract important statements and discussions. Specifically, the analysis unit uses speech recognition technology to convert the audio data into text with high accuracy. The generative AI uses a speech recognition model to accurately transcribe the content of statements into text and also identifies the speaker. This makes it possible to clearly record who said what. Furthermore, the analysis unit uses natural language processing technology to extract important keywords and phrases from the text data. The generative AI understands the context of the meeting and the flow of the discussion and automatically identifies important statements and discussions. For example, it can extract discussions on specific topics, decisions, action items, etc. The analysis unit organizes the extracted information and uses it to help create meeting summaries and minutes. Furthermore, the analysis unit can also refer to past meeting data and external information sources to provide background and relevant information on the discussions. This allows for a deeper understanding of the meeting content and supports effective decision-making. The analysis unit visually displays the analysis results through a user interface, allowing users to easily identify important information. This enables users to quickly grasp the key points of a meeting and move on to the next step.

[0068] The generation unit generates meeting summaries and action items based on the information extracted by the analysis unit. For example, the generation unit organizes the extracted information and creates a meeting summary. The generation unit uses generation AI to organize the extracted information and create a meeting summary. The generation unit lists the specific action items decided at the meeting as action items. The generation unit uses generation AI to list the specific action items decided at the meeting as action items. Specifically, the generation unit automatically creates a meeting summary based on important statements and discussion information provided by the analysis unit. The generation AI uses natural language generation technology to organize the extracted information and create a summary in an easy-to-understand format. For example, it concisely summarizes the main topics, points of discussion, and decisions made at the meeting. The generation unit also lists the specific action items decided at the meeting as action items and adds detailed information such as the person in charge and the deadline. The generation AI understands the content of statements and context and automatically extracts important action items. This makes post-meeting follow-up easier and enables efficient project management. The generation unit allows users to review and edit generated summaries and action items through a user interface. This enables users to modify content as needed and share accurate information. Furthermore, the generation unit supports meeting progress by referencing past meeting data and presenting similar discussions and action items. This improves meeting productivity and prevents important discussions and action items from being overlooked.

[0069] The sharing department shares the summaries and action items generated by the generation department with members after the meeting. Specifically, the sharing department quickly distributes the meeting summaries and action items created by the generation department to all meeting participants. The sharing department uses generation AI to share the generated summaries and action items with members after the meeting. The sharing department shares information using various communication methods, such as email, chat tools, and project management tools. The generation AI provides information in an appropriate format according to each member's role and interests. For example, it highlights the overall progress for project managers and specific action items for team members. The sharing department also monitors information distribution and sends reminders to members who haven't read the information. This ensures that important information reaches everyone and thorough follow-up after the meeting. Furthermore, the sharing department uses cloud storage to securely store the generated summaries and action items, making them accessible at any time. This allows for easy reference of past meeting records and quick retrieval of necessary information. The sharing section allows users to check the status of information sharing and feedback through the user interface. This allows users to understand how information has been received and provide additional explanations or follow-ups as needed. The sharing section can improve meeting productivity and prevent important discussions and action items from being overlooked.

[0070] The analysis unit can convert audio data into text and extract important statements and discussions. For example, the analysis unit converts audio data into text and extracts important statements and discussions. The analysis unit uses generative AI to convert audio data into text and extract important statements and discussions. For example, the analysis unit uses speech recognition technology to convert audio data into text. The analysis unit uses generative AI to convert audio data into text and extract important statements and discussions. This improves the accuracy of meeting content summaries by converting audio data into text and extracting important statements and discussions.

[0071] The generation unit can organize the extracted information and create a meeting summary. For example, the generation unit organizes the extracted information and creates a meeting summary. The generation unit uses generational AI to organize the extracted information and create a meeting summary. For example, the generation unit organizes information based on information classification methods and prioritization. The generation unit uses generational AI to organize the extracted information and create a meeting summary. This deepens the understanding of the meeting content by organizing the extracted information and creating a meeting summary.

[0072] The generation unit can list specific action items decided at a meeting as action items. For example, the generation unit lists specific action items decided at a meeting as action items. The generation unit uses generation AI to list specific action items decided at a meeting as action items. For example, the generation unit lists action items based on feasible tasks and deadlines. The generation unit uses generation AI to list specific action items decided at a meeting as action items. By listing the specific action items decided at a meeting, the actions to be taken after the meeting become clear.

[0073] The sharing department can share the generated summaries and action items with members after the meeting. For example, the sharing department shares the generated summaries and action items with members after the meeting. The sharing department uses generative AI to share the generated summaries and action items with members after the meeting. For example, the sharing department shares the summaries and action items via email or chat tools. The sharing department uses generative AI to share the generated summaries and action items with members after the meeting. This improves meeting transparency and traceability by sharing the generated summaries and action items after the meeting.

[0074] The shared section can notify users of generated summaries and action items. For example, the shared section notifies users of generated summaries and action items. The shared section uses generational AI to notify users of generated summaries and action items. For example, the shared section notifies users of summaries and action items via email or push notifications. The shared section uses generational AI to notify users of generated summaries and action items. This enables quick responses after meetings by notifying users of generated summaries and action items.

[0075] The recording unit can estimate the user's emotions and adjust the timing of audio data recording based on the estimated emotions. For example, if the user is nervous, the recording unit will delay recording until the user is relaxed. If the user is excited, the recording unit will immediately start recording because important statements are more likely to be made. If the user is tired, the recording unit will delay recording until the user has taken a break. By adjusting the timing of audio data recording based on the user's emotions, important statements can be captured without being missed. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0076] The recording function can automatically highlight important statements as the meeting progresses. For example, it can highlight the moment the meeting agenda is changed. It can automatically highlight the moment important decisions are made. It can highlight the parts that speakers want to emphasize. This makes it easy to find important parts later by highlighting key statements.

[0077] The recording unit can analyze the speaker's voice characteristics during recording and apply different audio filters to each speaker. For example, if a speaker's voice is quiet, the recording unit will automatically apply a filter to increase the volume. If a speaker's voice is high-pitched, the recording unit will apply a filter to adjust the sound for easier listening. If a speaker's voice contains noise, the recording unit will apply a filter to remove the noise. By applying audio filters to each speaker, the content of their speech becomes easier to understand.

[0078] The recording unit can estimate the user's emotions and determine the priority of audio data to record based on the estimated emotions. For example, if the user is excited, the recording unit will prioritize recording their statements. If the user is relaxed, the recording unit will maintain the normal recording order. If the user is tired, the recording unit will postpone less important statements. This allows important statements to be recorded preferentially by prioritizing audio data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0079] The recording unit can perform noise cancellation during recording, taking into account the meeting location and ambient noise. For example, the recording unit can perform noise cancellation to remove the sound of the air conditioner in a meeting room. The recording unit can perform noise cancellation to remove background noise in online meetings. The recording unit can perform noise cancellation to remove wind noise in outdoor meetings. By performing noise cancellation while considering the meeting location and ambient noise, the quality of the audio data is improved.

[0080] The recording unit can tag the content of a meeting's statements by referencing the profile information of the meeting participants during recording. For example, the recording unit can tag statements based on the speaker's job title, their area of ​​expertise, or their past speaking history. This makes it easier to categorize the content of a meeting by referencing the profile information of the meeting participants when tagging the statements.

[0081] The analysis unit can estimate the user's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the user is nervous, the analysis unit will analyze important statements more rigorously. If the user is relaxed, the analysis unit will maintain normal analysis accuracy. If the user is excited, the analysis unit will prioritize the nuances of the statements. This allows for the accurate extraction of important statements and discussions by adjusting the accuracy of the analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0082] The analysis unit can extract important statements by considering the context of the speech during the analysis of audio data. For example, the analysis unit analyzes the context before and after a statement to identify important statements. The analysis unit extracts emphasized parts of the speech. The analysis unit extracts points that are repeatedly mentioned in the speech as important statements. As a result, by extracting important statements while considering the context of the speech, the accuracy of summarizing the meeting content is improved.

[0083] The analysis unit can evaluate importance by referring to the speaker's past statement history during analysis. For example, the analysis unit evaluates importance based on how often the speaker has made important statements in the past. The analysis unit evaluates the importance of the current statement by referring to the content of the speaker's past statements. The analysis unit evaluates the importance of statements on a specific topic from the speaker's past statement history. In this way, important statements can be accurately extracted by evaluating importance by referring to the speaker's past statement history.

[0084] 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, if the user is tense, the analysis unit provides a simple and highly visible display method. If the user is relaxed, the analysis unit provides a display method that includes detailed information. If the user is excited, the analysis unit provides a visually stimulating display method. By adjusting the display method of the analysis results based on the user's emotions, it becomes possible to provide a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0085] The analysis unit can switch analysis algorithms based on the meeting's theme and agenda during analysis. For example, in the case of a technical agenda, the analysis unit applies an analysis algorithm that emphasizes technical terms. In the case of a management agenda, the analysis unit applies an analysis algorithm that emphasizes statements related to decision-making. In the case of a project progress report, the analysis unit applies an analysis algorithm that emphasizes statements related to progress. By switching analysis algorithms based on the meeting's theme and agenda, the accuracy of the analysis is improved.

[0086] The analysis unit can classify the content of a meeting's statements by considering the participants' areas of expertise during the analysis process. For example, the analysis unit can classify a technical speaker's statements as technical content, a manager's statements as business-related content, and a project manager's statements as content related to progress management. By classifying the content of a meeting's statements by considering the participants' areas of expertise, the accuracy of the statement classification is improved.

[0087] The generation unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is tense, the generation unit will generate a simple, to-the-point summary. If the user is relaxed, the generation unit will generate a summary that includes detailed information. If the user is excited, the generation unit will generate a visually stimulating summary. By adjusting the way the summary is presented based on the user's emotions, a summary that is easy for the user to understand is generated. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0088] The generation unit can adjust the level of detail in the summary based on the importance of the meeting. For example, it generates a detailed summary for important meetings, a concise summary of key points for regular meetings, and a brief summary for urgent meetings to allow for quick response. By adjusting the level of detail in the summary based on the importance of the meeting, it is possible to gain a detailed understanding of the content of important meetings.

[0089] The generation unit can apply different summarization algorithms depending on the meeting category when generating summaries. For example, in the case of a technical meeting, the generation unit applies a summarization algorithm that emphasizes technical content. In the case of a management meeting, the generation unit applies a summarization algorithm that emphasizes content related to decision-making. In the case of a project meeting, the generation unit applies a summarization algorithm that emphasizes content related to progress. By applying different summarization algorithms according to the meeting category, the most suitable summary for each category is generated.

[0090] The generation unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is in a hurry, the generation unit will generate a short, concise summary. If the user is relaxed, the generation unit will generate a longer summary with detailed explanations. If the user is excited, the generation unit will generate a visually stimulating summary. By adjusting the length of the summary based on the user's emotions, an appropriate summary is generated that is relevant to the user's situation. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The generation unit can determine the priority of summaries based on the progress of the meeting. For example, if important statements were made at the beginning of the meeting, the generation unit will prioritize summarizing those parts. If important decisions were made towards the end of the meeting, the generation unit will prioritize summarizing those parts. If the discussion became heated in the middle of the meeting, the generation unit will prioritize summarizing those parts. In this way, by determining the priority of summaries based on the progress of the meeting, the generation unit can prioritize summarizing the important parts.

[0092] The generation unit can improve the accuracy of the summary by referring to relevant meeting materials during summary generation. For example, the generation unit can improve the accuracy of the summary by referring to the meeting minutes. The generation unit can improve the accuracy of the summary by referring to the meeting presentation materials. The generation unit can improve the accuracy of the summary by referring to notes provided by meeting participants. As a result, a more accurate summary is generated by improving the accuracy of the summary by referring to relevant meeting materials.

[0093] The sharing function can estimate the user's emotions and adjust the timing of sharing based on those emotions. For example, if the user is tense, the sharing function will delay sharing until the user is relaxed. If the user is excited, the sharing function will share immediately. If the user is tired, the sharing function will share after a break. This allows information to be shared at the appropriate time by adjusting the timing of sharing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The sharing function can provide customized summaries and action items for each meeting participant during the sharing process. For example, the sharing function can provide relevant summaries and action items based on the participant's job title, their area of ​​expertise, or their past speaking history. This ensures that each participant receives the most relevant information by providing customized summaries and action items for each meeting participant.

[0095] The shared department can prioritize notifications based on the importance of the meeting when sharing information. For example, the shared department will immediately notify users of important meetings. For regular meetings, the shared department will maintain the normal notification schedule. For emergency meetings, the shared department will immediately notify users so that they can respond quickly. This ensures that important information is shared quickly by prioritizing notifications based on the importance of the meeting.

[0096] The sharing section can estimate the user's emotions and adjust how the shared content is displayed based on those emotions. For example, if the user is nervous, the sharing section provides a simple and highly visible display. If the user is relaxed, it provides a display that includes detailed information. If the user is excited, it provides a visually stimulating display. By adjusting how the shared content is displayed based on the user's emotions, it becomes possible to create a display that is easy for the user to understand. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The sharing function can share information in the most optimal format, taking into account the device information of meeting participants. For example, if a participant is using a smartphone, the sharing function provides a display method that matches the screen size. If a participant is using a tablet, the sharing function provides a display method optimized for larger screens. If a participant is using a smartwatch, the sharing function provides a concise and highly visible display method. In this way, by sharing information in the most optimal format, taking into account the device information of meeting participants, information optimized for each device is provided.

[0098] The sharing function can improve the accuracy of sharing by attaching relevant meeting materials during the sharing process. For example, it can improve the accuracy of sharing by attaching meeting minutes, meeting presentation materials, or notes provided by meeting participants. By attaching relevant meeting materials, more accurate information is shared.

[0099] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0100] The recording unit can analyze the tone and speed of speakers' voices when recording meeting audio data, and estimate the importance of what is said. For example, it can mark parts that a speaker emphasizes as important statements. Also, if a speaker speaks quickly, that part can be recorded as an important discussion. Furthermore, if a speaker speaks slowly, that part can be recorded as a detailed explanation. In this way, by estimating importance based on the tone and speed of speech, the content of the meeting can be understood more accurately.

[0101] The analysis unit can estimate the speaker's emotions when analyzing meeting audio data and consider the nuances of their statements based on those estimated emotions. For example, if a speaker is angry, their statement can be analyzed as a strong opinion. If a speaker is sad, their statement can be analyzed as raising an important issue. Furthermore, if a speaker is happy, their statement can be analyzed as a positive suggestion. By considering the nuances of statements based on the speaker's emotions, the content of the meeting can be understood more deeply.

[0102] The generation unit can adjust the format of the meeting summary according to the progress of the meeting. For example, at the beginning of the meeting, it can provide a concise summary of the agenda. In the middle of the meeting, it can generate a more detailed summary according to the progress of the discussion. Towards the end of the meeting, it can focus on summarizing decisions and action items. By adjusting the format of the summary according to the progress of the meeting, the content of the meeting can be effectively communicated.

[0103] The sharing function can estimate the user's emotions when sharing generated summaries and action items, and adjust the sharing method based on those emotions. For example, if the user is nervous, it can share in a simple, highly visible format. If the user is relaxed, it can share in a format that includes detailed information. If the user is excited, it can share in a visually stimulating format. This allows information to be delivered in the most optimal format for the user by adjusting the sharing method based on their emotions.

[0104] The recording unit can classify the content of a meeting's audio data by referring to the speaker's background information. For example, it can classify the content of a meeting based on the speaker's job title, their area of ​​expertise, or their past speaking history. By classifying the content of a meeting based on the speaker's background information, the meeting's content can be organized more systematically.

[0105] The analysis unit can estimate the speaker's emotions when analyzing meeting audio data and adjust the accuracy of the analysis based on the estimated emotions. For example, if the speaker is nervous, important statements can be analyzed more rigorously. If the speaker is relaxed, normal analysis accuracy can be maintained. If the speaker is excited, the analysis can be performed with an emphasis on the nuances of the statements. In this way, by adjusting the accuracy of the analysis based on the speaker's emotions, important statements and discussions can be accurately extracted.

[0106] The generation unit can apply different summarization algorithms depending on the meeting category when generating meeting summaries. For example, in the case of a technical meeting, a summarization algorithm that emphasizes technical content can be applied. In the case of a management meeting, a summarization algorithm that emphasizes decision-making content can be applied. In the case of a project meeting, a summarization algorithm that emphasizes progress status can be applied. By applying different summarization algorithms according to the meeting category, the system can generate summaries that are optimal for each category.

[0107] The sharing function can estimate the user's emotions when sharing generated summaries and action items, and adjust the timing of sharing based on those emotions. For example, if the user is stressed, sharing can be delayed until they relax. If the user is excited, sharing can be done immediately. If the user is tired, sharing can be done after they have taken a break. This allows information to be shared at the appropriate time by adjusting the timing of sharing based on the user's emotions.

[0108] The recording unit can analyze the voice characteristics of speakers when recording meeting audio data and apply different audio filters to each speaker. For example, if a speaker's voice is quiet, a filter can be applied to automatically increase the volume. If a speaker's voice is high-pitched, a filter can be applied to adjust the sound to make it easier to hear. If a speaker's voice contains noise, a filter can be applied to remove the noise. By applying audio filters to each speaker, the content of their speech can be made easier to understand.

[0109] The analysis unit can extract important statements by considering the context of the statements when analyzing meeting audio data. For example, it can identify important statements by analyzing the context before and after a statement. It can extract emphasized parts of a statement. It can extract points that are repeatedly mentioned in a statement as important statements. In this way, by extracting important statements while considering the context of the statements, the accuracy of summarizing the meeting content can be improved.

[0110] The following briefly describes the processing flow for example form 2.

[0111] Step 1: The recording unit records the meeting audio data in real time. The recording unit records everything said during the meeting so that it can be analyzed later. It is important for the recording unit to accurately record what all participants in the meeting say. Step 2: The analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. The analysis unit converts the audio data into text and uses a generation AI to extract important statements and discussions. Step 3: The generation unit generates a meeting summary and action items based on the information extracted by the analysis unit. The generation unit organizes the extracted information, uses generation AI to create a meeting summary, and lists the specific actions decided at the meeting as action items. Step 4: The sharing team shares the summaries and action items generated by the generation team with the members after the meeting. The sharing team shares the summaries and action items generated using the generation AI with the members after the meeting.

[0112] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0114] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0115] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, and sharing unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the audio data of the meeting in real time using the microphone 38B of the smart device 14. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded audio data to extract important statements and discussions. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates a meeting summary and action items based on the extracted information. The sharing unit is implemented in the control unit 46A of the smart device 14, for example, and shares the generated summary and action items with members after the meeting. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0116] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0117] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

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

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

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

[0122] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0123] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

[0125] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0126] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, and sharing unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the recording unit records the audio data of the meeting in real time using the microphone 238 of the smart glasses 214. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded audio data to extract important statements and discussions. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates a meeting summary and action items based on the extracted information. The sharing unit is implemented in the control unit 46A of the smart glasses 214, for example, and shares the generated summary and action items with the members after the meeting. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0132] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0133] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0135] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0139] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

[0141] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, and sharing unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the recording unit records the audio data of the meeting in real time using the microphone 238 of the headset terminal 314. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded audio data to extract important statements and discussions. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates a meeting summary and action items based on the extracted information. The sharing unit is implemented in the control unit 46A of the headset terminal 314, for example, and shares the generated summary and action items with members after the meeting. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0148] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0149] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0155] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0156] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0157] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0158] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0159] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0160] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0162] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0164] Each of the multiple elements described above, including the recording unit, analysis unit, generation unit, and sharing unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the recording unit records the audio data of the meeting in real time using the microphone 238 of the robot 414. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and analyzes the recorded audio data to extract important statements and discussions. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12, for example, and generates a meeting summary and action items based on the extracted information. The sharing unit is implemented in the control unit 46A of the robot 414, for example, and shares the generated summary and action items with the members after the meeting. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0165] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0167] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0168] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0169] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0173] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0174] 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.

[0175] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0176] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0177] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0178] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0180] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0181] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0182] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0183] (Note 1) A recording unit that records the audio data of the meeting in real time, An analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. A generation unit generates a meeting summary and action items based on the information extracted by the analysis unit, The system includes a sharing unit that shares the summaries and action items generated by the generation unit with members after the meeting. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Convert audio data to text and extract important statements and discussions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Organize the extracted information and create a meeting summary. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is List the specific action items decided at the meeting as action items. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned shared portion is, Share the generated summary and action items with members after the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned shared portion is, Notify about the generated summary and action items. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned recording unit is The system estimates the user's emotions and adjusts the timing of audio data recording based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned recording unit is The system automatically highlights important statements as the meeting progresses. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned recording unit is During recording, the speaker's voice characteristics are analyzed, and different voice filters are applied to each speaker. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned recording unit is It estimates the user's emotions and determines the priority of audio data to record based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned recording unit is During recording, noise cancellation is applied, taking into account the meeting location and ambient noise. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned recording unit is During recording, the system tags the content of the comments by referencing the profile information of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the accuracy of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, When analyzing audio data, important statements are extracted by considering the context of the speech. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During analysis, the importance of a speaker's past statements is evaluated by referring to their past statement history. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the analysis algorithm is switched based on the meeting's theme and agenda. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, the content of the statements is classified considering the areas of expertise of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is When generating a summary, adjust the level of detail in the summary based on the importance of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is When generating summaries, different summarization algorithms are applied depending on the meeting category. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is When generating summaries, prioritize the summaries based on the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is When generating summaries, we refer to relevant meeting materials to improve the accuracy of the summaries. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned shared portion is, It estimates the user's emotions and adjusts the timing of sharing based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned shared portion is, When sharing, it provides customized summaries and action items for each meeting participant. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned shared portion is, When sharing, prioritize notifications based on the importance of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned shared portion is, It estimates the user's emotions and adjusts how shared content is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned shared portion is, When sharing, the system will consider the device information of meeting participants and share in the most optimal format. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned shared portion is, When sharing, attach relevant meeting materials to improve the accuracy of the sharing process. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A recording unit that records the audio data of the meeting in real time, An analysis unit analyzes the audio data recorded by the recording unit and extracts important statements and discussions. A generation unit generates a meeting summary and action items based on the information extracted by the analysis unit, The system includes a sharing unit that shares the summaries and action items generated by the generation unit with members after the meeting. A system characterized by the following features.

2. The aforementioned analysis unit, Convert audio data to text and extract important statements and discussions. The system according to feature 1.

3. The generating unit is Organize the extracted information and create a meeting summary. The system according to feature 1.

4. The generating unit is List the specific action items decided at the meeting as action items. The system according to feature 1.

5. The aforementioned shared portion is, Share the generated summary and action items with members after the meeting. The system according to feature 1.

6. The aforementioned shared portion is, Notify about the generated summary and action items. The system according to feature 1.

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

8. The aforementioned recording unit is The system automatically highlights important statements as the meeting progresses. The system according to feature 1.

9. The aforementioned recording unit is During recording, the speaker's voice characteristics are analyzed, and different voice filters are applied to each speaker. The system according to feature 1.

Images