system

Abstract

The system according to this embodiment aims to transcribe the contents of a meeting in real time, summarize it, and suggest the next course of action. [Solution] The system according to the embodiment comprises a collection unit, a summarization unit, and a proposal unit. The collection unit transcribes the audio of the meeting in real time. The summarization unit summarizes the content transcribed by the collection unit. The proposal unit proposes the next action based on the content summarized by the summarization unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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, the content of a meeting has not been sufficiently transcribed in real time, and summaries and suggestions for the next actions have not been well provided, leaving room for improvement.

[0005] The system according to the embodiment aims to transcribe the content of a meeting in real time and propose a summary and the next action.

Means for Solving the Problems

[0006] The system according to the embodiment includes a collection unit, a summarization unit, and a proposal unit. The collection unit transcribes the voice of a meeting in real time. The summarization unit summarizes the content transcribed by the collection unit. The proposal unit proposes the next action based on the content summarized by the summarization unit. [Effects of the Invention]

[0007] The system according to this embodiment can transcribe the contents of a meeting in real time, summarize it, and suggest the next course of action. [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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are 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 support system according to an embodiment of the present invention is a system that transcribes meeting audio in real time and provides summaries and highlights. This meeting support system transcribes meeting audio in real time using speech recognition technology, summarizes the transcribed content using natural language processing technology, and highlights important points. Furthermore, it has a function to suggest the next action based on data analysis. This mechanism streamlines task management after meetings and improves productivity. For example, the meeting audio is transcribed in real time. In this process, speech recognition technology is used to instantly convert what meeting participants say into text. For example, since what is said during the meeting is displayed as text in real time, participants can visually confirm what has been said. Next, the transcribed content is summarized using natural language processing technology. Natural language processing technology extracts important information from the transcribed text and generates a summary. For example, the meeting agenda, decisions, and action items are displayed as a summary. Furthermore, it has a function to suggest the next action based on data analysis. Data analysis technology analyzes the content of the meeting and automatically suggests the next action to be taken. For example, tasks and follow-up actions decided at the meeting are displayed as a list. This system streamlines post-meeting task management and improves productivity. Meeting content is transcribed in real time, and summaries and highlights are provided, allowing participants to easily grasp the meeting's content. Furthermore, the system automatically suggests the next steps, facilitating smooth post-meeting task management. For example, what is said during the meeting is transcribed in real time, and a summary and highlights are provided after the meeting. Additionally, the system suggests the next steps, allowing participants to efficiently manage their post-meeting tasks. In this way, meeting efficiency and information organization are automated, leading to increased productivity. Thus, the meeting support system streamlines post-meeting task management and improves productivity by transcribing meeting audio in real time, providing summaries, and suggesting the next steps.

[0029] The meeting support system according to this embodiment comprises a collection unit, a summarization unit, and a proposal unit. The collection unit transcribes the audio of the meeting in real time. The collection unit transcribes the audio of the meeting using, for example, speech recognition technology. The collection unit can use, for example, speech recognition technology using deep learning. The collection unit can also use speech recognition technology using HMM (Hidden Markov Model). The collection unit instantly converts the content spoken by meeting participants into text using, for example, speech recognition technology. The summarization unit summarizes the transcribed content using natural language processing technology. The summarization unit can analyze the transcribed text using, for example, morphological analysis. The summarization unit can also analyze the transcribed text using grammatical analysis. The summarization unit extracts important information from the transcribed text using, for example, natural language processing technology, and generates a summary. The proposal unit proposes the next action based on data analysis. The proposal unit can analyze the content of the meeting using, for example, the algorithm to be used. The proposal unit can also propose the next action using the data to be analyzed. The proposal function, for example, uses data analysis technology to analyze the content of the meeting and automatically suggests the next action to take. As a result, the meeting support system according to the embodiment transcribes the meeting audio in real time, provides a summary, and suggests the next action, thereby streamlining post-meeting task management and improving productivity.

[0030] The data collection unit transcribes meeting audio in real time. For example, the data collection unit uses speech recognition technology to transcribe meeting audio. Specifically, it can use deep learning-based speech recognition technology. Deep learning-based speech recognition technology learns from large amounts of audio data to achieve high-precision speech recognition. For example, the data collection unit analyzes the audio signal and recognizes phonemes and words to instantly transcribe what meeting participants say into text. Furthermore, the data collection unit can also use speech recognition technology using HMMs (Hidden Markov Models). HMMs model the temporal changes in the audio signal, improving the accuracy of speech recognition. By combining these speech recognition technologies, the data collection unit can transcribe meeting audio with high accuracy and in real time. For example, the data collection unit can instantly transcribe what meeting participants say into text, recording important information without disrupting the meeting. Furthermore, the data collection unit can use noise reduction and speech enhancement technologies to improve the accuracy of speech recognition technology. This allows the data collection unit to transcribe meeting audio with high accuracy and accurately record the content of the meeting.

[0031] The summarization unit summarizes the transcribed content using natural language processing techniques. For example, the summarization unit can analyze the transcribed text using morphological analysis. Morphological analysis is a technique that divides text into words and analyzes the part of speech and meaning of each word. This allows the summarization unit to understand the structure of the transcribed text and extract important information. The summarization unit can also analyze the transcribed text using grammatical analysis. Grammar analysis is a technique that analyzes the grammatical structure of text and understands the meaning and relationships of sentences. This allows the summarization unit to understand the context of the transcribed text and extract important information. Furthermore, the summarization unit extracts important information from the transcribed text using natural language processing techniques and generates a summary. For example, the summarization unit extracts important keywords and phrases from the text and generates a summary based on them. It can also extract important sentences and paragraphs from the text and generate a summary based on them. This allows the summarization unit to concisely summarize the meeting content and efficiently convey important information. Furthermore, the summarization unit can provide the generated summary to the user, supporting task management and decision-making after the meeting.

[0032] The proposal team proposes the next course of action based on data analysis. For example, the proposal team can analyze meeting content using algorithms. Specifically, the proposal team can use machine learning algorithms to analyze meeting content and automatically propose the next course of action. For instance, the proposal team analyzes meeting content, identifies important agenda items and tasks, and proposes the next course of action based on these. The proposal team can also propose the next course of action using the data being analyzed. For example, the proposal team analyzes meeting content and proposes the next course of action based on historical data and statistical information. This allows the proposal team to efficiently analyze meeting content and automatically propose the next course of action. Furthermore, the proposal team can provide the proposed actions to the user, supporting post-meeting task management and decision-making. For example, the proposal team can display the proposed actions in a list format, making it easy for the user to see what they should do next. The proposal team can also collect feedback on the proposed actions and continuously improve the accuracy and effectiveness of the suggestions. This allows the proposal team to propose appropriate actions to the user, streamlining post-meeting task management and decision-making.

[0033] The data collection unit can transcribe meeting audio using speech recognition technology. The data collection unit can use, for example, speech recognition technology using deep learning. Alternatively, the data collection unit can use speech recognition technology using HMM (Hidden Markov Model). The data collection unit can instantly convert what meeting participants say into text using, for example, speech recognition technology. This allows for accurate transcription of meeting audio using speech recognition technology. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input meeting audio data into a generative AI and have the generative AI generate text data from the audio data.

[0034] The summarization unit can summarize the transcribed content using natural language processing techniques. The summarization unit can analyze the transcribed text using, for example, morphological analysis. It can also analyze the transcribed text using grammatical analysis. The summarization unit extracts important information from the transcribed text using, for example, natural language processing techniques, and generates a summary. This allows for efficient summarization of transcribed content using natural language processing techniques. Some or all of the above-described processes in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input the transcribed text data into a generative AI and have the generative AI generate the summary.

[0035] The proposal unit can propose the next action based on data analysis. For example, the proposal unit can analyze the content of a meeting using the algorithm it employs. The proposal unit can also propose the next action using the data being analyzed. For example, the proposal unit can analyze the content of a meeting using data analysis techniques and automatically propose the next action to be taken. This streamlines post-meeting task management by proposing the next action based on data analysis. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal unit can input meeting content data into a generative AI and have the generative AI execute a proposal for the next action.

[0036] The data collection unit can prioritize the collection of important statements according to the progress of the meeting. For example, when an agenda item is presented at the beginning of the meeting, the data collection unit will prioritize the collection of statements related to that agenda item. Furthermore, when an important decision is made in the middle of the meeting, the data collection unit can prioritize the collection of statements related to that decision. In addition, when an action item is confirmed towards the end of the meeting, the data collection unit can prioritize the collection of statements related to that action item. This allows for an effective grasp of the meeting's key points by prioritizing the collection of important statements according to the meeting's progress. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input meeting progress data into a generative AI and have the generative AI prioritize the collection of important statements.

[0037] The data collection unit can improve the accuracy of speech content by applying different speech recognition models to each participant in the meeting. For example, the data collection unit can pre-train the voice characteristics of each participant and apply individual speech recognition models. The data collection unit can also dynamically adjust the accuracy of the speech recognition models according to the frequency of each participant's speech. Furthermore, the data collection unit can improve the recognition accuracy of technical terms and proper nouns based on the content of each participant's speech. In this way, the accuracy of speech content is improved by applying different speech recognition models to each participant. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input each participant's voice data into a generative AI and have the generative AI perform the application of speech recognition models.

[0038] The collection unit can prioritize the collection of highly relevant statements by considering the geographical location information of participants when collecting audio from a meeting. For example, if participants are participating from different locations, the collection unit will prioritize the collection of statements from geographically closer participants. Furthermore, if participants are in the same location, the collection unit can prioritize the collection of statements related to that location. Additionally, if participants are on the move, the collection unit can prioritize the collection of statements related to their destination. This allows for the effective collection of highly relevant statements by considering the geographical location information of participants. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input participants' geographical location data into a generative AI and have the generative AI prioritize the collection of highly relevant statements.

[0039] The data collection unit can analyze participants' social media activity and collect relevant statements when collecting audio from a meeting. For example, the data collection unit can analyze the content of participants' social media posts and prioritize collecting posts related to the meeting agenda. The data collection unit can also determine the importance of a post based on the frequency of the participant's social media activity and collect it accordingly. Furthermore, the data collection unit can prioritize collecting influential posts based on the number of followers a participant has on social media. This allows for the effective collection of relevant statements by analyzing participants' social media activity. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input participants' social media data into a generative AI and have the generative AI collect relevant statements.

[0040] The summarization unit can adjust the level of detail in the summary based on the importance of the statements during summary generation. For example, if there are many important statements, the summarization unit can increase the level of detail in the summary and include specific content. Conversely, if there are few important statements, the summarization unit can decrease the level of detail in the summary and make it more concise. Furthermore, the summarization unit can dynamically adjust the level of detail in the summary according to the importance of the statements. This allows for an effective summary of important information by adjusting the level of detail in the summary based on the importance of the statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0041] The summarization unit can apply different summarization algorithms depending on the meeting agenda when generating summaries. For example, in the case of a technical agenda, the summarization unit can generate a detailed summary including technical terms. It can also generate a summary of decision-making in the case of a business agenda. Furthermore, in the case of a creative agenda, the summarization unit can generate an idea summary. This ensures that a summary appropriate to the agenda is generated by applying different summarization algorithms depending on the meeting agenda. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting agenda data into a generative AI and have the generative AI apply the summarization algorithm.

[0042] The summarization unit can determine the priority of summaries based on the timing of statements made during summary generation. For example, the summarization unit may prioritize summarizing statements made at the beginning of a meeting. It can also prioritize summarizing important statements made in the middle of a meeting. Furthermore, it can prioritize summarizing action items made towards the end of a meeting. This allows for the effective summarization of important information by determining the priority of summaries based on the timing of statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement timing data into a generation AI and have the generation AI perform the determination of summary priorities.

[0043] The summarization unit can adjust the order of summaries based on the relevance of the statements during summary generation. For example, the summarization unit prioritizes summarizing highly relevant statements. It can also postpone summarizing less relevant statements. Furthermore, the summarization unit can dynamically adjust the order of summaries according to the relevance of the statements. This allows for the effective summarization of important information by adjusting the order of summaries based on the relevance of the statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0044] The proposal department can determine the priority of the next actions based on the meeting content when making a proposal. For example, the proposal department can prioritize actions related to important agenda items. It can also prioritize actions with high urgency. Furthermore, the proposal department can dynamically adjust the priority of actions according to the meeting content. This allows for the effective proposal of important actions by determining the priority of the next actions based on the meeting content. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input meeting content data into a generative AI and have the generative AI perform the determination of the priority of the next actions.

[0045] The proposal unit can apply different proposal algorithms depending on the meeting agenda when making a proposal. For example, if the agenda is technical, the proposal unit will propose technical actions. It can also propose business actions if the agenda is business-related. Furthermore, if the agenda is creative, the proposal unit can propose creative actions. This allows for the proposal of appropriate actions by applying different proposal algorithms depending on the meeting agenda. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input meeting agenda data into a generative AI and have the generative AI apply the proposal algorithm.

[0046] The proposal department can adjust the timing of the next action based on the progress of the meeting when making a proposal. For example, the proposal department can propose an action early at the beginning of the meeting. It can also propose an action in the middle of the meeting in a timely manner. Furthermore, it can propose an action later at the end of the meeting. By adjusting the timing of the next action based on the progress of the meeting, it is possible to propose an action at the appropriate time. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input meeting progress data into a generative AI and have the generative AI adjust the timing of the next action.

[0047] The proposal unit can customize the following actions based on the roles of the meeting participants when making a proposal. For example, the proposal unit can propose important actions to the meeting leader. It can also propose specific actions to the meeting members. Furthermore, it can propose supplementary actions to the meeting support staff. This allows for the proposal of appropriate actions by customizing the following actions based on the roles of the meeting participants. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal unit can input meeting participant role data into a generative AI and have the generative AI perform the customization of the following actions.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] The following briefly describes the processing flow for example form 1.

[0050] Step 1: The data collection unit transcribes the meeting audio in real time. The data collection unit transcribes the meeting audio using, for example, speech recognition technology. The data collection unit can use speech recognition technology using deep learning or HMM (Hidden Markov Model). The data collection unit instantly converts what the meeting participants say into text. Step 2: The summarization unit summarizes the transcribed content using natural language processing techniques. The summarization unit analyzes the transcribed text using morphological and grammatical analysis, extracts important information, and generates a summary. Step 3: The proposal team proposes the next action based on data analysis. The proposal team uses the algorithms to analyze the meeting content and automatically proposes the next action to take.

[0051] (Example of form 2) The meeting support system according to an embodiment of the present invention is a system that transcribes meeting audio in real time and provides summaries and highlights. This meeting support system transcribes meeting audio in real time using speech recognition technology, summarizes the transcribed content using natural language processing technology, and highlights important points. Furthermore, it has a function to suggest the next action based on data analysis. This mechanism streamlines task management after meetings and improves productivity. For example, the meeting audio is transcribed in real time. In this process, speech recognition technology is used to instantly convert what meeting participants say into text. For example, since what is said during the meeting is displayed as text in real time, participants can visually confirm what has been said. Next, the transcribed content is summarized using natural language processing technology. Natural language processing technology extracts important information from the transcribed text and generates a summary. For example, the meeting agenda, decisions, and action items are displayed as a summary. Furthermore, it has a function to suggest the next action based on data analysis. Data analysis technology analyzes the content of the meeting and automatically suggests the next action to be taken. For example, tasks and follow-up actions decided at the meeting are displayed as a list. This system streamlines post-meeting task management and improves productivity. Meeting content is transcribed in real time, and summaries and highlights are provided, allowing participants to easily grasp the meeting's content. Furthermore, the system automatically suggests the next steps, facilitating smooth post-meeting task management. For example, what is said during the meeting is transcribed in real time, and a summary and highlights are provided after the meeting. Additionally, the system suggests the next steps, allowing participants to efficiently manage their post-meeting tasks. In this way, meeting efficiency and information organization are automated, leading to increased productivity. Thus, the meeting support system streamlines post-meeting task management and improves productivity by transcribing meeting audio in real time, providing summaries, and suggesting the next steps.

[0052] The meeting support system according to this embodiment comprises a collection unit, a summarization unit, and a proposal unit. The collection unit transcribes the audio of the meeting in real time. The collection unit transcribes the audio of the meeting using, for example, speech recognition technology. The collection unit can use, for example, speech recognition technology using deep learning. The collection unit can also use speech recognition technology using HMM (Hidden Markov Model). The collection unit instantly converts the content spoken by meeting participants into text using, for example, speech recognition technology. The summarization unit summarizes the transcribed content using natural language processing technology. The summarization unit can analyze the transcribed text using, for example, morphological analysis. The summarization unit can also analyze the transcribed text using grammatical analysis. The summarization unit extracts important information from the transcribed text using, for example, natural language processing technology, and generates a summary. The proposal unit proposes the next action based on data analysis. The proposal unit can analyze the content of the meeting using, for example, the algorithm to be used. The proposal unit can also propose the next action using the data to be analyzed. The proposal function, for example, uses data analysis technology to analyze the content of the meeting and automatically suggests the next action to take. As a result, the meeting support system according to the embodiment transcribes the meeting audio in real time, provides a summary, and suggests the next action, thereby streamlining post-meeting task management and improving productivity.

[0053] The data collection unit transcribes meeting audio in real time. For example, the data collection unit uses speech recognition technology to transcribe meeting audio. Specifically, it can use deep learning-based speech recognition technology. Deep learning-based speech recognition technology learns from large amounts of audio data to achieve high-precision speech recognition. For example, the data collection unit analyzes the audio signal and recognizes phonemes and words to instantly transcribe what meeting participants say into text. Furthermore, the data collection unit can also use speech recognition technology using HMMs (Hidden Markov Models). HMMs model the temporal changes in the audio signal, improving the accuracy of speech recognition. By combining these speech recognition technologies, the data collection unit can transcribe meeting audio with high accuracy and in real time. For example, the data collection unit can instantly transcribe what meeting participants say into text, recording important information without disrupting the meeting. Furthermore, the data collection unit can use noise reduction and speech enhancement technologies to improve the accuracy of speech recognition technology. This allows the data collection unit to transcribe meeting audio with high accuracy and accurately record the content of the meeting.

[0054] The summarization unit summarizes the transcribed content using natural language processing techniques. For example, the summarization unit can analyze the transcribed text using morphological analysis. Morphological analysis is a technique that divides text into words and analyzes the part of speech and meaning of each word. This allows the summarization unit to understand the structure of the transcribed text and extract important information. The summarization unit can also analyze the transcribed text using grammatical analysis. Grammar analysis is a technique that analyzes the grammatical structure of text and understands the meaning and relationships of sentences. This allows the summarization unit to understand the context of the transcribed text and extract important information. Furthermore, the summarization unit extracts important information from the transcribed text using natural language processing techniques and generates a summary. For example, the summarization unit extracts important keywords and phrases from the text and generates a summary based on them. It can also extract important sentences and paragraphs from the text and generate a summary based on them. This allows the summarization unit to concisely summarize the meeting content and efficiently convey important information. Furthermore, the summarization unit can provide the generated summary to the user, supporting task management and decision-making after the meeting.

[0055] The proposal team proposes the next course of action based on data analysis. For example, the proposal team can analyze meeting content using algorithms. Specifically, the proposal team can use machine learning algorithms to analyze meeting content and automatically propose the next course of action. For instance, the proposal team analyzes meeting content, identifies important agenda items and tasks, and proposes the next course of action based on these. The proposal team can also propose the next course of action using the data being analyzed. For example, the proposal team analyzes meeting content and proposes the next course of action based on historical data and statistical information. This allows the proposal team to efficiently analyze meeting content and automatically propose the next course of action. Furthermore, the proposal team can provide the proposed actions to the user, supporting post-meeting task management and decision-making. For example, the proposal team can display the proposed actions in a list format, making it easy for the user to see what they should do next. The proposal team can also collect feedback on the proposed actions and continuously improve the accuracy and effectiveness of the suggestions. This allows the proposal team to propose appropriate actions to the user, streamlining post-meeting task management and decision-making.

[0056] The data collection unit can transcribe meeting audio using speech recognition technology. The data collection unit can use, for example, speech recognition technology using deep learning. Alternatively, the data collection unit can use speech recognition technology using HMM (Hidden Markov Model). The data collection unit can instantly convert what meeting participants say into text using, for example, speech recognition technology. This allows for accurate transcription of meeting audio using speech recognition technology. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input meeting audio data into a generative AI and have the generative AI generate text data from the audio data.

[0057] The summarization unit can summarize the transcribed content using natural language processing techniques. The summarization unit can analyze the transcribed text using, for example, morphological analysis. It can also analyze the transcribed text using grammatical analysis. The summarization unit extracts important information from the transcribed text using, for example, natural language processing techniques, and generates a summary. This allows for efficient summarization of transcribed content using natural language processing techniques. Some or all of the above-described processes in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input the transcribed text data into a generative AI and have the generative AI generate the summary.

[0058] The proposal unit can propose the next action based on data analysis. For example, the proposal unit can analyze the content of a meeting using the algorithm it employs. The proposal unit can also propose the next action using the data being analyzed. For example, the proposal unit can analyze the content of a meeting using data analysis techniques and automatically propose the next action to be taken. This streamlines post-meeting task management by proposing the next action based on data analysis. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal unit can input meeting content data into a generative AI and have the generative AI execute a proposal for the next action.

[0059] The collection unit can estimate the emotions of meeting participants and adjust the timing of audio collection based on the estimated emotions. For example, if a meeting participant is excited, the collection unit can shorten the collection timing because important statements are more likely to be made. Conversely, if a meeting participant is tired, the collection unit can lengthen the collection timing because fewer statements will be made. Furthermore, if a meeting participant is relaxed, the collection unit can maintain a constant collection timing to preserve a natural flow of conversation. By adjusting the timing of audio collection according to the emotions of the meeting participants, important statements can be effectively collected. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input the meeting participant's audio data into a generative AI and have the generative AI perform emotion estimation.

[0060] The data collection unit can prioritize the collection of important statements according to the progress of the meeting. For example, when an agenda item is presented at the beginning of the meeting, the data collection unit will prioritize the collection of statements related to that agenda item. Furthermore, when an important decision is made in the middle of the meeting, the data collection unit can prioritize the collection of statements related to that decision. In addition, when an action item is confirmed towards the end of the meeting, the data collection unit can prioritize the collection of statements related to that action item. This allows for an effective grasp of the meeting's key points by prioritizing the collection of important statements according to the meeting's progress. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input meeting progress data into a generative AI and have the generative AI prioritize the collection of important statements.

[0061] The data collection unit can improve the accuracy of speech content by applying different speech recognition models to each participant in the meeting. For example, the data collection unit can pre-train the voice characteristics of each participant and apply individual speech recognition models. The data collection unit can also dynamically adjust the accuracy of the speech recognition models according to the frequency of each participant's speech. Furthermore, the data collection unit can improve the recognition accuracy of technical terms and proper nouns based on the content of each participant's speech. In this way, the accuracy of speech content is improved by applying different speech recognition models to each participant. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input each participant's voice data into a generative AI and have the generative AI perform the application of speech recognition models.

[0062] The collection unit can estimate the emotions of meeting participants and determine the priority of audio to collect based on the estimated emotions. For example, if a meeting participant is excited, the collection unit will prioritize collecting their statements. If a meeting participant is calm, the collection unit can also collect their statements with normal priority. Furthermore, if a meeting participant is tired, the collection unit can postpone collecting their statements. This allows for the effective collection of important statements by prioritizing the audio to be collected according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the collection unit may be performed using AI, or not using AI. For example, the collection unit can input the meeting participants' audio data into a generative AI and have the generative AI perform emotion estimation.

[0063] The collection unit can prioritize the collection of highly relevant statements by considering the geographical location information of participants when collecting audio from a meeting. For example, if participants are participating from different locations, the collection unit will prioritize the collection of statements from geographically closer participants. Furthermore, if participants are in the same location, the collection unit can prioritize the collection of statements related to that location. Additionally, if participants are on the move, the collection unit can prioritize the collection of statements related to their destination. This allows for the effective collection of highly relevant statements by considering the geographical location information of participants. Some or all of the above processing in the collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collection unit can input participants' geographical location data into a generative AI and have the generative AI prioritize the collection of highly relevant statements.

[0064] The data collection unit can analyze participants' social media activity and collect relevant statements when collecting audio from a meeting. For example, the data collection unit can analyze the content of participants' social media posts and prioritize collecting posts related to the meeting agenda. The data collection unit can also determine the importance of a post based on the frequency of the participant's social media activity and collect it accordingly. Furthermore, the data collection unit can prioritize collecting influential posts based on the number of followers a participant has on social media. This allows for the effective collection of relevant statements by analyzing participants' social media activity. Some or all of the above processing in the data collection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data collection unit can input participants' social media data into a generative AI and have the generative AI collect relevant statements.

[0065] The summarization unit can estimate the emotions of meeting participants and adjust the way the summary is presented based on the estimated emotions. For example, if a meeting participant is excited, the summarization unit can make the summary concise and emphasize key points. If the meeting participant is calm, the summarization unit can make the summary more detailed and easier to understand. Furthermore, if the meeting participant is tired, the summarization unit can simplify the summary to make it easier to understand. In this way, adjusting the way the summary is presented according to the emotions of the meeting participants improves the comprehension of the summary. 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. Some or all of the above processing in the summarization unit may be performed using AI or not using AI. For example, the summarization unit can input the meeting participant's audio data into a generative AI and have the generative AI perform emotion estimation.

[0066] The summarization unit can adjust the level of detail in the summary based on the importance of the statements during summary generation. For example, if there are many important statements, the summarization unit can increase the level of detail in the summary and include specific content. Conversely, if there are few important statements, the summarization unit can decrease the level of detail in the summary and make it more concise. Furthermore, the summarization unit can dynamically adjust the level of detail in the summary according to the importance of the statements. This allows for an effective summary of important information by adjusting the level of detail in the summary based on the importance of the statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0067] The summarization unit can apply different summarization algorithms depending on the meeting agenda when generating summaries. For example, in the case of a technical agenda, the summarization unit can generate a detailed summary including technical terms. It can also generate a summary of decision-making in the case of a business agenda. Furthermore, in the case of a creative agenda, the summarization unit can generate an idea summary. This ensures that a summary appropriate to the agenda is generated by applying different summarization algorithms depending on the meeting agenda. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input meeting agenda data into a generative AI and have the generative AI apply the summarization algorithm.

[0068] The summarization unit can estimate the emotions of meeting participants and adjust the length of the summary based on the estimated emotions. For example, if a meeting participant is excited, the summarization unit can shorten the summary and emphasize key points. Conversely, if a meeting participant is calm, the summarization unit can lengthen the summary and include more detailed information. Furthermore, if a meeting participant is tired, the summarization unit can shorten the summary and make it easier to understand. This improves the comprehension of the summary by adjusting its length according to the emotions of the meeting participants. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input meeting participant audio data into a generative AI and have the generative AI perform emotion estimation.

[0069] The summarization unit can determine the priority of summaries based on the timing of statements made during summary generation. For example, the summarization unit may prioritize summarizing statements made at the beginning of a meeting. It can also prioritize summarizing important statements made in the middle of a meeting. Furthermore, it can prioritize summarizing action items made towards the end of a meeting. This allows for the effective summarization of important information by determining the priority of summaries based on the timing of statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement timing data into a generation AI and have the generation AI perform the determination of summary priorities.

[0070] The summarization unit can adjust the order of summaries based on the relevance of the statements during summary generation. For example, the summarization unit prioritizes summarizing highly relevant statements. It can also postpone summarizing less relevant statements. Furthermore, the summarization unit can dynamically adjust the order of summaries according to the relevance of the statements. This allows for the effective summarization of important information by adjusting the order of summaries based on the relevance of the statements. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input statement relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0071] The suggestion unit can estimate the emotions of meeting participants and adjust how it suggests the next action based on the estimated emotions. For example, if a meeting participant is excited, the suggestion unit can quickly suggest the next action. If the meeting participant is calm, the suggestion unit can also suggest the next action in detail. Furthermore, if the meeting participant is tired, the suggestion unit can suggest the next action concisely. In this way, by adjusting how the next action is suggested according to the emotions of the meeting participants, appropriate actions can be suggested. 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. Some or all of the processing described above in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input the voice data of meeting participants into a generative AI and have the generative AI perform emotion estimation.

[0072] The proposal department can determine the priority of the next actions based on the meeting content when making a proposal. For example, the proposal department can prioritize actions related to important agenda items. It can also prioritize actions with high urgency. Furthermore, the proposal department can dynamically adjust the priority of actions according to the meeting content. This allows for the effective proposal of important actions by determining the priority of the next actions based on the meeting content. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input meeting content data into a generative AI and have the generative AI perform the determination of the priority of the next actions.

[0073] The proposal unit can apply different proposal algorithms depending on the meeting agenda when making a proposal. For example, if the agenda is technical, the proposal unit will propose technical actions. It can also propose business actions if the agenda is business-related. Furthermore, if the agenda is creative, the proposal unit can propose creative actions. This allows for the proposal of appropriate actions by applying different proposal algorithms depending on the meeting agenda. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input meeting agenda data into a generative AI and have the generative AI apply the proposal algorithm.

[0074] The suggestion unit can estimate the emotions of meeting participants and adjust how the next action is displayed based on the estimated emotions. For example, if a meeting participant is excited, the suggestion unit can visually highlight the next action. If a meeting participant is calm, the suggestion unit can also display the next action in detail. Furthermore, if a meeting participant is tired, the suggestion unit can display the next action concisely. In this way, by adjusting how the next action is displayed according to the emotions of the meeting participants, the appropriate action can be displayed. 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. Some or all of the processing described above in the suggestion unit may be performed using AI or not using AI. For example, the suggestion unit can input the voice data of meeting participants into a generative AI and have the generative AI perform emotion estimation.

[0075] The proposal department can adjust the timing of the next action based on the progress of the meeting when making a proposal. For example, the proposal department can propose an action early at the beginning of the meeting. It can also propose an action in the middle of the meeting in a timely manner. Furthermore, it can propose an action later at the end of the meeting. By adjusting the timing of the next action based on the progress of the meeting, it is possible to propose an action at the appropriate time. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input meeting progress data into a generative AI and have the generative AI adjust the timing of the next action.

[0076] The proposal unit can customize the following actions based on the roles of the meeting participants when making a proposal. For example, the proposal unit can propose important actions to the meeting leader. It can also propose specific actions to the meeting members. Furthermore, it can propose supplementary actions to the meeting support staff. This allows for the proposal of appropriate actions by customizing the following actions based on the roles of the meeting participants. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal unit can input meeting participant role data into a generative AI and have the generative AI perform the customization of the following actions.

[0077] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0078] The meeting support system can also include a translation function. This function translates meeting audio in real time, facilitating communication between participants who speak different languages. For example, it can translate what is said in English into Japanese and display it in Japanese. The translation function can also translate meeting summaries and proposed next actions. This enables effective communication across language barriers, even in international meetings. Furthermore, the translation function can estimate participants' emotions and adjust the translation accordingly. For example, if a participant is excited, the translation will be concise and key points emphasized. If a participant is calm, a detailed translation will be provided to facilitate understanding of the overall flow. This ensures that the translation is appropriate to the participants' emotions.

[0079] The meeting support system can also be equipped with a visual assistance unit. This unit automatically generates graphs and charts to visually support the meeting content. For example, it can generate graphs in real time based on data discussed during the meeting, providing participants with visual information. The visual assistance unit can also visually display a meeting summary and highlight key points. This makes it easier for participants to understand the meeting content through visual information. Furthermore, the visual assistance unit can estimate participants' emotions and adjust the visual representation accordingly. For example, if a participant is excited, it might display a simple, highlighted graph; if calm, it might provide a detailed graph. This ensures that participants receive appropriate visual information based on their emotions.

[0080] The meeting support system can also include a feedback function. This function collects feedback from participants after the meeting and uses it to improve future meetings. For example, it can automatically generate and send questionnaires about the meeting's progress and content to participants. The feedback function can also analyze the collected feedback and suggest areas for improvement, thereby continuously improving the quality of meetings. Furthermore, the feedback function can estimate participants' emotions and adjust the feedback collection method accordingly. For example, it might provide a concise questionnaire if participants are agitated, and a more detailed questionnaire if they are calm. This ensures that appropriate feedback is collected based on the participants' emotional state.

[0081] The meeting support system can also include a reminder function. This function automatically generates reminders to encourage the execution of action items decided upon during the meeting. For example, it can set deadlines for action items after the meeting and send reminders to participants as the deadline approaches. The reminder function can also track the progress of action items and issue alerts if progress is behind schedule, ensuring that action items are completed. Furthermore, the reminder function can estimate participants' emotions and adjust the way reminders are sent accordingly. For example, it can send a concise reminder if participants are excited and a more detailed reminder if they are calm. This ensures that participants receive appropriate reminders based on their emotional state.

[0082] The meeting support system can also include an archiving section. This section stores meeting audio and transcript data for later reference. For example, after a meeting, audio and transcript data can be saved to the cloud, allowing participants to access them as needed. The archiving section can also provide tagging functionality to facilitate searching of saved data, making it easy to refer to past meeting content. Furthermore, the archiving section can estimate participants' emotions and adjust how the archive is displayed accordingly. For example, if a participant is excited, key points might be highlighted; if calm, detailed information might be displayed. This ensures that the archive is appropriate to the participants' emotional state.

[0083] The meeting support system can also include a scheduling unit. This unit automatically adjusts meeting schedules to accommodate all participants. For example, it can refer to participants' calendars and suggest the most suitable meeting date and time. The scheduling unit can also automatically send meeting reminders, notifying participants of upcoming meetings. This streamlines the meeting scheduling process. Furthermore, the scheduling unit can estimate participants' emotions and adjust scheduling accordingly. For example, if participants are excited, it might quickly adjust the schedule; if they are calm, it might provide a more detailed schedule. This ensures appropriate scheduling based on participants' emotions.

[0084] The meeting support system can also be equipped with a noise-canceling unit. The noise-canceling unit removes background noise during meetings in real time, improving speech clarity. For example, it eliminates background noise and echoes that occur during meetings, making participants' speech clearer. The noise-canceling unit can also be applied to meeting recordings, providing clear audio during later playback. This improves the audio quality of meetings, allowing participants to accurately understand what is being said. Furthermore, the noise-canceling unit can estimate participants' emotions and adjust the intensity of noise cancellation accordingly. For example, it can apply strong noise cancellation when participants are excited, and maintain natural speech when they are calm. This provides appropriate noise cancellation tailored to the participants' emotions.

[0085] The meeting support system can also be equipped with a real-time translation function. This function instantly translates what is said during a meeting into another language, facilitating communication between participants who speak different languages. For example, it can translate what is said in English into Japanese and display it in Japanese. The real-time translation function can also translate meeting summaries and proposed next actions. This enables effective communication across language barriers, even in international meetings. Furthermore, the real-time translation function can estimate participants' emotions and adjust the translation accordingly. For example, if a participant is excited, the translation will be concise and key points emphasized. If a participant is calm, a detailed translation will be provided to make it easier to grasp the overall flow. This ensures that the translation is appropriate to the participant's emotions.

[0086] The meeting support system can also include a data visualization unit. This unit converts data discussed during the meeting into graphs and charts in real time, providing participants with visual information. For example, it can display sales data or market analysis data as graphs. The data visualization unit can also visually display a meeting summary and highlight key points. This makes it easier for participants to understand the meeting content through visual information. Furthermore, the data visualization unit can estimate participants' emotions and adjust the visual representation accordingly. For example, if participants are excited, it might display a simple, highlighted graph; if they are calm, it might provide a detailed graph. This ensures that participants receive appropriate visual information tailored to their emotions.

[0087] The meeting support system can also include a minutes generation unit. This unit automatically generates meeting minutes based on audio and transcript data from the meeting. For example, it can automatically generate minutes after the meeting and distribute them to participants. The minutes generation unit can also provide a tagging function to make the minutes easier to search, allowing for easy reference to past meeting content. Furthermore, the minutes generation unit can estimate participants' emotions and adjust the way the minutes are presented accordingly. For example, if participants are excited, it can generate concise minutes emphasizing key points; if they are calm, it can provide detailed minutes. This ensures that appropriate minutes are provided based on the participants' emotions.

[0088] The following briefly describes the processing flow for example form 2.

[0089] Step 1: The data collection unit transcribes the meeting audio in real time. The data collection unit transcribes the meeting audio using, for example, speech recognition technology. The data collection unit can use speech recognition technology using deep learning or HMM (Hidden Markov Model). The data collection unit instantly converts what the meeting participants say into text. Step 2: The summarization unit summarizes the transcribed content using natural language processing techniques. The summarization unit analyzes the transcribed text using morphological and grammatical analysis, extracts important information, and generates a summary. Step 3: The proposal team proposes the next action based on data analysis. The proposal team uses the algorithms to analyze the meeting content and automatically proposes the next action to take.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] Each of the multiple elements described above, including the collection unit, summarization unit, and proposal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit acquires meeting audio using the microphone 38B of the smart device 14 and transcribes it in real time using speech recognition technology by the control unit 46A. The summarization unit is implemented in the specific processing unit 290 of the data processing unit 12 and summarizes the transcribed content using natural language processing technology. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes the next action based on data analysis. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0094] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] Each of the multiple elements described above, including the collection unit, summarization unit, and proposal unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit acquires the audio of the meeting using the microphone 238 of the smart glasses 214 and transcribes it in real time using speech recognition technology by the control unit 46A. The summarization unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12 and summarizes the transcribed content using natural language processing technology. The proposal unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12 and proposes the next action based on data analysis. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0110] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] Each of the multiple elements described above, including the collection unit, summarization unit, and proposal unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit acquires conference audio using the microphone 238 of the headset terminal 314 and transcribes it in real time using speech recognition technology by the control unit 46A. The summarization unit is implemented in the specific processing unit 290 of the data processing unit 12 and summarizes the transcribed content using natural language processing technology. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes the next action based on data analysis. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0126] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the collection unit, summarization unit, and proposal unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the collection unit acquires the audio of the meeting using the microphone 238 of the robot 414 and transcribes it in real time using speech recognition technology by the control unit 46A. The summarization unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and summarizes the transcribed content using natural language processing technology. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and proposes the next action based on data analysis. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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."

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] (Note 1) The collection department transcribes the meeting audio in real time, A summarization unit that summarizes the content transcribed by the aforementioned collection unit, The system comprises: a proposal unit that proposes the next action based on the content summarized by the summarization unit; A system characterized by the following features. (Note 2) The aforementioned collection unit is Use speech recognition technology to transcribe meeting audio into text. The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Summarize the transcribed content using natural language processing technology. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned proposal section is, Data suggestion: Next action The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is The system estimates the emotions of meeting participants and adjusts the timing of audio collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is Depending on the progress of the meeting, prioritize collecting important comments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is Applying different speech recognition models to each participant in the meeting improves the accuracy of the speech content. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is The system estimates the emotions of meeting participants and determines the priority of audio to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When collecting meeting audio, the system prioritizes the collection of highly relevant statements by considering the geographical location information of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When collecting meeting audio, analyze participants' social media activity and collect relevant comments. The system described in Appendix 1, characterized by the features described herein. (Note 11) The summary section above is, The system estimates the emotions of meeting participants 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 12) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of each statement. The system described in Appendix 1, characterized by the features described herein. (Note 13) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the meeting agenda. The system described in Appendix 1, characterized by the features described herein. (Note 14) The summary section above is, The system estimates the emotions of meeting participants and adjusts the length of the summary based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The summary section above is, When generating summaries, the priority of summaries is determined based on the timing of the statements. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, When generating summaries, the order of the summaries is adjusted based on the relevance of the statements. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, The system estimates the emotions of meeting participants and adjusts how the next actions are proposed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, When making a proposal, prioritize the next actions based on the meeting's content. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, When making a proposal, apply a different proposal algorithm depending on the meeting agenda. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, The system estimates the emotions of meeting participants and adjusts how the next action is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, When making a proposal, adjust the timing of the next action based on the progress of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, When making a proposal, customize the following actions based on the roles of the meeting participants. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0162] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department transcribes the meeting audio in real time, A summarization unit that summarizes the content transcribed by the aforementioned collection unit, The system comprises: a proposal unit that proposes the next action based on the content summarized by the summarization unit; A system characterized by the following features.

2. The aforementioned collection unit is Use speech recognition technology to transcribe meeting audio into text. The system according to feature 1.

3. The summary section above is, Summarize the transcribed content using natural language processing technology. The system according to feature 1.

4. The aforementioned proposal section is, Data suggestion: Next action The system according to feature 1.

5. The aforementioned collection unit is The system estimates the emotions of meeting participants and adjusts the timing of audio collection based on the estimated emotions. The system according to feature 1.

6. The aforementioned collection unit is Depending on the progress of the meeting, prioritize collecting important comments. The system according to feature 1.

7. The aforementioned collection unit is Applying different speech recognition models to each participant in the meeting improves the accuracy of the speech content. The system according to feature 1.

8. The aforementioned collection unit is The system estimates the emotions of meeting participants and determines the priority of audio to collect based on those estimated emotions. The system according to feature 1.

9. The aforementioned collection unit is When collecting meeting audio, the system prioritizes the collection of highly relevant statements by considering the geographical location information of the participants. The system according to feature 1.

10. The aforementioned collection unit is When collecting meeting audio, analyze participants' social media activity and collect relevant comments. The system according to feature 1.

Images