system

Abstract

The system according to the embodiment aims to automate speech and summarization in a conference and realize efficient conference management. [Solution] A system according to an embodiment includes a storage unit, a tracking unit, a speech unit, a summarizing unit, and an image generating unit. The storage unit stores materials or communication tools, emails, and conversation history. The tracking unit tracks the flow of conversation in real time based on the information stored by the storage unit. The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The summarizing unit summarizes the content spoken by the speech unit. The image generating unit generates camera images based on the content summarized by the summarizing unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately automated conference speech and summarization, and there is room for improvement.

[0005] The system according to the embodiment aims to automate speech and summarization in a conference and realize efficient conference management. [Means for solving the problem]

[0006] The system according to the embodiment includes a storage unit, a tracking unit, a speech unit, a summarizing unit, and an image generating unit. The storage unit stores materials or communication tools, emails, and conversation history. The tracking unit tracks the flow of conversation in real time based on the information stored by the storage unit. The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The summarizing unit summarizes the content spoken by the speech unit. The image generating unit generates camera images based on the content summarized by the summarizing unit. [Effects of the Invention]

[0007] The system according to the embodiment automates speech and summarization in a conference, and can realize efficient conference management. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A meeting automation system according to an embodiment of the present invention stores documents, communication tools, emails, and conversation histories, tracks the flow of conversation in real time, automates speech, summarizes the meeting content, and generates camera footage. The meeting automation system stores the documents, communication tools, emails, and conversation histories owned by the user in a database (DB). Next, the system tracks the flow of conversation in real time during a meeting. When the user's speech is needed, a generation AI references the DB, synthesizes the user's voice, and automatically speaks. After the meeting, the meeting content is summarized, allowing even non-attendees to understand the meeting content in five minutes. Furthermore, when camera footage is needed, a video generation AI generates camera footage in real time that appears as if the user is speaking. Furthermore, it is possible to assign an agenda and have the MTG optimizer AIs discuss and reach a conclusion. For example, the meeting automation system stores the documents, communication tools, emails, and conversation histories owned by the user in a DB. For example, the DB stores emails sent and received by the user and conversation history via chat tools. Next, the meeting automation system tracks the flow of conversation in real time during a meeting. The generation AI analyzes the audio of a meeting and understands the content of the conversation. For example, if someone asks a question during a meeting, it searches the database for an appropriate answer and synthesizes the user's voice to automatically speak it. This allows users to automate their own speech during the meeting. Next, the meeting automation system summarizes the meeting content after the meeting. The generation AI analyzes the meeting audio data, extracts key points, and creates a summary. For example, it summarizes the meeting agenda, decisions, and next action items and provides them to the user. This allows users to quickly understand the meeting content even if they are not in attendance. In addition, if camera footage is required, the meeting automation system uses the video generation AI to generate camera footage in real time, making it appear as if the user is speaking. For example, even if a user cannot attend a meeting, the video generation AI synthesizes the user's face and facial expressions to create a video that makes it appear as if the user is actually attending the meeting. This allows users to participate in meetings remotely.Furthermore, the meeting automation system can also provide an agenda and have MTG optimizer AIs discuss it among themselves to reach a conclusion. For example, multiple AIs can discuss a specific agenda and reach an optimal conclusion. This allows users to proceed with meetings efficiently. This allows the meeting automation system to automate meeting utterances and summaries, and efficiently grasp the meeting content. For example, even if a user is not present at the meeting, the meeting content can be grasped in a short amount of time. Users can also participate in meetings remotely, allowing meetings to proceed efficiently.

[0029] A conference automation system according to an embodiment includes a storage unit, a tracking unit, a speech unit, a summarizing unit, and a video generation unit. The storage unit stores materials, communication tools, emails, and conversation histories. The materials include, for example, PDF files and presentation materials. The communication tools include, for example, chat apps and video conferencing tools. The emails include, for example, text emails and HTML emails. The conversation histories include, for example, voice data and text data. The tracking unit tracks the flow of conversation in real time based on the information stored by the storage unit. The tracking unit, for example, uses speech recognition technology to analyze the audio of the conference and understand the content of the conversation. The tracking unit can also analyze the context of the conversation using natural language processing technology. The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The speech unit, for example, searches for an appropriate answer from a database, synthesizes the user's voice, and automatically speaks it. The speech unit synthesizes the user's voice using speech synthesis technology. The summarizing unit summarizes the content spoken by the speaking unit. The summarizing unit, for example, analyzes audio data of a conference and extracts important points to create a summary. The summarizing unit can also extract important information using keyword extraction technology. The video generating unit generates camera video based on the content summarized by the summarizing unit. The video generating unit, for example, synthesizes a user's face and facial expression to generate video that makes it appear as if the user is attending the conference. The video generating unit generates video using face recognition technology and facial expression generation algorithms. As a result, the conference automation system according to the embodiment automates the speech and summarization of a conference, and can efficiently grasp the content of the conference. For example, even if a user is not attending the conference, the content of the conference can be grasped in a short time. Furthermore, a user can participate in the conference remotely, allowing the conference to proceed efficiently.

[0030] The storage unit can store minutes of past meetings, email content, and chat history. The storage unit stores, for example, minutes of past meetings in text format. The minutes include the meeting agenda, comments, decisions, etc. The storage unit can also store the content of past emails in text format or HTML format. The content of emails includes the sender, recipient, subject, body, etc. The storage unit can also store the history of past chats in text format. The chat history includes the speaker, comment content, and comment time, etc. This enables centralized management of information by storing the minutes of past meetings, email content, and chat history. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI, for example. For example, the storage unit can input the minutes of past meetings into a generation AI and have the generation AI summarize the minutes.

[0031] The tracking unit can analyze the audio of the conference and understand the content of the conversation. The tracking unit can analyze the audio of the conference using, for example, speech recognition technology. For example, the tracking unit can convert the audio data of the conference into text data. The tracking unit can also improve the quality of the audio data using noise reduction technology. For example, the tracking unit can remove background noise and make the speaker's voice clearer. The tracking unit can also understand the content of the conversation using natural language processing technology. For example, the tracking unit can analyze the context of the conversation and understand the intention of the utterances. This allows the flow of the conversation to be followed in real time by analyzing the audio of the conference and understanding the content of the conversation. Some or all of the above-mentioned processing in the tracking unit can be performed using, for example, AI, or can be performed without using AI. For example, the tracking unit can input the audio data of the conference to a generation AI and have the generation AI understand the content of the conversation.

[0032] The speech unit can search for an appropriate answer from the database, synthesize the user's voice, and automatically speak it. The speech unit, for example, searches for an appropriate answer from the database. For example, the speech unit refers to an FAQ database to search for an appropriate answer to a question. The speech unit can also generate an appropriate answer using a machine learning model. For example, the speech unit generates an answer to a question using a model that has learned from past conversation data. The speech unit also synthesizes the user's voice using speech synthesis technology. For example, the speech unit extracts features of the user's voice and generates synthetic speech. This allows the speech unit to search for an appropriate answer from the database, synthesize the user's voice, and automatically speak it, thereby automating the user's speech. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without AI. For example, the speech unit can input the answer searched for from the database to a generation AI and have the generation AI synthesize the user's voice.

[0033] The summarization unit can analyze the audio data of a meeting, extract important points, and create a summary. The summarization unit, for example, analyzes the audio data of the meeting. For example, the summarization unit converts the audio data into text data using speech recognition technology. The summarization unit can also extract important points using keyword extraction technology. For example, the summarization unit extracts the meeting agenda, decisions, next action items, etc. The summarization unit also creates a summary using a summarization algorithm. For example, the summarization unit summarizes the content of the meeting using an abstract summarization algorithm. In this way, by analyzing the audio data of the meeting, extracting important points, and creating a summary, the content of the meeting can be understood in a short period of time. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the audio data to a generation AI and have the generation AI generate a summary.

[0034] The image generation unit can synthesize the user's face and facial expression to generate an image that makes it appear as if the user is attending a meeting. The image generation unit synthesizes, for example, the user's face and facial expression. For example, the image generation unit extracts the user's facial features using facial recognition technology to generate a synthetic image. The image generation unit can also synthesize the user's facial expression using a facial expression generation algorithm. For example, the image generation unit generates facial expressions in real time based on the user's facial expression data. This enables remote participation in a meeting by synthesizing the user's face and facial expression to generate an image that makes it appear as if the user is attending a meeting. Some or all of the above-described processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the user's facial feature data into a generation AI and cause the generation AI to generate a synthetic image.

[0035] The storage unit can adjust the level of detail of storage based on the importance of the information when storing the information. The storage unit, for example, evaluates the importance of the information. For example, the storage unit evaluates the importance based on the frequency of use and relevance of the information. The storage unit also adjusts the level of detail of storage based on the importance of the information. For example, the storage unit stores minutes of important meetings in detail to make them easier to search later. The storage unit can also simplify and store the content of general emails to extract only the necessary information. Furthermore, the storage unit can prioritize and store important messages in chat history, and simplify and store other messages. In this way, important information can be stored in detail by adjusting the level of detail of storage based on the importance of the information. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the importance of the information to a generation AI and cause the generation AI to adjust the level of detail of storage.

[0036] The storage unit can apply different storage algorithms depending on the category of information when storing the information. The storage unit, for example, classifies the category of information. For example, the storage unit classifies the information into categories such as text data, audio data, and image data. The storage unit also applies different storage algorithms depending on the category of information. For example, the storage unit stores meeting minutes using a text analysis algorithm. The storage unit can also store email content using a natural language processing algorithm. Furthermore, the storage unit can store chat history using a keyword extraction algorithm. In this way, by applying different storage algorithms depending on the category of information, information management becomes more efficient. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of information to a generation AI and cause the generation AI to apply a storage algorithm.

[0037] The storage unit can improve the accuracy of storage by referring to the user's past storage history when storing data. The storage unit, for example, analyzes the user's past storage history. For example, the storage unit analyzes patterns of information previously stored by the user and automatically classifies similar information. The storage unit can also prioritize storing information frequently referenced by the user to make it easier to search. Furthermore, the storage unit can suggest an optimal storage method based on the user's past storage history. This improves the accuracy of storage by referring to the user's past storage history. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the user's past storage history into a generation AI and have the generation AI improve the accuracy of storage.

[0038] The tracking unit can adjust the level of detail of tracking based on the importance of the conversation during tracking. The tracking unit, for example, evaluates the importance of the conversation. For example, the tracking unit evaluates the importance based on the frequency of utterances and the relevance of the content. The tracking unit also adjusts the level of detail of tracking based on the importance of the conversation. For example, the tracking unit follows important meeting conversations in detail and records all necessary information. The tracking unit can also simplify and follow general conversations and record only necessary information. Furthermore, the tracking unit can quickly follow urgent conversations and prioritize recording important information. In this way, important conversations can be tracked in detail by adjusting the level of detail of tracking based on the importance of the conversation. Some or all of the above-mentioned processing in the tracking unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracking unit can input the importance of the conversation to a generation AI and cause the generation AI to adjust the level of detail of tracking.

[0039] The tracking unit can apply different tracking algorithms depending on the category of the conversation during tracking. The tracking unit, for example, classifies the category of the conversation. For example, the tracking unit classifies the category into business conversation, everyday conversation, technical conversation, etc. Furthermore, the tracking unit applies different tracking algorithms depending on the category of the conversation. For example, the tracking unit applies a business tracking algorithm to a conversation in a business meeting. Furthermore, the tracking unit can also apply a project management tracking algorithm to a conversation in a project meeting. Furthermore, the tracking unit can apply a team management tracking algorithm to a conversation in a team meeting. In this way, by applying different tracking algorithms depending on the category of the conversation, conversation management becomes more efficient. Some or all of the above-mentioned processing in the tracking unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracking unit can input the category of the conversation to a generation AI and cause the generation AI to apply the tracking algorithm.

[0040] The tracking unit can improve the accuracy of tracking by referring to the user's past tracking history when tracking. The tracking unit, for example, analyzes the user's past tracking history. For example, the tracking unit analyzes patterns of conversations that the user has followed in the past and automatically follows similar conversations. The tracking unit can also prioritize following conversations that the user frequently follows, thereby improving accuracy. Furthermore, the tracking unit can also suggest an optimal tracking method based on the user's past tracking history. In this way, by referring to the user's past tracking history, the accuracy of tracking is improved. Some or all of the above-mentioned processing in the tracking unit may be performed, for example, using AI, or may be performed without using AI. For example, the tracking unit can input the user's past following history to a generation AI and cause the generation AI to improve the accuracy of tracking.

[0041] The speech unit can adjust the level of detail of the speech when speaking based on the importance of the conversation. The speech unit, for example, evaluates the importance of the conversation. For example, the speech unit evaluates the importance based on the frequency of utterances and the relevance of the content. The speech unit also adjusts the level of detail of the speech based on the importance of the conversation. For example, the speech unit can provide detailed speech for important meetings and convey all necessary information. The speech unit can also simplify speech for general conversations and convey only the necessary information. Furthermore, the speech unit can provide rapid speech for urgent conversations and prioritize the conveyance of important information. In this way, important information can be conveyed in detail by adjusting the level of detail of the speech based on the importance of the conversation. Some or all of the above-mentioned processing in the speech unit may be performed using AI, for example, or may be performed without using AI. For example, the speech unit can input the importance of the conversation to a generation AI and cause the generation AI to adjust the level of detail of the speech.

[0042] The speech unit can apply different speech algorithms depending on the category of the conversation when speaking. The speech unit, for example, classifies the category of the conversation. For example, the speech unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The speech unit also applies different speech algorithms depending on the category of the conversation. For example, the speech unit applies a business speech algorithm to speech at a business meeting. The speech unit can also apply a project management speech algorithm to speech at a project meeting. Furthermore, the speech unit can apply a team management speech algorithm to speech at a team meeting. In this way, by applying different speech algorithms depending on the category of the conversation, the management of speech is made more efficient. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the category of the conversation to a generation AI and cause the generation AI to apply the speech algorithm.

[0043] The speech unit can improve speech accuracy by referring to the user's past speech history when speaking. The speech unit, for example, analyzes the user's past speech history. For example, the speech unit analyzes patterns of content that the user has previously spoken and automatically produces similar speech. The speech unit can also prioritize content that the user frequently speaks to improve accuracy. Furthermore, the speech unit can also suggest an optimal speech method based on the user's past speech history. This improves speech accuracy by referring to the user's past speech history. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the user's past speech history into a generation AI and cause the generation AI to improve speech accuracy.

[0044] The summarization unit can adjust the level of detail of the summary based on the importance of the conversation when generating a summary. The summarization unit, for example, evaluates the importance of the conversation. For example, the summarization unit evaluates the importance based on the frequency of utterances and the relevance of the content. The summarization unit also adjusts the level of detail of the summary based on the importance of the conversation. For example, the summarization unit summarizes important meetings in detail and includes all necessary information. The summarization unit can also simplify summarization of general conversations and include only necessary information. Furthermore, the summarization unit can quickly summarize urgent conversations and prioritize the inclusion of important information. In this way, important information can be summarized in detail by adjusting the level of detail of the summary based on the importance of the conversation. Some or all of the above-mentioned processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the importance of the conversation to the generation AI and have the generation AI adjust the level of detail of the summary.

[0045] The summarization unit can apply different summarization algorithms depending on the category of the conversation when generating a summary. The summarization unit, for example, classifies the category of the conversation. For example, the summarization unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The summarization unit also applies different summarization algorithms depending on the category of the conversation. For example, the summarization unit applies a business summarization algorithm to summarize a business meeting. The summarization unit can also apply a project management summarization algorithm to summarize a project meeting. Furthermore, the summarization unit can apply a team management summarization algorithm to summarize a team meeting. In this way, by applying different summarization algorithms depending on the category of the conversation, the accuracy of the summary is improved. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the category of the conversation to the generation AI and cause the generation AI to apply the summarization algorithm.

[0046] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, analyzes the user's past summarization results. For example, the summarization unit analyzes patterns of content previously summarized by the user and automatically generates similar summaries. The summarization unit can also prioritize summarizing content that the user frequently summarizes, thereby improving accuracy. Furthermore, the summarization unit can suggest an optimal summarization method based on the user's past summarization results. This improves the accuracy of the summary by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input the user's past summarization results into the generation AI and have the generation AI improve the accuracy of the summary.

[0047] The video generation unit can adjust the level of detail of the video based on the importance of the conversation when generating the video. The video generation unit, for example, evaluates the importance of the conversation. For example, the video generation unit evaluates the importance based on the frequency of utterances and the relevance of the content. The video generation unit also adjusts the level of detail of the video based on the importance of the conversation. For example, the video generation unit generates detailed video of an important meeting and includes all necessary information. The video generation unit can also generate simplified video of a general conversation and include only the necessary information. Furthermore, the video generation unit can quickly generate video of an urgent conversation and prioritize the inclusion of important information. In this way, important information can be visualized in detail by adjusting the level of detail of the video based on the importance of the conversation. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the importance of the conversation to a generation AI and have the generation AI adjust the level of detail of the video.

[0048] The image generation unit can apply different image generation algorithms depending on the category of the conversation when generating the image. The image generation unit, for example, classifies the category of the conversation. For example, the image generation unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The image generation unit also applies different image generation algorithms depending on the category of the conversation. For example, the image generation unit applies a business image generation algorithm to video of a business meeting. The image generation unit can also apply a project management image generation algorithm to video of a project meeting. Furthermore, the image generation unit can apply a team management image generation algorithm to video of a team meeting. In this way, by applying different image generation algorithms depending on the category of the conversation, the accuracy of the image is improved. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the category of the conversation to a generation AI and cause the generation AI to apply the image generation algorithm.

[0049] When generating an image, the image generation unit can improve the accuracy of the image by referring to the user's past image generation history. The image generation unit, for example, analyzes the user's past image generation history. For example, the image generation unit analyzes patterns of images generated by the user in the past and automatically generates similar images. The image generation unit can also prioritize generating images that the user frequently generates, thereby improving accuracy. Furthermore, the image generation unit can also suggest an optimal image generation method based on the user's past image generation history. In this way, the accuracy of the image is improved by referring to the user's past image generation history. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the user's past image generation history into the generation AI and cause the generation AI to improve the accuracy of the image.

[0050] The video generation unit can determine the priority of videos based on the submission time of the conversations when generating the videos. The video generation unit, for example, evaluates the submission time of the conversations. For example, the video generation unit evaluates the submission time based on the start time and end time of the conversations. The video generation unit also determines the priority of videos based on the submission time of the conversations. For example, the video generation unit prioritizes generating videos of the most recent meetings and postpones older videos. The video generation unit can also prioritize generating videos of urgent conversations and postpone general conversations. Furthermore, the video generation unit can prioritize generating videos of important conversations and postpone other conversations. In this way, by determining the priority of videos based on the submission time of the conversations, the latest information can be visualized preferentially. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the submission time of the conversations to a generation AI and have the generation AI determine the priority of the videos.

[0051] The video generation unit can adjust the order of videos based on the relevance of the conversations when generating videos. The video generation unit, for example, evaluates the relevance of the conversations. For example, the video generation unit evaluates the relevance based on common topics and the relationships between speakers. The video generation unit also adjusts the order of videos based on the relevance of the conversations. For example, the video generation unit generates videos by grouping related conversations together to provide necessary information all at once. The video generation unit can also generate videos with priority for related conversations to make them easier to refer to later. Furthermore, the video generation unit can suggest an optimal video generation method based on the related conversations. In this way, by adjusting the order of videos based on the relevance of the conversations, related information can be provided all at once. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the relevance of the conversations to a generation AI and have the generation AI adjust the order of the videos.

[0052] When generating a video, the video generation unit can adjust the use of technical terms in the video according to the user's level of expertise. The video generation unit, for example, evaluates the user's level of expertise. For example, the video generation unit evaluates the user's level of expertise based on the user's occupation and past learning history. The video generation unit also adjusts the use of technical terms in the video according to the user's level of expertise. For example, the video generation unit generates a video using detailed technical terms for a user with high technical expertise. The video generation unit can also generate a video using simplified terms for a user with low technical expertise. Furthermore, the video generation unit can suggest an optimal video generation method according to the user's level of expertise. In this way, by adjusting the use of technical terms in the video according to the user's level of expertise, a more understandable video is provided. Some or all of the above-described processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The conference automation system may further include a translation unit. The translation unit can translate the content spoken during a conference into other languages ​​in real time. For example, the content of a conference held in English may be translated into Japanese and provided to participants. The translation unit may also translate a summary of the content after the conference into multiple languages ​​and provide it to participants who speak different languages. Furthermore, the translation unit may translate chat messages during a conference in real time to facilitate communication between participants who speak different languages. This allows participants who speak different languages ​​to participate in the same conference and communicate smoothly.

[0055] The conference automation system can further include an annotation unit. The annotation unit can add annotations in real time to the content spoken during the conference. For example, it can automatically add materials and links related to the content spoken so that participants can refer to them immediately. The annotation unit can also add annotations to the content summarized after the conference to provide important points and supplementary information. The annotation unit can also add annotations to chat messages during the conference to provide related information. This makes the content of the conference easier to understand and allows participants to quickly obtain the information they need.

[0056] The meeting automation system can also be equipped with a reminder module, which can remind participants of important tasks and action items before and after the meeting. For example, before the meeting, it can remind participants to prepare the agenda and materials, allowing them to prepare in advance. After the meeting, it can remind participants of decisions made and next action items, allowing them to remember to carry them out. Furthermore, the reminder module can adjust the timing of reminders taking into account the schedules of participants. This allows for efficient meeting preparation and follow-up, maximizing the effectiveness of the meeting.

[0057] The meeting automation system can further include an agenda management unit. The agenda management unit can set the agenda before the meeting and share it with participants. For example, it can set the meeting's purpose, agenda, and time allocation in advance and notify participants. The agenda management unit can also track the progress of the agenda in real time during the meeting and check whether it is proceeding as planned. Furthermore, the agenda management unit can summarize the progress and decisions made for each agenda item after the meeting and use this information to plan the next meeting. This allows meetings to proceed smoothly and discussions to be held efficiently.

[0058] The conference automation system can further include an archive unit. The archive unit can store records of past conferences for a long period of time and make them available for reference as needed. For example, audio data, video data, and minutes of conferences can be archived and later searched for and referenced. The archive unit can also classify the contents of conferences by keywords and tags, enabling efficient searches. Furthermore, the archive unit can analyze data from past conferences and extract trends and patterns. This allows past conference records to be effectively utilized and can be used to plan future conferences.

[0059] The conference automation system may further include a security unit. The security unit can protect data during and after the conference to prevent confidential information from being leaked. For example, the security unit can encrypt conference audio and video data to protect it from unauthorized access. The security unit can also authenticate conference participants to ensure that only authorized users can participate in the conference. Furthermore, the security unit can regularly back up conference records to prevent data loss. This securely protects conference data and reduces the risk of confidential information being leaked.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The storage unit stores documents, communication tools, emails, and conversation histories. Documents include PDF files and presentation materials, communication tools include chat apps and video conferencing tools, emails include text emails and HTML emails, and conversation histories include audio data and text data. Step 2: The tracking unit follows the flow of the conversation in real time based on the information stored by the storage unit. The tracking unit uses voice recognition technology to analyze the audio of the meeting and understand the content of the conversation. It can also analyze the context of the conversation using natural language processing technology. Step 3: The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The speech unit searches the database for an appropriate response, synthesizes the user's voice using speech synthesis technology, and automatically speaks the response. Step 4: The summarization unit summarizes what was said by the speech unit. The summarization unit analyzes the audio data of the meeting, extracts important points, and creates a summary. Keyword extraction technology can also be used to extract important information. Step 5: The video generation unit generates camera footage based on the content summarized by the summarization unit. The video generation unit synthesizes the user's face and facial expressions to create footage that looks as if the user is attending a meeting. The video is generated using facial recognition technology and facial expression generation algorithms.

[0062] (Example 2) A meeting automation system according to an embodiment of the present invention stores documents, communication tools, emails, and conversation histories, tracks the flow of conversation in real time, automates speech, summarizes the meeting content, and generates camera footage. The meeting automation system stores the documents, communication tools, emails, and conversation histories owned by the user in a database (DB). Next, the system tracks the flow of conversation in real time during a meeting. When the user's speech is needed, a generation AI references the DB, synthesizes the user's voice, and automatically speaks. After the meeting, the meeting content is summarized, allowing even non-attendees to understand the meeting content in five minutes. Furthermore, when camera footage is needed, a video generation AI generates camera footage in real time that appears as if the user is speaking. Furthermore, it is possible to assign an agenda and have the MTG optimizer AIs discuss and reach a conclusion. For example, the meeting automation system stores the documents, communication tools, emails, and conversation histories owned by the user in a DB. For example, the DB stores emails sent and received by the user and conversation history via chat tools. Next, the meeting automation system tracks the flow of conversation in real time during a meeting. The generation AI analyzes the audio of a meeting and understands the content of the conversation. For example, if someone asks a question during a meeting, it searches the database for an appropriate answer and synthesizes the user's voice to automatically speak it. This allows users to automate their own speech during the meeting. Next, the meeting automation system summarizes the meeting content after the meeting. The generation AI analyzes the meeting audio data, extracts key points, and creates a summary. For example, it summarizes the meeting agenda, decisions, and next action items and provides them to the user. This allows users to quickly understand the meeting content even if they are not in attendance. In addition, if camera footage is required, the meeting automation system uses the video generation AI to generate camera footage in real time, making it appear as if the user is speaking. For example, even if a user cannot attend a meeting, the video generation AI synthesizes the user's face and facial expressions to create a video that makes it appear as if the user is actually attending the meeting. This allows users to participate in meetings remotely.Furthermore, the meeting automation system can also provide an agenda and have MTG optimizer AIs discuss it among themselves to reach a conclusion. For example, multiple AIs can discuss a specific agenda and reach an optimal conclusion. This allows users to proceed with meetings efficiently. This allows the meeting automation system to automate meeting utterances and summaries, and efficiently grasp the meeting content. For example, even if a user is not present at the meeting, the meeting content can be grasped in a short amount of time. Users can also participate in meetings remotely, allowing meetings to proceed efficiently.

[0063] A conference automation system according to an embodiment includes a storage unit, a tracking unit, a speech unit, a summarizing unit, and a video generation unit. The storage unit stores materials, communication tools, emails, and conversation histories. The materials include, for example, PDF files and presentation materials. The communication tools include, for example, chat apps and video conferencing tools. The emails include, for example, text emails and HTML emails. The conversation histories include, for example, voice data and text data. The tracking unit tracks the flow of conversation in real time based on the information stored by the storage unit. The tracking unit, for example, uses speech recognition technology to analyze the audio of the conference and understand the content of the conversation. The tracking unit can also analyze the context of the conversation using natural language processing technology. The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The speech unit, for example, searches for an appropriate answer from a database, synthesizes the user's voice, and automatically speaks it. The speech unit synthesizes the user's voice using speech synthesis technology. The summarizing unit summarizes the content spoken by the speaking unit. The summarizing unit, for example, analyzes audio data of a conference and extracts important points to create a summary. The summarizing unit can also extract important information using keyword extraction technology. The video generating unit generates camera video based on the content summarized by the summarizing unit. The video generating unit, for example, synthesizes a user's face and facial expression to generate video that makes it appear as if the user is attending the conference. The video generating unit generates video using face recognition technology and facial expression generation algorithms. As a result, the conference automation system according to the embodiment automates the speech and summarization of a conference, and can efficiently grasp the content of the conference. For example, even if a user is not attending the conference, the content of the conference can be grasped in a short time. Furthermore, a user can participate in the conference remotely, allowing the conference to proceed efficiently.

[0064] The storage unit can store minutes of past meetings, email content, and chat history. The storage unit stores, for example, minutes of past meetings in text format. The minutes include the meeting agenda, comments, decisions, etc. The storage unit can also store the content of past emails in text format or HTML format. The content of emails includes the sender, recipient, subject, body, etc. The storage unit can also store the history of past chats in text format. The chat history includes the speaker, comment content, and comment time, etc. This enables centralized management of information by storing the minutes of past meetings, email content, and chat history. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI, for example. For example, the storage unit can input the minutes of past meetings into a generation AI and have the generation AI summarize the minutes.

[0065] The tracking unit can analyze the audio of the conference and understand the content of the conversation. The tracking unit can analyze the audio of the conference using, for example, speech recognition technology. For example, the tracking unit can convert the audio data of the conference into text data. The tracking unit can also improve the quality of the audio data using noise reduction technology. For example, the tracking unit can remove background noise and make the speaker's voice clearer. The tracking unit can also understand the content of the conversation using natural language processing technology. For example, the tracking unit can analyze the context of the conversation and understand the intention of the utterances. This allows the flow of the conversation to be followed in real time by analyzing the audio of the conference and understanding the content of the conversation. Some or all of the above-mentioned processing in the tracking unit can be performed using, for example, AI, or can be performed without using AI. For example, the tracking unit can input the audio data of the conference to a generation AI and have the generation AI understand the content of the conversation.

[0066] The speech unit can search for an appropriate answer from the database, synthesize the user's voice, and automatically speak it. The speech unit, for example, searches for an appropriate answer from the database. For example, the speech unit refers to an FAQ database to search for an appropriate answer to a question. The speech unit can also generate an appropriate answer using a machine learning model. For example, the speech unit generates an answer to a question using a model that has learned from past conversation data. The speech unit also synthesizes the user's voice using speech synthesis technology. For example, the speech unit extracts features of the user's voice and generates synthetic speech. This allows the speech unit to search for an appropriate answer from the database, synthesize the user's voice, and automatically speak it, thereby automating the user's speech. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without AI. For example, the speech unit can input the answer searched for from the database to a generation AI and have the generation AI synthesize the user's voice.

[0067] The summarization unit can analyze the audio data of a meeting, extract important points, and create a summary. The summarization unit, for example, analyzes the audio data of the meeting. For example, the summarization unit converts the audio data into text data using speech recognition technology. The summarization unit can also extract important points using keyword extraction technology. For example, the summarization unit extracts the meeting agenda, decisions, next action items, etc. The summarization unit also creates a summary using a summarization algorithm. For example, the summarization unit summarizes the content of the meeting using an abstract summarization algorithm. In this way, by analyzing the audio data of the meeting, extracting important points, and creating a summary, the content of the meeting can be understood in a short period of time. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the audio data to a generation AI and have the generation AI generate a summary.

[0068] The image generation unit can synthesize the user's face and facial expression to generate an image that makes it appear as if the user is attending a meeting. The image generation unit synthesizes, for example, the user's face and facial expression. For example, the image generation unit extracts the user's facial features using facial recognition technology to generate a synthetic image. The image generation unit can also synthesize the user's facial expression using a facial expression generation algorithm. For example, the image generation unit generates facial expressions in real time based on the user's facial expression data. This enables remote participation in a meeting by synthesizing the user's face and facial expression to generate an image that makes it appear as if the user is attending a meeting. Some or all of the above-described processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the user's facial feature data into a generation AI and cause the generation AI to generate a synthetic image.

[0069] The storage unit can estimate the user's emotions and determine the priority of information to be stored based on the estimated user's emotions. The storage unit, for example, estimates the user's emotions using emotion recognition technology. For example, the storage unit analyzes the user's facial expressions to estimate the emotions. The storage unit can also estimate the user's emotions using voice analysis technology. For example, the storage unit analyzes the tone and speed of the user's voice to estimate the emotions. Furthermore, the storage unit determines the priority of information to be stored based on the estimated user's emotions. For example, when the user is feeling stressed, the storage unit prioritizes storing important information and postpones unnecessary information. Furthermore, when the user is relaxed, the storage unit stores detailed information as well for later reference. In this way, by determining the priority of information to be stored based on the user's emotions, important information can be prioritized and stored. Some or all of the above-described processing in the storage unit may be performed using AI, for example, or without AI. For example, the storage unit may input the user's emotion data into a generation AI and have the generation AI determine the priority of information.

[0070] The storage unit can adjust the level of detail of storage based on the importance of the information when storing the information. The storage unit, for example, evaluates the importance of the information. For example, the storage unit evaluates the importance based on the frequency of use and relevance of the information. The storage unit also adjusts the level of detail of storage based on the importance of the information. For example, the storage unit stores minutes of important meetings in detail to make them easier to search later. The storage unit can also simplify and store the content of general emails to extract only the necessary information. Furthermore, the storage unit can prioritize and store important messages in chat history, and simplify and store other messages. In this way, important information can be stored in detail by adjusting the level of detail of storage based on the importance of the information. Some or all of the above-mentioned processing in the storage unit may be performed using, or without, AI. For example, the storage unit can input the importance of the information to a generation AI and cause the generation AI to adjust the level of detail of storage.

[0071] The storage unit can apply different storage algorithms depending on the category of information when storing the information. The storage unit, for example, classifies the category of information. For example, the storage unit classifies the information into categories such as text data, audio data, and image data. The storage unit also applies different storage algorithms depending on the category of information. For example, the storage unit stores meeting minutes using a text analysis algorithm. The storage unit can also store email content using a natural language processing algorithm. Furthermore, the storage unit can store chat history using a keyword extraction algorithm. In this way, by applying different storage algorithms depending on the category of information, information management becomes more efficient. Some or all of the above-mentioned processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the category of information to a generation AI and cause the generation AI to apply a storage algorithm.

[0072] The storage unit can improve the accuracy of storage by referring to the user's past storage history when storing data. The storage unit, for example, analyzes the user's past storage history. For example, the storage unit analyzes patterns of information previously stored by the user and automatically classifies similar information. The storage unit can also prioritize storing information frequently referenced by the user to make it easier to search. Furthermore, the storage unit can suggest an optimal storage method based on the user's past storage history. This improves the accuracy of storage by referring to the user's past storage history. Some or all of the above-described processing in the storage unit may be performed using, for example, AI, or may be performed without using AI. For example, the storage unit can input the user's past storage history into a generation AI and have the generation AI improve the accuracy of storage.

[0073] The tracking unit can estimate the user's emotions and adjust the flow of conversation based on the estimated user's emotions. The tracking unit estimates the user's emotions using, for example, emotion recognition technology. For example, the tracking unit analyzes the user's facial expressions to estimate the emotions. The tracking unit can also estimate the user's emotions using voice analysis technology. For example, the tracking unit analyzes the tone and speed of the user's voice to estimate the emotions. The tracking unit also adjusts the flow of conversation based on the estimated user's emotions. For example, the tracking unit slows down the flow of conversation when the user is nervous. The tracking unit can also smoothly advance the flow of conversation when the user is relaxed. In this way, adjusting the flow of conversation based on the user's emotions allows the conversation to proceed smoothly. Some or all of the above-described processing in the tracking unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracking unit can input the user's emotion data to a generation AI and cause the generation AI to adjust the flow of conversation.

[0074] The tracking unit can adjust the level of detail of tracking based on the importance of the conversation during tracking. The tracking unit, for example, evaluates the importance of the conversation. For example, the tracking unit evaluates the importance based on the frequency of utterances and the relevance of the content. The tracking unit also adjusts the level of detail of tracking based on the importance of the conversation. For example, the tracking unit follows important meeting conversations in detail and records all necessary information. The tracking unit can also simplify and follow general conversations and record only necessary information. Furthermore, the tracking unit can quickly follow urgent conversations and prioritize recording important information. In this way, important conversations can be tracked in detail by adjusting the level of detail of tracking based on the importance of the conversation. Some or all of the above-mentioned processing in the tracking unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracking unit can input the importance of the conversation to a generation AI and cause the generation AI to adjust the level of detail of tracking.

[0075] The tracking unit can apply different tracking algorithms depending on the category of the conversation during tracking. The tracking unit, for example, classifies the category of the conversation. For example, the tracking unit classifies the category into business conversation, everyday conversation, technical conversation, etc. Furthermore, the tracking unit applies different tracking algorithms depending on the category of the conversation. For example, the tracking unit applies a business tracking algorithm to a conversation in a business meeting. Furthermore, the tracking unit can also apply a project management tracking algorithm to a conversation in a project meeting. Furthermore, the tracking unit can apply a team management tracking algorithm to a conversation in a team meeting. In this way, by applying different tracking algorithms depending on the category of the conversation, conversation management becomes more efficient. Some or all of the above-mentioned processing in the tracking unit may be performed using, for example, AI, or may be performed without using AI. For example, the tracking unit can input the category of the conversation to a generation AI and cause the generation AI to apply the tracking algorithm.

[0076] The tracking unit can improve the accuracy of tracking by referring to the user's past tracking history when tracking. The tracking unit, for example, analyzes the user's past tracking history. For example, the tracking unit analyzes patterns of conversations that the user has followed in the past and automatically follows similar conversations. The tracking unit can also prioritize following conversations that the user frequently follows, thereby improving accuracy. Furthermore, the tracking unit can also suggest an optimal tracking method based on the user's past tracking history. In this way, by referring to the user's past tracking history, the accuracy of tracking is improved. Some or all of the above-mentioned processing in the tracking unit may be performed, for example, using AI, or may be performed without using AI. For example, the tracking unit can input the user's past following history to a generation AI and cause the generation AI to improve the accuracy of tracking.

[0077] The speech unit can estimate the user's emotions and adjust the manner of speech expression based on the estimated user's emotions. The speech unit can estimate the user's emotions using, for example, emotion recognition technology. For example, the speech unit can analyze the user's facial expressions to estimate the emotions. The speech unit can also estimate the user's emotions using voice analysis technology. For example, the speech unit can analyze the tone and speed of the user's voice to estimate the emotions. The speech unit can also adjust the manner of speech expression based on the estimated user's emotions. For example, the speech unit can speak in a calm voice if the user is nervous. The speech unit can also speak in a bright voice if the user is relaxed. This allows for more appropriate speech by adjusting the manner of speech expression based on the user's emotions. Some or all of the above-described processing in the speech unit can be performed using, for example, AI, or without AI. For example, the speech unit can input the user's emotion data into a generation AI and cause the generation AI to adjust the manner of speech expression.

[0078] The speech unit can adjust the level of detail of the speech when speaking based on the importance of the conversation. The speech unit, for example, evaluates the importance of the conversation. For example, the speech unit evaluates the importance based on the frequency of utterances and the relevance of the content. The speech unit also adjusts the level of detail of the speech based on the importance of the conversation. For example, the speech unit can provide detailed speech for important meetings and convey all necessary information. The speech unit can also simplify speech for general conversations and convey only the necessary information. Furthermore, the speech unit can provide rapid speech for urgent conversations and prioritize the conveyance of important information. In this way, important information can be conveyed in detail by adjusting the level of detail of the speech based on the importance of the conversation. Some or all of the above-mentioned processing in the speech unit may be performed using AI, for example, or may be performed without using AI. For example, the speech unit can input the importance of the conversation to a generation AI and cause the generation AI to adjust the level of detail of the speech.

[0079] The speech unit can apply different speech algorithms depending on the category of the conversation when speaking. The speech unit, for example, classifies the category of the conversation. For example, the speech unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The speech unit also applies different speech algorithms depending on the category of the conversation. For example, the speech unit applies a business speech algorithm to speech at a business meeting. The speech unit can also apply a project management speech algorithm to speech at a project meeting. Furthermore, the speech unit can apply a team management speech algorithm to speech at a team meeting. In this way, by applying different speech algorithms depending on the category of the conversation, the management of speech is made more efficient. Some or all of the above-mentioned processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the category of the conversation to a generation AI and cause the generation AI to apply the speech algorithm.

[0080] The speech unit can improve speech accuracy by referring to the user's past speech history when speaking. The speech unit, for example, analyzes the user's past speech history. For example, the speech unit analyzes patterns of content that the user has previously spoken and automatically produces similar speech. The speech unit can also prioritize content that the user frequently speaks to improve accuracy. Furthermore, the speech unit can also suggest an optimal speech method based on the user's past speech history. This improves speech accuracy by referring to the user's past speech history. Some or all of the above-described processing in the speech unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech unit can input the user's past speech history into a generation AI and cause the generation AI to improve speech accuracy.

[0081] The summarization unit can estimate the user's emotion and adjust the summary presentation style based on the estimated user's emotion. The summarization unit can estimate the user's emotion using, for example, emotion recognition technology. For example, the summarization unit can analyze the user's facial expressions to estimate the emotion. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the tone and speed of the user's voice to estimate the emotion. The summarization unit can also adjust the summary presentation style based on the estimated user's emotion. For example, the summarization unit can provide a simple, highly visible summary when the user is nervous. The summarization unit can also provide a summary that includes detailed information when the user is relaxed. This allows for a more appropriate summary to be provided by adjusting the summary presentation style based on the user's emotion. Some or all of the above-described processing in the summarization unit can be performed using, for example, AI, or without AI. For example, the summarization unit can input the user's emotion data into a generation AI and cause the generation AI to adjust the summary presentation style.

[0082] The summarization unit can adjust the level of detail of the summary based on the importance of the conversation when generating a summary. The summarization unit, for example, evaluates the importance of the conversation. For example, the summarization unit evaluates the importance based on the frequency of utterances and the relevance of the content. The summarization unit also adjusts the level of detail of the summary based on the importance of the conversation. For example, the summarization unit summarizes important meetings in detail and includes all necessary information. The summarization unit can also simplify summarization of general conversations and include only necessary information. Furthermore, the summarization unit can quickly summarize urgent conversations and prioritize the inclusion of important information. In this way, important information can be summarized in detail by adjusting the level of detail of the summary based on the importance of the conversation. Some or all of the above-mentioned processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input the importance of the conversation to the generation AI and have the generation AI adjust the level of detail of the summary.

[0083] The summarization unit can apply different summarization algorithms depending on the category of the conversation when generating a summary. The summarization unit, for example, classifies the category of the conversation. For example, the summarization unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The summarization unit also applies different summarization algorithms depending on the category of the conversation. For example, the summarization unit applies a business summarization algorithm to summarize a business meeting. The summarization unit can also apply a project management summarization algorithm to summarize a project meeting. Furthermore, the summarization unit can apply a team management summarization algorithm to summarize a team meeting. In this way, by applying different summarization algorithms depending on the category of the conversation, the accuracy of the summary is improved. Some or all of the above-mentioned processing in the summarization unit may be performed using, for example, AI, or may be performed without using AI. For example, the summarization unit can input the category of the conversation to the generation AI and cause the generation AI to apply the summarization algorithm.

[0084] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, analyzes the user's past summarization results. For example, the summarization unit analyzes patterns of content previously summarized by the user and automatically generates similar summaries. The summarization unit can also prioritize summarizing content that the user frequently summarizes, thereby improving accuracy. Furthermore, the summarization unit can suggest an optimal summarization method based on the user's past summarization results. This improves the accuracy of the summary by referring to the user's past summarization results. Some or all of the above-mentioned processing in the summarization unit may be performed, for example, using AI, or may be performed without using AI. For example, the summarization unit can input the user's past summarization results into the generation AI and have the generation AI improve the accuracy of the summary.

[0085] The image generation unit can estimate the user's emotion and adjust the image presentation method based on the estimated user's emotion. The image generation unit estimates the user's emotion using, for example, emotion recognition technology. For example, the image generation unit analyzes the user's facial expression to estimate the emotion. The image generation unit can also estimate the user's emotion using voice analysis technology. For example, the image generation unit analyzes the tone and speed of the user's voice to estimate the emotion. Furthermore, the image generation unit adjusts the image presentation method based on the estimated user's emotion. For example, the image generation unit can provide an image with calm colors when the user is nervous. Furthermore, the image generation unit can provide an image with bright colors when the user is relaxed. In this way, by adjusting the image presentation method based on the user's emotion, a more appropriate image is provided. Some or all of the above-described processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the user's emotion data into a generation AI and cause the generation AI to adjust the image presentation method.

[0086] The video generation unit can adjust the level of detail of the video based on the importance of the conversation when generating the video. The video generation unit, for example, evaluates the importance of the conversation. For example, the video generation unit evaluates the importance based on the frequency of utterances and the relevance of the content. The video generation unit also adjusts the level of detail of the video based on the importance of the conversation. For example, the video generation unit generates detailed video of an important meeting and includes all necessary information. The video generation unit can also generate simplified video of a general conversation and include only the necessary information. Furthermore, the video generation unit can quickly generate video of an urgent conversation and prioritize the inclusion of important information. In this way, important information can be visualized in detail by adjusting the level of detail of the video based on the importance of the conversation. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the importance of the conversation to a generation AI and have the generation AI adjust the level of detail of the video.

[0087] The image generation unit can apply different image generation algorithms depending on the category of the conversation when generating the image. The image generation unit, for example, classifies the category of the conversation. For example, the image generation unit classifies the category into business conversation, everyday conversation, technical conversation, etc. The image generation unit also applies different image generation algorithms depending on the category of the conversation. For example, the image generation unit applies a business image generation algorithm to video of a business meeting. The image generation unit can also apply a project management image generation algorithm to video of a project meeting. Furthermore, the image generation unit can apply a team management image generation algorithm to video of a team meeting. In this way, by applying different image generation algorithms depending on the category of the conversation, the accuracy of the image is improved. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the category of the conversation to a generation AI and cause the generation AI to apply the image generation algorithm.

[0088] When generating an image, the image generation unit can improve the accuracy of the image by referring to the user's past image generation history. The image generation unit, for example, analyzes the user's past image generation history. For example, the image generation unit analyzes patterns of images generated by the user in the past and automatically generates similar images. The image generation unit can also prioritize generating images that the user frequently generates, thereby improving accuracy. Furthermore, the image generation unit can also suggest an optimal image generation method based on the user's past image generation history. In this way, the accuracy of the image is improved by referring to the user's past image generation history. Some or all of the above-mentioned processing in the image generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the image generation unit can input the user's past image generation history into the generation AI and cause the generation AI to improve the accuracy of the image.

[0089] The video generation unit can estimate the user's emotions and adjust the length of the video based on the estimated user's emotions. The video generation unit can estimate the user's emotions using, for example, emotion recognition technology. For example, the video generation unit can analyze the user's facial expressions to estimate the emotions. The video generation unit can also estimate the user's emotions using voice analysis technology. For example, the video generation unit can analyze the tone and speed of the user's voice to estimate the emotions. The video generation unit can also adjust the length of the video based on the estimated user's emotions. For example, the video generation unit can provide a short, to-the-point video when the user is in a hurry. The video generation unit can also provide a longer video with detailed explanations when the user is relaxed. In this way, adjusting the length of the video based on the user's emotions provides a more appropriate video. Some or all of the above-described processing in the video generation unit can be performed using, for example, AI, or without AI. For example, the video generation unit can input the user's emotion data into a generation AI and have the generation AI adjust the length of the video.

[0090] The video generation unit can determine the priority of videos based on the submission time of the conversations when generating the videos. The video generation unit, for example, evaluates the submission time of the conversations. For example, the video generation unit evaluates the submission time based on the start time and end time of the conversations. The video generation unit also determines the priority of videos based on the submission time of the conversations. For example, the video generation unit prioritizes generating videos of the most recent meetings and postpones older videos. The video generation unit can also prioritize generating videos of urgent conversations and postpone general conversations. Furthermore, the video generation unit can prioritize generating videos of important conversations and postpone other conversations. In this way, by determining the priority of videos based on the submission time of the conversations, the latest information can be visualized preferentially. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the submission time of the conversations to a generation AI and have the generation AI determine the priority of the videos.

[0091] The video generation unit can adjust the order of videos based on the relevance of the conversations when generating videos. The video generation unit, for example, evaluates the relevance of the conversations. For example, the video generation unit evaluates the relevance based on common topics and the relationships between speakers. The video generation unit also adjusts the order of videos based on the relevance of the conversations. For example, the video generation unit generates videos by grouping related conversations together to provide necessary information all at once. The video generation unit can also generate videos with priority for related conversations to make them easier to refer to later. Furthermore, the video generation unit can suggest an optimal video generation method based on the related conversations. In this way, by adjusting the order of videos based on the relevance of the conversations, related information can be provided all at once. Some or all of the above-mentioned processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the relevance of the conversations to a generation AI and have the generation AI adjust the order of the videos.

[0092] When generating a video, the video generation unit can adjust the use of technical terms in the video according to the user's level of expertise. The video generation unit, for example, evaluates the user's level of expertise. For example, the video generation unit evaluates the user's level of expertise based on the user's occupation and past learning history. The video generation unit also adjusts the use of technical terms in the video according to the user's level of expertise. For example, the video generation unit generates a video using detailed technical terms for a user with high technical expertise. The video generation unit can also generate a video using simplified terms for a user with low technical expertise. Furthermore, the video generation unit can suggest an optimal video generation method according to the user's level of expertise. In this way, by adjusting the use of technical terms in the video according to the user's level of expertise, a more understandable video is provided. Some or all of the above-described processing in the video generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the video generation unit can input the user's level of expertise into the generation AI and cause the generation AI to adjust the use of technical terms. === Hard Collateral 1-1 === Each of the multiple elements including the storage unit, tracking unit, speech unit, summarizing unit, and image generating unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the storage unit is realized by the database 24 of the data processing device 12. The tracking unit is realized, for example, by the processor 46 of the smart device 14 and the specific processing unit 290 of the data processing device 12. The speech unit is realized, for example, by the control unit 46A of the smart device 14 and the specific processing unit 290 of the data processing device 12. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The image generating unit is realized, for example, by the camera 42 of the smart device 14 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned storage unit, tracking unit, speaking unit, summarizing unit, and image generating unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the storage unit is realized by the database 24 of the data processing device 12. The tracking unit is realized, for example, by the processor 46 of the smart glasses 214 and the specific processing unit 290 of the data processing device 12. The speaking unit is realized, for example, by the control unit 46A of the smart glasses 214 and the specific processing unit 290 of the data processing device 12. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The image generating unit is realized, for example, by the camera 42 of the smart glasses 214 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned storage unit, tracking unit, speaking unit, summarizing unit, and image generating unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the storage unit is realized by the database 24 of the data processing device 12. The tracking unit is realized, for example, by the processor 46 of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12. The speaking unit is realized, for example, by the control unit 46A of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The image generating unit is realized, for example, by the camera 42 of the headset type terminal 314 and the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned storage unit, tracking unit, speaking unit, summarizing unit, and image generating unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the storage unit is realized by the database 24 of the data processing device 12. The tracking unit is realized, for example, by the processor 46 of the robot 414 and the specific processing unit 290 of the data processing device 12. The speaking unit is realized, for example, by the control unit 46A of the robot 414 and the specific processing unit 290 of the data processing device 12. The summarizing unit is realized, for example, by the specific processing unit 290 of the data processing device 12. The image generating unit is realized, for example, by the camera 42 of the robot 414 and the specific processing unit 290 of the data processing device 12.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The conference automation system may further include a translation unit. The translation unit can translate the content spoken during a conference into other languages ​​in real time. For example, the content of a conference held in English may be translated into Japanese and provided to participants. The translation unit may also translate a summary of the content after the conference into multiple languages ​​and provide it to participants who speak different languages. Furthermore, the translation unit may translate chat messages during a conference in real time to facilitate communication between participants who speak different languages. This allows participants who speak different languages ​​to participate in the same conference and communicate smoothly.

[0095] The conference automation system can further include an annotation unit. The annotation unit can add annotations in real time to the content spoken during the conference. For example, it can automatically add materials and links related to the content spoken so that participants can refer to them immediately. The annotation unit can also add annotations to the content summarized after the conference to provide important points and supplementary information. The annotation unit can also add annotations to chat messages during the conference to provide related information. This makes the content of the conference easier to understand and allows participants to quickly obtain the information they need.

[0096] The meeting automation system can further include a feedback unit. The feedback unit can collect feedback from participants after the meeting and analyze it to improve the quality of the meeting. For example, it can conduct a survey of participants about the content and progress of the meeting and analyze the results. The feedback unit can also analyze participants' comments and actions and suggest areas for improvement. Furthermore, the feedback unit can evaluate participants' satisfaction and stress levels based on emotional data during the meeting and reflect this in the next meeting. This allows for continuous improvement in the quality of meetings.

[0097] The meeting automation system can also be equipped with a reminder module, which can remind participants of important tasks and action items before and after the meeting. For example, before the meeting, it can remind participants to prepare the agenda and materials, allowing them to prepare in advance. After the meeting, it can remind participants of decisions made and next action items, allowing them to remember to carry them out. Furthermore, the reminder module can adjust the timing of reminders taking into account the schedules of participants. This allows for efficient meeting preparation and follow-up, maximizing the effectiveness of the meeting.

[0098] The meeting automation system can further include an insights unit. The insights unit can analyze what is said during the meeting and the behavior of the participants to extract important insights. For example, it can analyze the frequency and content of comments made during the meeting to understand the trends in participants' interests and opinions. The insights unit can also analyze changes in participants' emotions based on emotional data during the meeting and identify factors that affect the progress of the meeting. Furthermore, the insights unit can provide the extracted insights as a report after the meeting, which can be used to plan the next meeting. This allows for a deeper understanding of the content of the meeting and more effective decision-making.

[0099] The meeting automation system can further include an agenda management unit. The agenda management unit can set the agenda before the meeting and share it with participants. For example, it can set the meeting's purpose, agenda, and time allocation in advance and notify participants. The agenda management unit can also track the progress of the agenda in real time during the meeting and check whether it is proceeding as planned. Furthermore, the agenda management unit can summarize the progress and decisions made for each agenda item after the meeting and use this information to plan the next meeting. This allows meetings to proceed smoothly and discussions to be held efficiently.

[0100] The conference automation system can further include a networking unit. The networking unit can support participants in networking during and after the conference. For example, it can match participants with common topics based on the participants' profiles and interests. The networking unit can also support participants in following up after the conference, supporting them in exchanging contact information and setting up the next meeting. Furthermore, the networking unit can match participants with good chemistry based on participants' emotional data, promoting effective communication. This strengthens relationships between participants and expands business opportunities.

[0101] The meeting automation system can further include a training unit. The training unit can provide training to participants before and after the meeting. For example, training can be provided before the meeting to teach knowledge and skills related to the agenda, enabling participants to discuss effectively. The training unit can also point out areas for improvement based on feedback after the meeting and provide training for the next meeting. Furthermore, the training unit can provide relaxation training to reduce stress based on participants' emotional data. This improves the skills of participants and improves the quality of the meeting.

[0102] The conference automation system can further include an archive unit. The archive unit can store records of past conferences for a long period of time and make them available for reference as needed. For example, audio data, video data, and minutes of conferences can be archived and later searched for and referenced. The archive unit can also classify the contents of conferences by keywords and tags, enabling efficient searches. Furthermore, the archive unit can analyze data from past conferences and extract trends and patterns. This allows past conference records to be effectively utilized and can be used to plan future conferences.

[0103] The conference automation system may further include a security unit. The security unit can protect data during and after the conference to prevent confidential information from being leaked. For example, the security unit can encrypt conference audio and video data to protect it from unauthorized access. The security unit can also authenticate conference participants to ensure that only authorized users can participate in the conference. Furthermore, the security unit can regularly back up conference records to prevent data loss. This securely protects conference data and reduces the risk of confidential information being leaked.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The storage unit stores documents, communication tools, emails, and conversation histories. Documents include PDF files and presentation materials, communication tools include chat apps and video conferencing tools, emails include text emails and HTML emails, and conversation histories include audio data and text data. Step 2: The tracking unit follows the flow of the conversation in real time based on the information stored by the storage unit. The tracking unit uses voice recognition technology to analyze the audio of the meeting and understand the content of the conversation. It can also analyze the context of the conversation using natural language processing technology. Step 3: The speech unit automates speech based on the content of the conversation tracked by the tracking unit. The speech unit searches the database for an appropriate response, synthesizes the user's voice using speech synthesis technology, and automatically speaks the response. Step 4: The summarization unit summarizes what was said by the speech unit. The summarization unit analyzes the audio data of the meeting, extracts important points, and creates a summary. Keyword extraction technology can also be used to extract important information. Step 5: The video generation unit generates camera footage based on the content summarized by the summarization unit. The video generation unit synthesizes the user's face and facial expressions to create footage that looks as if the user is attending a meeting. The video is generated using facial recognition technology and facial expression generation algorithms.

[0106] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 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.

[0112] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0117] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0118] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0120] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, a 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.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0150] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0161] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0162] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0167] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0168] 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.

[0169] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0170] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0171] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0172] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0174] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0175] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0176] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0177] [Explanation of symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A storage department that stores documents, communication tools, emails, and conversation histories; a tracking unit that tracks the flow of conversation in real time based on the information stored by the storage unit; a speech unit that automates speech based on the content of the conversation tracked by the tracking unit; a summarizing unit that summarizes the content uttered by the utterance unit; an image generating unit that generates a camera image based on the content summarized by the summarizing unit; Equipped with A system characterized by:

2. The storage unit includes: Keeping minutes of past meetings, emails, and chat histories 2. The system of claim 1.

3. The following unit is Analyzes meeting audio and understands the content of conversations 2. The system of claim 1.

4. The speech unit is Searches for the appropriate answer from the database and automatically speaks it by synthesizing the user's voice 2. The system of claim 1.

5. The summary section Analyzes audio data from meetings, extracts key points, and creates summaries 2. The system of claim 1.

6. The image generation unit Synthesizes the user's face and facial expressions to generate an image that makes it appear as if the user is attending a meeting.

2. The system of claim 1.

7. The storage unit includes: Estimate the user's emotions and prioritize the information to be stored based on the estimated user emotions.

2. The system of claim 1.

8. The storage unit includes: At the time of storage, adjust the granularity of storage based on the importance of the information 2. The system of claim 1.

9. The storage unit includes: During storage, different storage algorithms are applied depending on the category of information.

2. The system of claim 1.

10. The storage unit includes: When storing data, the accuracy of storage is improved by referring to the user's past storage history.

2. The system of claim 1.

Images