system

Abstract

The system according to the embodiment aims to efficiently record the contents of meetings and business negotiations and to automate task management and schedule adjustment. [Solution] A system according to an embodiment includes a speech recognition unit, a generation unit, a monitoring unit, and a calendar creation unit. The speech recognition unit converts speech into text. The generation unit analyzes the text created by the speech recognition unit and automatically creates minutes, ToDo lists, and a WBS. The monitoring unit monitors the progress of tasks created by the generation unit and issues an alert if there is no progress. The calendar creation unit automatically creates a calendar when the next meeting is required based on tasks determined by the monitoring unit to be no progress, and automatically sends it to relevant parties.

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 do not adequately record the contents of meetings and business negotiations efficiently, and do not automate task management and schedule adjustments, so there is room for improvement.

[0005] The system according to the embodiment aims to efficiently record the contents of meetings and business negotiations and to automate task management and schedule adjustment. [Means for solving the problem]

[0006] The system according to the embodiment includes a speech recognition unit, a generation unit, a monitoring unit, and a calendar creation unit. The speech recognition unit converts speech into text. The generation unit analyzes the text created by the speech recognition unit and automatically creates minutes, ToDo lists, and a WBS. The monitoring unit monitors the progress of tasks created by the generation unit and issues an alert if there is no progress. The calendar creation unit automatically creates a calendar when the next meeting is required based on tasks determined by the monitoring unit to be no progress, and automatically sends the calendar to relevant parties. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently record the contents of meetings and business negotiations, and automate task management and schedule adjustment. [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) The automatic conversation recording system according to an embodiment of the present invention transcribes the speech content of business negotiations and meetings with customers in both face-to-face and offline sales, automatically creating meeting minutes, to-do lists, and work breakdown structures. This system uses speech recognition AI to transcribe the conversation content, and then uses generation AI to automatically create meeting minutes, to-do lists, and work breakdown structures from the transcribed content. Furthermore, if there is no progress on a task, the system generates an alert, and when the next meeting is required, automatically creates a calendar and sends it to relevant parties. For example, the system transcribes the conversation content using speech recognition AI. By using the speech recognition AI "Whisper" or a Chrome extension, the conversation content can be transcribed in real time, allowing for accurate recording of the conversation content. Next, the system uses generation AI to automatically create meeting minutes, to-do lists, and work breakdown structures from the transcribed content. The generation AI analyzes the transcribed content and extracts important points and tasks. For example, it can automatically extract action items and deadlines mentioned in the conversation and create to-do lists and work breakdown structures. Furthermore, it generates an alert if there is no progress on a task. The generation AI monitors the progress of tasks and issues alerts for tasks with approaching deadlines or tasks that have not progressed. This makes task management easier and prevents important tasks from being overlooked. It also automatically creates a calendar entry when the next meeting is needed and sends it to relevant parties. The generation AI determines when the next meeting is needed based on the content of the conversation and the progress of the task, and automatically creates a calendar entry. Furthermore, by automatically sending the calendar entry to relevant parties, meeting schedules can be adjusted smoothly. As a result, the automatic conversation recording system improves the efficiency of conversation recording and task management in both face-to-face and offline sales, improving work productivity.

[0029] An automatic conversation content recording system according to an embodiment includes a speech recognition unit, a generation unit, a monitoring unit, and a calendar creation unit. The speech recognition unit converts speech into text. Examples of conversation content include, but are not limited to, business meetings and casual conversations. The speech recognition unit transcribes the conversation content in real time using, for example, the speech recognition AI "Whisper" or a Chrome extension. The speech recognition AI analyzes the speech data and converts it into text data using a deep learning model. For example, the speech recognition AI performs preprocessing of the speech data, such as noise reduction and speech normalization, and then converts the speech into text using a deep learning model. The generation unit analyzes the transcribed content and automatically creates documents such as minutes, to-do lists, and work breakdown structures. For example, the generation unit analyzes the transcribed content using a generation AI and extracts important points and tasks. The generation AI analyzes the text data using natural language processing technology and extracts important information. For example, the generation AI extracts important points based on the frequency of keywords and the importance of the context, and automatically creates "minutes," "ToDo lists," and "WBS." The monitoring unit monitors the progress of tasks generated by the generation unit and issues an alert if there is no progress. The monitoring unit, for example, uses the generation AI to monitor task progress and issues an alert for tasks whose deadlines are approaching or for which there is no progress. The generation AI evaluates progress based on the task completion rate and deadline compliance status and issues an alert. The calendar creation unit automatically creates a calendar when the next meeting is needed based on tasks determined by the monitoring unit to have no progress, and automatically sends it to relevant parties. The calendar creation unit, for example, uses the generation AI to determine when the next meeting is needed based on the content of conversations and the progress of tasks, and automatically creates a calendar. The generation AI analyzes the content of conversations and the progress of tasks to determine when the next meeting is needed. For example, the generation AI predicts when the next meeting is needed based on the progress of tasks, and automatically creates a calendar. This allows the automatic conversation recording system to streamline conversation recording and task management, improving work productivity. For example, accurately recording conversation content is useful for reviewing the content later.In addition, by understanding the progress of tasks in real time, you can prevent important tasks from being overlooked. Furthermore, by automatically determining when the next meeting is needed and creating a calendar, you can smoothly adjust your schedule.

[0030] The speech recognition unit can transcribe conversation content in real time using speech recognition AI. A deep learning model, for example, is used for the speech recognition AI. The deep learning model learns large amounts of speech data to achieve highly accurate speech recognition. For example, the speech recognition AI performs preprocessing of the speech data, such as noise removal and speech normalization, and then converts the speech into text using a deep learning model. The speech recognition AI can, for example, analyze speech data in real time and convert it into text data. This allows for accurate recording by transcribing the conversation content in real time. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input speech data to a generation AI and have the generation AI generate text data from the speech data.

[0031] The generation unit can analyze the transcribed content, extract important points and tasks, and automatically create "minutes," "ToDo lists," "WBS," etc. The generation unit, for example, uses a generation AI to analyze the transcribed content and extract important points and tasks. The generation AI analyzes the text data using natural language processing technology and extracts important information. For example, the generation AI extracts important points based on keyword frequency and context importance, and automatically creates "minutes," "ToDo lists," and "WBS." The generation unit can automatically extract action items and deadlines that come up in conversations and create "ToDo lists" and "WBS." This allows for automatic extraction and efficient management of important points and tasks. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the transcribed content into a generation AI and have the generation AI extract important points and tasks.

[0032] The monitoring unit can monitor the progress of tasks and generate alerts for tasks with approaching deadlines or no progress. The monitoring unit can, for example, use a generation AI to monitor the progress of tasks and generate alerts for tasks with approaching deadlines or no progress. The generation AI evaluates the progress based on the task completion rate and deadline compliance and generates alerts. For example, the generation AI can monitor the progress of tasks in real time and generate alerts for tasks with approaching deadlines. The generation AI can also generate alerts for tasks with no progress. This allows the progress of tasks to be understood in real time and prevents important tasks from being overlooked. Some or all of the above-described processing in the monitoring unit can be performed, for example, using AI or without AI. For example, the monitoring unit can input the progress of tasks into the generation AI and have the generation AI monitor the progress and generate alerts.

[0033] The calendar creation unit can determine when the next meeting is needed based on the content of the conversation and the progress of the tasks, automatically create a calendar, and automatically send it to the relevant parties. The calendar creation unit, for example, uses a generation AI to determine when the next meeting is needed based on the content of the conversation and the progress of the tasks, and automatically create a calendar. The generation AI analyzes the content of the conversation and the progress of the tasks and determines when the next meeting is needed. For example, the generation AI predicts when the next meeting is needed based on the progress of the tasks, and automatically creates a calendar. Furthermore, the calendar creation unit automatically sends the calendar to the relevant parties using the generation AI. The generation AI automatically sends the meeting schedule to the relevant parties and adjusts the schedule. This allows for smooth adjustment of the meeting schedule. Some or all of the above-mentioned processing in the calendar creation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calendar creation unit can input the content of the conversation and the progress of the tasks into the generation AI, and have the generation AI create and send the calendar.

[0034] The speech recognition unit can improve the accuracy of speech recognition by analyzing background sounds of a conversation and optimizing noise removal. The speech recognition unit, for example, analyzes background sounds of a conversation and optimizes noise removal. Background sounds include, for example, environmental sounds and noise. For example, the speech recognition unit detects the sound of an air conditioner in a conference room as noise and removes it. It can also recognize noise in a cafe as background sound and extract only the conversation voice. It can also detect the sound of a car running as noise and improve the accuracy of speech recognition. In this way, the accuracy of speech recognition is improved by analyzing background sounds and optimizing noise removal. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input background sound data to a generation AI and cause the generation AI to optimize noise removal.

[0035] The speech recognition unit can be equipped with a function that understands the context of a conversation and automatically recognizes and converts technical terms and abbreviations. For example, the speech recognition unit understands the context of a conversation and automatically recognizes and converts technical terms and abbreviations. Understanding the context includes, for example, the context surrounding the conversation and related topics. For example, the speech recognition unit can automatically recognize abbreviations used in IT conversations and convert them to the appropriate terminology. It can also automatically recognize technical terms in the medical industry and accurately transcribe them. It can also automatically recognize abbreviations in the legal industry and convert them to the appropriate terminology. This enables accurate transcription by automatically recognizing and converting technical terms and abbreviations. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI. For example, the speech recognition unit can input context data into a generation AI and have the generation AI recognize and convert technical terms and abbreviations.

[0036] During speech recognition, the speech recognition unit can analyze the voice characteristics of each speaker and apply a speech recognition model optimized for each individual speaker. For example, during speech recognition, the speech recognition unit can analyze the voice characteristics of each speaker and apply a speech recognition model optimized for each individual speaker. The speaker's voice characteristics include, for example, voice tone, pitch, and rhythm. For example, the speech recognition unit can analyze the voice characteristics of speaker A and apply a dedicated speech recognition model. It can also analyze the voice characteristics of speaker B and apply a dedicated speech recognition model. It can also analyze the voice characteristics of speaker C and apply a dedicated speech recognition model. This improves the accuracy of speech recognition by applying a speech recognition model optimized for each speaker. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI. For example, the speech recognition unit can input speaker voice characteristic data to a generation AI and cause the generation AI to apply a speech recognition model.

[0037] The speech recognition unit can automatically classify conversation topics during speech recognition and apply different recognition algorithms to each topic. For example, the speech recognition unit can automatically classify conversation topics during speech recognition and apply different recognition algorithms to each topic. Conversation topics include, for example, business, technology, and everyday life. For example, if the conversation is a business topic, the speech recognition unit can apply a business recognition algorithm. Also, if the conversation is a technical topic, the speech recognition unit can apply a technical recognition algorithm. Furthermore, if the conversation is an everyday topic, the speech recognition unit can apply an everyday recognition algorithm. By applying different recognition algorithms to each conversation topic, the accuracy of speech recognition is improved. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input conversation topic data to a generation AI and have the generation AI apply a recognition algorithm.

[0038] The generation unit can dynamically adjust the level of detail of the generated content based on the importance of the conversation during generation. For example, the generation unit dynamically adjusts the level of detail of the generated content based on the importance of the conversation during generation. The importance of the conversation is evaluated based on, for example, the frequency of keywords or the importance of the context. For example, the generation unit generates detailed "minutes" for important conversation content. For low-importance conversation content, the generation unit can generate concise "ToDos." For medium-importance conversation content, the generation unit can generate a "WBS" with appropriate level of detail. By adjusting the level of detail of the content based on the importance of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input conversation importance data into a generation AI and cause the generation AI to adjust the level of detail of the content.

[0039] The generation unit can apply different generation algorithms depending on the category of the conversation during generation. For example, the generation unit applies different generation algorithms depending on the category of the conversation during generation. Conversation categories include, for example, business, technical, and everyday. For example, the generation unit applies a business generation algorithm to a business conversation. Also, for a technical conversation, the generation unit can apply a technical generation algorithm. Furthermore, for an everyday conversation, the generation unit can apply an everyday generation algorithm. In this way, by applying different generation algorithms depending on the category of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation category data into a generation AI and cause the generation AI to apply a generation algorithm.

[0040] The generation unit can adjust the priority of the content to be generated based on the time of the conversation during generation. For example, the generation unit can adjust the priority of the content to be generated based on the time of the conversation during generation. Conversation time periods include, for example, morning, afternoon, and evening. For example, the generation unit can generate a "ToDo" list for morning conversation content, prioritizing important tasks. For afternoon conversation content, the generation unit can generate a "minutes" with normal priority. For evening conversation content, the generation unit can generate a "WBS" by prioritizing the tasks for the next day. By adjusting the priority of the content based on the time of the conversation, more appropriate "minutes," "ToDo" lists, and "WBS" lists can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, AI. For example, the generation unit can input conversation time period data into a generation AI and have the generation AI adjust the priority.

[0041] The generation unit can adjust the order of the generated content based on the relevance of the conversation during generation. The generation unit, for example, adjusts the order of the generated content based on the relevance of the conversation during generation. Conversation relevance includes, for example, topic relevance and task relevance. For example, the generation unit prioritizes generating "minutes" for highly relevant conversation content. For less relevant conversation content, the generation unit can postpone generating "ToDos." Furthermore, for moderately relevant conversation content, the generation unit can generate "WBS" in an appropriate order. By adjusting the order of the content based on the relevance of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input conversation relevance data into a generation AI and have the generation AI adjust the order of the content.

[0042] The monitoring unit can monitor the progress of the task in real time and detect abnormal progress using an anomaly detection algorithm. The monitoring unit, for example, monitors the progress of the task in real time and detects abnormal progress using an anomaly detection algorithm. Abnormal progress includes, for example, slow progress and stagnation of progress. For example, the monitoring unit detects slow progress of the task as an abnormality. It can also detect rapid progress of the task as an abnormality. Furthermore, it can detect no progress of the task as an abnormality. This enables rapid response by monitoring the progress of the task in real time and detecting abnormal progress. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input task progress data to a generation AI and cause the generation AI to detect abnormal progress.

[0043] The monitoring unit can dynamically adjust the importance of an alert based on the priority of a task. The monitoring unit dynamically adjusts the importance of an alert based on, for example, the priority of a task. The importance of an alert includes, for example, the priority and progress of the task. For example, the monitoring unit can issue an alert with a high importance for an important task. Also, for a low-priority task, the monitoring unit can issue an alert with a low importance. Furthermore, for a medium-priority task, the monitoring unit can issue an alert with a moderate importance. This allows for adjusting the importance of an alert based on the priority of the task, enabling a prompt response to important tasks. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input task priority data to a generation AI and cause the generation AI to adjust the importance of the alert.

[0044] When monitoring the progress of a task, the monitoring unit can simultaneously monitor the progress of related projects and perform a comprehensive progress evaluation. For example, when monitoring the progress of a task, the monitoring unit can simultaneously monitor the progress of related projects and perform a comprehensive progress evaluation. The comprehensive progress evaluation includes, for example, an integrated evaluation of the progress of the task and the project. For example, the monitoring unit simultaneously monitors the progress of the task and the progress of the related project. Furthermore, if the progress of the task is delayed, the progress of the related project can also be evaluated. Furthermore, if the progress of the task is going well, the progress of the related project can also be evaluated. In this way, by simultaneously monitoring the progress of the task and the related project, a comprehensive progress evaluation is possible. Some or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit can input progress data of the task and the project to a generation AI and have the generation AI perform a comprehensive progress evaluation.

[0045] When monitoring the progress of a task, the monitoring unit can perform progress prediction by referring to past progress data. For example, when monitoring the progress of a task, the monitoring unit can perform progress prediction by referring to past progress data. Progress prediction includes, for example, analysis of past data and a prediction algorithm. For example, the monitoring unit can predict the current progress of a task based on past progress data. It can also predict the future progress of a task based on past progress data. It can also predict abnormal progress based on past progress data. This enables more accurate progress management by performing progress prediction based on past progress data. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input past progress data to a generation AI and have the generation AI perform a progress prediction.

[0046] The calendar creation unit can be added with a function to automatically suggest optimal meeting times based on the content of conversations and task progress. The calendar creation unit automatically suggests optimal meeting times based on, for example, the content of conversations and task progress. The optimal meeting time includes, for example, the schedules of the parties involved and the progress of tasks. For example, the calendar creation unit suggests optimal meeting times based on the content of conversations. It can also suggest optimal meeting times based on task progress. Furthermore, it can comprehensively evaluate the content of conversations and task progress to suggest optimal meeting times. This enables efficient schedule management by suggesting optimal meeting times based on the content of conversations and task progress. Some or all of the above-described processing in the calendar creation unit may be performed using, or without, AI. For example, the calendar creation unit can input data on the content of conversations and task progress into a generation AI and have the generation AI suggest optimal meeting times.

[0047] The calendar creation unit can automatically adjust the schedules of the parties involved and set optimal meeting times when creating a calendar. For example, the calendar creation unit can automatically adjust the schedules of the parties involved and set optimal meeting times when creating a calendar. The schedules of the parties involved include, for example, a schedule sharing method and an adjustment algorithm. For example, the calendar creation unit can automatically obtain the schedules of the parties involved and set optimal meeting times. The calendar creation unit can also adjust the meeting times based on the schedules of the parties involved. Furthermore, the calendar creation unit can comprehensively evaluate the schedules of the parties involved and set optimal meeting times. This makes it possible to set optimal meeting times by automatically adjusting the schedules of the parties involved. Some or all of the above-mentioned processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input schedule data of the parties involved into a generation AI and have the generation AI adjust the schedules and set meeting times.

[0048] The calendar creation unit can propose an optimal meeting location by taking into account the geographical location information of the participants when creating a calendar. For example, the calendar creation unit proposes an optimal meeting location by taking into account the geographical location information of the participants when creating a calendar. Geographical location information includes, for example, GPS data and location information services. For example, the calendar creation unit proposes an optimal meeting location based on the geographical location information of the participants. The calendar creation unit can also comprehensively evaluate the geographical location information of the participants and propose an optimal meeting location. Furthermore, the meeting location can be adjusted by taking into account the geographical location information of the participants. This makes it possible to propose an optimal meeting location by taking into account the geographical location information of the participants. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input the geographical location information data of the participants to a generation AI and cause the generation AI to suggest a meeting location.

[0049] The calendar creation unit can suggest an optimal meeting format (e.g., in-person, online, etc.) by referring to past meeting data when creating a calendar. For example, the calendar creation unit can suggest an optimal meeting format by referring to past meeting data when creating a calendar. Meeting formats include, for example, in-person meetings and online meetings. For example, the calendar creation unit suggests an optimal meeting format based on past meeting data. It can also comprehensively evaluate past meeting data and suggest an optimal meeting format. It can also adjust the meeting format by referring to past meeting data. This makes it possible to suggest an optimal meeting format by referring to past meeting data. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input past meeting data into a generation AI and have the generation AI suggest a meeting format.

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

[0051] The automatic conversation recording system can also be equipped with a translation unit, which can translate conversation content into other languages ​​in real time. For example, a conversation held in English can be translated into Japanese, and meeting minutes and to-do lists can be created in Japanese. Or, a conversation held in French can be translated into English, and a WBS can be created in English. This facilitates communication between parties who speak different languages, and helps international projects proceed more smoothly.

[0052] The speech recognition unit can be equipped with a function to automatically adjust the speed of speech. For example, if the speech is too fast, the speech recognition unit can automatically slow down the speech before transcribing. Alternatively, if the speech is too slow, the speech recognition unit can speed up the speech before transcribing. Furthermore, the strength of noise reduction can be adjusted according to the speed of speech. This allows for accurate transcription regardless of the speed of speech.

[0053] When monitoring the progress of tasks, the monitoring unit can generate alerts taking into account task dependencies. For example, if a task cannot start until the next task is completed, an alert will be generated if the progress of that task is behind schedule. Also, if dependent tasks are progressing simultaneously, an alert can be generated based on a comprehensive evaluation of the progress. Furthermore, if dependent tasks are progressing smoothly, an alert can be suppressed. This enables progress management that takes task dependencies into account.

[0054] The calendar creation section can be added with a function that automatically suggests the optimal meeting location based on the content of the conversation and the progress of tasks. For example, it can suggest the optimal meeting location based on the geographical location information of the people involved. It can also adjust the meeting location taking into account the schedules of the people involved. It can also comprehensively evaluate the content of the conversation and the progress of tasks to suggest the optimal meeting location. This minimizes the travel time of the people involved and enables efficient meetings.

[0055] The speech recognition unit can analyze background sounds of a conversation and enhance specific noises to improve the accuracy of speech recognition. For example, it can enhance the sound of an air conditioner in a conference room and remove other noises. It can also enhance the noise of a cafe to extract only the conversation. It can also enhance the sound of a car running. In this way, enhancing specific noises improves the accuracy of speech recognition.

[0056] The speech recognition unit can be equipped with the ability to understand the context of a conversation and automatically recognize and convert specific phrases and expressions. For example, it can automatically recognize specific phrases used in business meetings and convert them to the appropriate terminology. It can also automatically recognize specific expressions used in casual conversations and accurately transcribe them. It can also automatically recognize technical terms and abbreviations and convert them to the appropriate terminology. This allows for accurate transcription by automatically recognizing and converting specific phrases and expressions.

[0057] During speech recognition, the speech recognition unit can analyze the characteristics of the speaker's voice and apply a speech recognition model optimized for each individual speaker. For example, it can analyze the characteristics of speaker A's voice and apply a dedicated speech recognition model. It can also analyze the characteristics of speaker B's voice and apply a dedicated speech recognition model. It can also analyze the characteristics of speaker C's voice and apply a dedicated speech recognition model. In this way, by applying a speech recognition model optimized for each speaker, the accuracy of speech recognition is improved.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The speech recognition unit converts the speech into text. This includes business meetings and casual conversations. The speech recognition unit converts the speech into text in real time using, for example, the speech recognition AI "Whisper" or a Chrome extension. The speech recognition AI analyzes the speech data using a deep learning model and converts it into text data. Preprocessing of the speech data involves noise removal and speech normalization, and then the deep learning model is used to convert the speech into text. Step 2: The generation unit analyzes the content transcribed by the speech recognition unit and automatically creates "minutes," "ToDos," "WBS," etc. The generation unit uses generation AI to analyze the transcribed content and extract important points and tasks. The generation AI uses natural language processing technology to analyze the text data, extract important points based on the frequency of keywords and the importance of the context, and automatically create "minutes," "ToDos," and "WBS." Step 3: The monitoring unit monitors the progress of the tasks generated by the generation unit and issues an alert if there is no progress. The monitoring unit uses the generation AI to monitor the progress of the tasks and issues an alert for tasks whose deadlines are approaching or for which there is no progress. The generation AI evaluates the progress based on the task completion rate and deadline compliance status and issues an alert. Step 4: The calendar creation unit automatically creates a calendar for the next meeting required based on tasks determined by the monitoring unit to be no progress, and automatically sends it to the relevant parties. The calendar creation unit uses the generation AI to determine when the next meeting is required based on the content of the conversation and the progress of the task, and automatically creates a calendar. The generation AI predicts when the next meeting is required based on the progress of the task, and automatically creates a calendar.

[0060] (Example 2) The automatic conversation recording system according to an embodiment of the present invention transcribes the speech content of business negotiations and meetings with customers in both face-to-face and offline sales, automatically creating meeting minutes, to-do lists, and work breakdown structures. This system uses speech recognition AI to transcribe the conversation content, and then uses generation AI to automatically create meeting minutes, to-do lists, and work breakdown structures from the transcribed content. Furthermore, if there is no progress on a task, the system generates an alert, and when the next meeting is required, automatically creates a calendar and sends it to relevant parties. For example, the system transcribes the conversation content using speech recognition AI. By using the speech recognition AI "Whisper" or a Chrome extension, the conversation content can be transcribed in real time, allowing for accurate recording of the conversation content. Next, the system uses generation AI to automatically create meeting minutes, to-do lists, and work breakdown structures from the transcribed content. The generation AI analyzes the transcribed content and extracts important points and tasks. For example, it can automatically extract action items and deadlines mentioned in the conversation and create to-do lists and work breakdown structures. Furthermore, it generates an alert if there is no progress on a task. The generation AI monitors the progress of tasks and issues alerts for tasks with approaching deadlines or tasks that have not progressed. This makes task management easier and prevents important tasks from being overlooked. It also automatically creates a calendar entry when the next meeting is needed and sends it to relevant parties. The generation AI determines when the next meeting is needed based on the content of the conversation and the progress of the task, and automatically creates a calendar entry. Furthermore, by automatically sending the calendar entry to relevant parties, meeting schedules can be adjusted smoothly. As a result, the automatic conversation recording system improves the efficiency of conversation recording and task management in both face-to-face and offline sales, improving work productivity.

[0061] An automatic conversation content recording system according to an embodiment includes a speech recognition unit, a generation unit, a monitoring unit, and a calendar creation unit. The speech recognition unit converts speech into text. Examples of conversation content include, but are not limited to, business meetings and casual conversations. The speech recognition unit transcribes the conversation content in real time using, for example, the speech recognition AI "Whisper" or a Chrome extension. The speech recognition AI analyzes the speech data and converts it into text data using a deep learning model. For example, the speech recognition AI performs preprocessing of the speech data, such as noise reduction and speech normalization, and then converts the speech into text using a deep learning model. The generation unit analyzes the transcribed content and automatically creates documents such as minutes, to-do lists, and work breakdown structures. For example, the generation unit analyzes the transcribed content using a generation AI and extracts important points and tasks. The generation AI analyzes the text data using natural language processing technology and extracts important information. For example, the generation AI extracts important points based on the frequency of keywords and the importance of the context, and automatically creates "minutes," "ToDo lists," and "WBS." The monitoring unit monitors the progress of tasks generated by the generation unit and issues an alert if there is no progress. The monitoring unit, for example, uses the generation AI to monitor task progress and issues an alert for tasks whose deadlines are approaching or for which there is no progress. The generation AI evaluates progress based on the task completion rate and deadline compliance status and issues an alert. The calendar creation unit automatically creates a calendar when the next meeting is needed based on tasks determined by the monitoring unit to have no progress, and automatically sends it to relevant parties. The calendar creation unit, for example, uses the generation AI to determine when the next meeting is needed based on the content of conversations and the progress of tasks, and automatically creates a calendar. The generation AI analyzes the content of conversations and the progress of tasks to determine when the next meeting is needed. For example, the generation AI predicts when the next meeting is needed based on the progress of tasks, and automatically creates a calendar. This allows the automatic conversation recording system to streamline conversation recording and task management, improving work productivity. For example, accurately recording conversation content is useful for reviewing the content later.In addition, by understanding the progress of tasks in real time, you can prevent important tasks from being overlooked. Furthermore, by automatically determining when the next meeting is needed and creating a calendar, you can smoothly adjust your schedule.

[0062] The speech recognition unit can transcribe conversation content in real time using speech recognition AI. A deep learning model, for example, is used for the speech recognition AI. The deep learning model learns large amounts of speech data to achieve highly accurate speech recognition. For example, the speech recognition AI performs preprocessing of the speech data, such as noise removal and speech normalization, and then converts the speech into text using a deep learning model. The speech recognition AI can, for example, analyze speech data in real time and convert it into text data. This allows for accurate recording by transcribing the conversation content in real time. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input speech data to a generation AI and have the generation AI generate text data from the speech data.

[0063] The generation unit can analyze the transcribed content, extract important points and tasks, and automatically create "minutes," "ToDo lists," "WBS," etc. The generation unit, for example, uses a generation AI to analyze the transcribed content and extract important points and tasks. The generation AI analyzes the text data using natural language processing technology and extracts important information. For example, the generation AI extracts important points based on keyword frequency and context importance, and automatically creates "minutes," "ToDo lists," and "WBS." The generation unit can automatically extract action items and deadlines that come up in conversations and create "ToDo lists" and "WBS." This allows for automatic extraction and efficient management of important points and tasks. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the transcribed content into a generation AI and have the generation AI extract important points and tasks.

[0064] The monitoring unit can monitor the progress of tasks and generate alerts for tasks with approaching deadlines or no progress. The monitoring unit can, for example, use a generation AI to monitor the progress of tasks and generate alerts for tasks with approaching deadlines or no progress. The generation AI evaluates the progress based on the task completion rate and deadline compliance and generates alerts. For example, the generation AI can monitor the progress of tasks in real time and generate alerts for tasks with approaching deadlines. The generation AI can also generate alerts for tasks with no progress. This allows the progress of tasks to be understood in real time and prevents important tasks from being overlooked. Some or all of the above-described processing in the monitoring unit can be performed, for example, using AI or without AI. For example, the monitoring unit can input the progress of tasks into the generation AI and have the generation AI monitor the progress and generate alerts.

[0065] The calendar creation unit can determine when the next meeting is needed based on the content of the conversation and the progress of the tasks, automatically create a calendar, and automatically send it to the relevant parties. The calendar creation unit, for example, uses a generation AI to determine when the next meeting is needed based on the content of the conversation and the progress of the tasks, and automatically create a calendar. The generation AI analyzes the content of the conversation and the progress of the tasks and determines when the next meeting is needed. For example, the generation AI predicts when the next meeting is needed based on the progress of the tasks, and automatically creates a calendar. Furthermore, the calendar creation unit automatically sends the calendar to the relevant parties using the generation AI. The generation AI automatically sends the meeting schedule to the relevant parties and adjusts the schedule. This allows for smooth adjustment of the meeting schedule. Some or all of the above-mentioned processing in the calendar creation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the calendar creation unit can input the content of the conversation and the progress of the tasks into the generation AI, and have the generation AI create and send the calendar.

[0066] The speech recognition unit can estimate a user's emotions and dynamically adjust the accuracy of speech recognition based on the estimated user emotions. The speech recognition unit, for example, estimates a user's emotions and dynamically adjusts the accuracy of speech recognition based on the estimated user emotions. The user's emotions are estimated, for example, using voice tone analysis or facial expression recognition. For example, if the user is nervous, the speech recognition unit can increase the sensitivity of speech recognition to more accurately transcribe speech. Also, if the user is relaxed, the speech recognition unit can return the sensitivity of speech recognition to normal and transcribe natural conversations. Furthermore, if the user is in a hurry, the speech recognition unit can prioritize the speed of speech recognition to quickly transcribe speech. This allows for more accurate transcription by adjusting the accuracy of speech recognition according to the user's emotions. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without AI. For example, the speech recognition unit can input user emotion data to a generation AI and have the generation AI adjust the accuracy of speech recognition.

[0067] The speech recognition unit can improve the accuracy of speech recognition by analyzing background sounds of a conversation and optimizing noise removal. The speech recognition unit, for example, analyzes background sounds of a conversation and optimizes noise removal. Background sounds include, for example, environmental sounds and noise. For example, the speech recognition unit detects the sound of an air conditioner in a conference room as noise and removes it. It can also recognize noise in a cafe as background sound and extract only the conversation voice. It can also detect the sound of a car running as noise and improve the accuracy of speech recognition. In this way, the accuracy of speech recognition is improved by analyzing background sounds and optimizing noise removal. Some or all of the above-mentioned processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input background sound data to a generation AI and cause the generation AI to optimize noise removal.

[0068] The speech recognition unit can be equipped with a function that understands the context of a conversation and automatically recognizes and converts technical terms and abbreviations. For example, the speech recognition unit understands the context of a conversation and automatically recognizes and converts technical terms and abbreviations. Understanding the context includes, for example, the context surrounding the conversation and related topics. For example, the speech recognition unit can automatically recognize abbreviations used in IT conversations and convert them to the appropriate terminology. It can also automatically recognize technical terms in the medical industry and accurately transcribe them. It can also automatically recognize abbreviations in the legal industry and convert them to the appropriate terminology. This enables accurate transcription by automatically recognizing and converting technical terms and abbreviations. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI. For example, the speech recognition unit can input context data into a generation AI and have the generation AI recognize and convert technical terms and abbreviations.

[0069] The speech recognition unit can estimate a user's emotion and filter the speech recognition results based on the estimated user's emotion. The speech recognition unit, for example, estimates a user's emotion and filters the speech recognition results based on the estimated user's emotion. The user's emotion is estimated, for example, using voice tone analysis or facial expression recognition. For example, if the user is angry, the speech recognition unit can filter emotional statements and transcribe only the calm parts. Also, if the user is sad, the speech recognition unit can filter emotional statements and transcribe only important information. Furthermore, if the user is excited, the speech recognition unit can filter emotional statements and transcribe only the calm parts. This allows for more appropriate transcription by filtering the speech recognition results according to the user's emotion. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or without AI. For example, the speech recognition unit can input user emotion data into a generation AI and have the generation AI filter the speech recognition results.

[0070] During speech recognition, the speech recognition unit can analyze the voice characteristics of each speaker and apply a speech recognition model optimized for each individual speaker. For example, during speech recognition, the speech recognition unit can analyze the voice characteristics of each speaker and apply a speech recognition model optimized for each individual speaker. The speaker's voice characteristics include, for example, voice tone, pitch, and rhythm. For example, the speech recognition unit can analyze the voice characteristics of speaker A and apply a dedicated speech recognition model. It can also analyze the voice characteristics of speaker B and apply a dedicated speech recognition model. It can also analyze the voice characteristics of speaker C and apply a dedicated speech recognition model. This improves the accuracy of speech recognition by applying a speech recognition model optimized for each speaker. Some or all of the above-described processing in the speech recognition unit may be performed using, or without, AI. For example, the speech recognition unit can input speaker voice characteristic data to a generation AI and cause the generation AI to apply a speech recognition model.

[0071] The speech recognition unit can automatically classify conversation topics during speech recognition and apply different recognition algorithms to each topic. For example, the speech recognition unit can automatically classify conversation topics during speech recognition and apply different recognition algorithms to each topic. Conversation topics include, for example, business, technology, and everyday life. For example, if the conversation is a business topic, the speech recognition unit can apply a business recognition algorithm. Also, if the conversation is a technical topic, the speech recognition unit can apply a technical recognition algorithm. Furthermore, if the conversation is an everyday topic, the speech recognition unit can apply an everyday recognition algorithm. By applying different recognition algorithms to each conversation topic, the accuracy of speech recognition is improved. Some or all of the above-described processing in the speech recognition unit may be performed using, for example, AI, or may be performed without using AI. For example, the speech recognition unit can input conversation topic data to a generation AI and have the generation AI apply a recognition algorithm.

[0072] The generation unit can estimate the user's emotions and adjust the expression of the generated "minutes," "ToDos," and "WBS" based on the estimated user emotions. The generation unit, for example, estimates the user's emotions and adjusts the expression of the generated "minutes," "ToDos," and "WBS" based on the estimated user emotions. The user's emotions are estimated, for example, using voice tone analysis or facial expression recognition. For example, if the user is relaxed, the generation unit can generate "minutes" using soft expressions. If the user is in a hurry, the generation unit can generate "ToDos" using concise expressions. Furthermore, if the user is excited, the generation unit can generate "WBS" using visually stimulating expressions. By adjusting the expression methods according to the user's emotions, more appropriate "minutes," "ToDos," and "WBS" can be generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the expression methods.

[0073] The generation unit can dynamically adjust the level of detail of the generated content based on the importance of the conversation during generation. For example, the generation unit dynamically adjusts the level of detail of the generated content based on the importance of the conversation during generation. The importance of the conversation is evaluated based on, for example, the frequency of keywords or the importance of the context. For example, the generation unit generates detailed "minutes" for important conversation content. For low-importance conversation content, the generation unit can generate concise "ToDos." For medium-importance conversation content, the generation unit can generate a "WBS" with appropriate level of detail. By adjusting the level of detail of the content based on the importance of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input conversation importance data into a generation AI and cause the generation AI to adjust the level of detail of the content.

[0074] The generation unit can apply different generation algorithms depending on the category of the conversation during generation. For example, the generation unit applies different generation algorithms depending on the category of the conversation during generation. Conversation categories include, for example, business, technical, and everyday. For example, the generation unit applies a business generation algorithm to a business conversation. Also, for a technical conversation, the generation unit can apply a technical generation algorithm. Furthermore, for an everyday conversation, the generation unit can apply an everyday generation algorithm. In this way, by applying different generation algorithms depending on the category of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can input conversation category data into a generation AI and cause the generation AI to apply a generation algorithm.

[0075] The generation unit can estimate the user's emotions and prioritize the generated "minutes," "ToDos," and "WBS" based on the estimated user emotions. The generation unit, for example, estimates the user's emotions and prioritizes the generated "minutes," "ToDos," and "WBS" based on the estimated user emotions. The user's emotions can be estimated, for example, using voice tone analysis or facial expression recognition. For example, if the user is relaxed, the generation unit can generate "minutes" with normal priority. If the user is in a hurry, the generation unit can generate "ToDos" by prioritizing important tasks. Furthermore, if the user is excited, the generation unit can generate "WBS" by prioritizing visually stimulating tasks. This allows for more appropriate "minutes," "ToDos," and "WBS" to be generated by prioritizing tasks according to the user's emotions. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or without AI. For example, the generation unit can input the user's emotional data into the generation AI and have the generation AI determine the priorities.

[0076] The generation unit can adjust the priority of the content to be generated based on the time of the conversation during generation. For example, the generation unit can adjust the priority of the content to be generated based on the time of the conversation during generation. Conversation time periods include, for example, morning, afternoon, and evening. For example, the generation unit can generate a "ToDo" list for morning conversation content, prioritizing important tasks. For afternoon conversation content, the generation unit can generate a "minutes" with normal priority. For evening conversation content, the generation unit can generate a "WBS" by prioritizing the tasks for the next day. By adjusting the priority of the content based on the time of the conversation, more appropriate "minutes," "ToDo" lists, and "WBS" lists can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, AI. For example, the generation unit can input conversation time period data into a generation AI and have the generation AI adjust the priority.

[0077] The generation unit can adjust the order of the generated content based on the relevance of the conversation during generation. The generation unit, for example, adjusts the order of the generated content based on the relevance of the conversation during generation. Conversation relevance includes, for example, topic relevance and task relevance. For example, the generation unit prioritizes generating "minutes" for highly relevant conversation content. For less relevant conversation content, the generation unit can postpone generating "ToDos." Furthermore, for moderately relevant conversation content, the generation unit can generate "WBS" in an appropriate order. By adjusting the order of the content based on the relevance of the conversation, more appropriate "minutes," "ToDos," and "WBS" are generated. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without AI. For example, the generation unit can input conversation relevance data into a generation AI and have the generation AI adjust the order of the content.

[0078] The monitoring unit can monitor the progress of the task in real time and detect abnormal progress using an anomaly detection algorithm. The monitoring unit, for example, monitors the progress of the task in real time and detects abnormal progress using an anomaly detection algorithm. Abnormal progress includes, for example, slow progress and stagnation of progress. For example, the monitoring unit detects slow progress of the task as an abnormality. It can also detect rapid progress of the task as an abnormality. Furthermore, it can detect no progress of the task as an abnormality. This enables rapid response by monitoring the progress of the task in real time and detecting abnormal progress. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input task progress data to a generation AI and cause the generation AI to detect abnormal progress.

[0079] The monitoring unit can dynamically adjust the importance of an alert based on the priority of a task. The monitoring unit dynamically adjusts the importance of an alert based on, for example, the priority of a task. The importance of an alert includes, for example, the priority and progress of the task. For example, the monitoring unit can issue an alert with a high importance for an important task. Also, for a low-priority task, the monitoring unit can issue an alert with a low importance. Furthermore, for a medium-priority task, the monitoring unit can issue an alert with a moderate importance. This allows for adjusting the importance of an alert based on the priority of the task, enabling a prompt response to important tasks. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input task priority data to a generation AI and cause the generation AI to adjust the importance of the alert.

[0080] The monitoring unit can estimate the user's emotions and adjust the alert display method based on the estimated user emotions. The monitoring unit, for example, estimates the user's emotions and adjusts the alert display method based on the estimated user emotions. The user's emotions are estimated, for example, using voice tone analysis or facial expression recognition. For example, the monitoring unit displays the alert in a normal display method when the user is relaxed. Furthermore, the monitoring unit can display the alert in a visually noticeable display method when the user is in a hurry. Furthermore, the monitoring unit can display the alert in a visually stimulating display method when the user is excited. This enables more effective alert notification by adjusting the alert display method according to the user's emotions. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input user emotion data into a generation AI and cause the generation AI to adjust the alert display method.

[0081] When monitoring the progress of a task, the monitoring unit can simultaneously monitor the progress of related projects and perform a comprehensive progress evaluation. For example, when monitoring the progress of a task, the monitoring unit can simultaneously monitor the progress of related projects and perform a comprehensive progress evaluation. The comprehensive progress evaluation includes, for example, an integrated evaluation of the progress of the task and the project. For example, the monitoring unit simultaneously monitors the progress of the task and the progress of the related project. Furthermore, if the progress of the task is delayed, the progress of the related project can also be evaluated. Furthermore, if the progress of the task is going well, the progress of the related project can also be evaluated. In this way, by simultaneously monitoring the progress of the task and the related project, a comprehensive progress evaluation is possible. Some or all of the above-mentioned processing in the monitoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the monitoring unit can input progress data of the task and the project to a generation AI and have the generation AI perform a comprehensive progress evaluation.

[0082] When monitoring the progress of a task, the monitoring unit can perform progress prediction by referring to past progress data. For example, when monitoring the progress of a task, the monitoring unit can perform progress prediction by referring to past progress data. Progress prediction includes, for example, analysis of past data and a prediction algorithm. For example, the monitoring unit can predict the current progress of a task based on past progress data. It can also predict the future progress of a task based on past progress data. It can also predict abnormal progress based on past progress data. This enables more accurate progress management by performing progress prediction based on past progress data. Some or all of the above-described processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input past progress data to a generation AI and have the generation AI perform a progress prediction.

[0083] The calendar creation unit can estimate the user's emotions and adjust the timing of calendar creation based on the estimated user emotions. The calendar creation unit, for example, estimates the user's emotions and adjusts the timing of calendar creation based on the estimated user emotions. The user's emotions are estimated, for example, using voice tone analysis or facial expression recognition. For example, the calendar creation unit creates a calendar at a normal timing when the user is relaxed. Furthermore, if the user is in a hurry, the calendar creation unit can create a calendar earlier. Furthermore, if the user is excited, a visually stimulating calendar can be created. This enables more appropriate schedule management by adjusting the timing of calendar creation according to the user's emotions. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input user emotion data into a generation AI and have the generation AI adjust the timing of calendar creation.

[0084] The calendar creation unit can be added with a function to automatically suggest optimal meeting times based on the content of conversations and task progress. The calendar creation unit automatically suggests optimal meeting times based on, for example, the content of conversations and task progress. The optimal meeting time includes, for example, the schedules of the parties involved and the progress of tasks. For example, the calendar creation unit suggests optimal meeting times based on the content of conversations. It can also suggest optimal meeting times based on task progress. Furthermore, it can comprehensively evaluate the content of conversations and task progress to suggest optimal meeting times. This enables efficient schedule management by suggesting optimal meeting times based on the content of conversations and task progress. Some or all of the above-described processing in the calendar creation unit may be performed using, or without, AI. For example, the calendar creation unit can input data on the content of conversations and task progress into a generation AI and have the generation AI suggest optimal meeting times.

[0085] The calendar creation unit can automatically adjust the schedules of the parties involved and set optimal meeting times when creating a calendar. For example, the calendar creation unit can automatically adjust the schedules of the parties involved and set optimal meeting times when creating a calendar. The schedules of the parties involved include, for example, a schedule sharing method and an adjustment algorithm. For example, the calendar creation unit can automatically obtain the schedules of the parties involved and set optimal meeting times. The calendar creation unit can also adjust the meeting times based on the schedules of the parties involved. Furthermore, the calendar creation unit can comprehensively evaluate the schedules of the parties involved and set optimal meeting times. This makes it possible to set optimal meeting times by automatically adjusting the schedules of the parties involved. Some or all of the above-mentioned processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input schedule data of the parties involved into a generation AI and have the generation AI adjust the schedules and set meeting times.

[0086] The calendar creation unit can estimate a user's emotions and adjust the calendar display method based on the estimated user emotions. The calendar creation unit, for example, estimates a user's emotions and adjusts the calendar display method based on the estimated user emotions. The user's emotions are estimated, for example, using voice tone analysis or facial expression recognition. For example, the calendar creation unit displays the calendar in a normal display method when the user is relaxed. Furthermore, the calendar creation unit can display the calendar in a visually striking display method when the user is in a hurry. Furthermore, the calendar creation unit can display the calendar in a visually stimulating display method when the user is excited. This enables more effective schedule management by adjusting the calendar display method according to the user's emotions. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without AI. For example, the calendar creation unit can input user emotion data into a generation AI and have the generation AI adjust the calendar display method.

[0087] The calendar creation unit can propose an optimal meeting location by taking into account the geographical location information of the participants when creating a calendar. For example, the calendar creation unit proposes an optimal meeting location by taking into account the geographical location information of the participants when creating a calendar. Geographical location information includes, for example, GPS data and location information services. For example, the calendar creation unit proposes an optimal meeting location based on the geographical location information of the participants. The calendar creation unit can also comprehensively evaluate the geographical location information of the participants and propose an optimal meeting location. Furthermore, the meeting location can be adjusted by taking into account the geographical location information of the participants. This makes it possible to propose an optimal meeting location by taking into account the geographical location information of the participants. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input the geographical location information data of the participants to a generation AI and cause the generation AI to suggest a meeting location.

[0088] The calendar creation unit can suggest an optimal meeting format (e.g., in-person, online, etc.) by referring to past meeting data when creating a calendar. For example, the calendar creation unit can suggest an optimal meeting format by referring to past meeting data when creating a calendar. Meeting formats include, for example, in-person meetings and online meetings. For example, the calendar creation unit suggests an optimal meeting format based on past meeting data. It can also comprehensively evaluate past meeting data and suggest an optimal meeting format. It can also adjust the meeting format by referring to past meeting data. This makes it possible to suggest an optimal meeting format by referring to past meeting data. Some or all of the above-described processing in the calendar creation unit may be performed using, for example, AI, or may be performed without using AI. For example, the calendar creation unit can input past meeting data into a generation AI and have the generation AI suggest a meeting format. === Hard Collateral 1-1 === Each of the multiple elements, including the speech recognition unit, generation unit, monitoring unit, and calendar creation unit, is implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the speech recognition unit detects conversation content using the microphone 38B of the smart device 14 and converts the speech into text using the specific processing unit 290 of the data processing device 12. The generation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text content and automatically creates "minutes," "ToDos," "WBS," and the like. The monitoring unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, monitors the progress of tasks and issues alerts as necessary. The calendar creation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, determines when the next meeting is needed, automatically creates a calendar, and sends it to relevant parties. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned voice recognition unit, generation unit, monitoring unit, and calendar creation unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit detects conversation content using the microphone 238 of the smart glasses 214 and converts the speech into text using the specific processing unit 290 of the data processing device 12. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text content and automatically creates "minutes," "ToDos," "WBS," etc. The monitoring unit, realized, for example, by the specific processing unit 290 of the data processing device 12, monitors the progress of tasks and issues alerts as necessary. The calendar creation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, determines the next necessary meeting time, automatically creates a calendar, and sends it to relevant parties. === Hard Collateral 1-3 === Each of the multiple elements, including the speech recognition unit, generation unit, monitoring unit, and calendar creation unit, is implemented, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the speech recognition unit detects conversation content using the microphone 238 of the headset terminal 314 and converts the speech into text using the specific processing unit 290 of the data processing device 12. The generation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text content and automatically creates "minutes," "ToDo," "WBS," and the like. The monitoring unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, monitors the progress of tasks and issues alerts as necessary. The calendar creation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, determines when the next meeting is needed, automatically creates a calendar, and sends it to relevant parties. === Hard Collateral 1-4 === Each of the multiple elements, including the speech recognition unit, generation unit, monitoring unit, and calendar creation unit, is implemented, for example, by at least one of the robot 414 and the data processing device 12. For example, the speech recognition unit detects conversation content using the microphone 238 of the robot 414 and converts the speech into text using the specific processing unit 290 of the data processing device 12. The generation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzes the text content and automatically creates "minutes," "ToDos," "WBS," and the like. The monitoring unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, monitors the progress of tasks and issues alerts as necessary. The calendar creation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, determines when the next meeting is needed, automatically creates a calendar, and sends it to relevant parties.

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

[0090] The automatic conversation recording system can also be equipped with a translation unit, which can translate conversation content into other languages ​​in real time. For example, a conversation held in English can be translated into Japanese, and meeting minutes and to-do lists can be created in Japanese. Or, a conversation held in French can be translated into English, and a WBS can be created in English. This facilitates communication between parties who speak different languages, and helps international projects proceed more smoothly.

[0091] The speech recognition unit can be equipped with a function to automatically adjust the speed of speech. For example, if the speech is too fast, the speech recognition unit can automatically slow down the speech before transcribing. Alternatively, if the speech is too slow, the speech recognition unit can speed up the speech before transcribing. Furthermore, the strength of noise reduction can be adjusted according to the speed of speech. This allows for accurate transcription regardless of the speed of speech.

[0092] The generation unit can analyze the emotions of conversations and adjust the priority of meeting minutes and to-do lists based on the emotions. For example, parts of a conversation that express strong emotions can be prioritized in the minutes. Tasks with many emotional comments can also be prioritized when added to the to-do list. Furthermore, the importance of tasks in the WBS can be adjusted according to the strength of emotions. This enables prioritization based on emotions, preventing important tasks from being overlooked.

[0093] When monitoring the progress of tasks, the monitoring unit can generate alerts taking into account task dependencies. For example, if a task cannot start until the next task is completed, an alert will be generated if the progress of that task is behind schedule. Also, if dependent tasks are progressing simultaneously, an alert can be generated based on a comprehensive evaluation of the progress. Furthermore, if dependent tasks are progressing smoothly, an alert can be suppressed. This enables progress management that takes task dependencies into account.

[0094] The calendar creation section can be added with a function that automatically suggests the optimal meeting location based on the content of the conversation and the progress of tasks. For example, it can suggest the optimal meeting location based on the geographical location information of the people involved. It can also adjust the meeting location taking into account the schedules of the people involved. It can also comprehensively evaluate the content of the conversation and the progress of tasks to suggest the optimal meeting location. This minimizes the travel time of the people involved and enables efficient meetings.

[0095] The speech recognition unit can estimate the user's emotions and provide speech recognition feedback based on the estimated user emotions. For example, if the user is nervous, the speech recognition unit can provide feedback to relax. Also, if the user is relaxed, the speech recognition unit can provide feedback to maintain the relaxed state. Furthermore, if the user is in a hurry, the speech recognition unit can also provide feedback to quickly transcribe the speech. This makes it possible to provide feedback according to the user's emotions, improving the accuracy of speech recognition.

[0096] The speech recognition unit can analyze background sounds of a conversation and enhance specific noises to improve the accuracy of speech recognition. For example, it can enhance the sound of an air conditioner in a conference room and remove other noises. It can also enhance the noise of a cafe to extract only the conversation. It can also enhance the sound of a car running. In this way, enhancing specific noises improves the accuracy of speech recognition.

[0097] The speech recognition unit can be equipped with the ability to understand the context of a conversation and automatically recognize and convert specific phrases and expressions. For example, it can automatically recognize specific phrases used in business meetings and convert them to the appropriate terminology. It can also automatically recognize specific expressions used in casual conversations and accurately transcribe them. It can also automatically recognize technical terms and abbreviations and convert them to the appropriate terminology. This allows for accurate transcription by automatically recognizing and converting specific phrases and expressions.

[0098] The speech recognition unit can estimate the user's emotions and filter the results of speech recognition based on the estimated user's emotions. For example, if the user is angry, emotional statements can be filtered and only the calm parts can be transcribed. Also, if the user is sad, emotional statements can be filtered and only important information can be transcribed. Furthermore, if the user is excited, emotional statements can be filtered and only the calm parts can be transcribed. In this way, filtering the results of speech recognition according to the user's emotions enables more appropriate transcription.

[0099] During speech recognition, the speech recognition unit can analyze the characteristics of the speaker's voice and apply a speech recognition model optimized for each individual speaker. For example, it can analyze the characteristics of speaker A's voice and apply a dedicated speech recognition model. It can also analyze the characteristics of speaker B's voice and apply a dedicated speech recognition model. It can also analyze the characteristics of speaker C's voice and apply a dedicated speech recognition model. In this way, by applying a speech recognition model optimized for each speaker, the accuracy of speech recognition is improved.

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

[0101] Step 1: The speech recognition unit converts the speech into text. This includes business meetings and casual conversations. The speech recognition unit converts the speech into text in real time using, for example, the speech recognition AI "Whisper" or a Chrome extension. The speech recognition AI analyzes the speech data using a deep learning model and converts it into text data. Preprocessing of the speech data involves noise removal and speech normalization, and then the deep learning model is used to convert the speech into text. Step 2: The generation unit analyzes the content transcribed by the speech recognition unit and automatically creates "minutes," "ToDos," "WBS," etc. The generation unit uses generation AI to analyze the transcribed content and extract important points and tasks. The generation AI uses natural language processing technology to analyze the text data, extract important points based on the frequency of keywords and the importance of the context, and automatically create "minutes," "ToDos," and "WBS." Step 3: The monitoring unit monitors the progress of the tasks generated by the generation unit and issues an alert if there is no progress. The monitoring unit uses the generation AI to monitor the progress of the tasks and issues an alert for tasks whose deadlines are approaching or for which there is no progress. The generation AI evaluates the progress based on the task completion rate and deadline compliance status and issues an alert. Step 4: The calendar creation unit automatically creates a calendar for the next meeting required based on tasks determined by the monitoring unit to be no progress, and automatically sends it to the relevant parties. The calendar creation unit uses the generation AI to determine when the next meeting is required based on the content of the conversation and the progress of the task, and automatically creates a calendar. The generation AI predicts when the next meeting is required based on the progress of the task, and automatically creates a calendar.

[0102] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

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

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

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

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

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

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

[0139] 7, 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

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

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

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

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

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0155] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0156] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0167] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0171] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0173] [Explanation of symbols]

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

Claims

1. A voice recognition unit that converts the contents of the conversation into text; a generation unit that analyzes the content transcribed by the speech recognition unit and automatically creates minutes, ToDos, and WBS; a monitoring unit that monitors the progress of the task generated by the generation unit and issues an alert when there is no progress; a calendar creation unit that automatically creates a calendar when the next meeting is required based on the task for which the monitoring unit has determined that there is no progress, and automatically sends the calendar to the relevant parties. A system characterized by:

2. The voice recognition unit Using voice recognition AI to transcribe conversations in real time 2. The system of claim 1.

3. The generation unit Analyzes written content, extracts important points and tasks, and automatically creates minutes, ToDos, and WBS.

2. The system of claim 1.

4. The monitoring unit Monitor task progress and get alerts for tasks that are approaching deadlines or have no progress 2. The system of claim 1.

5. The calendar creation unit Based on the content of conversations and the progress of tasks, it determines when the next meeting is needed, automatically creates a calendar entry, and automatically sends it to the relevant parties.

2. The system of claim 1.

6. The voice recognition unit Estimates user emotions and dynamically adjusts speech recognition accuracy based on the estimated user emotions.

2. The system of claim 1.

7. The voice recognition unit Analyzes background sounds in conversations and optimizes noise reduction to improve speech recognition accuracy 2. The system of claim 1.

8. The voice recognition unit Add functionality to understand the context of conversations and automatically recognize and convert technical terms and abbreviations 2. The system of claim 1.

Images