System

Abstract

An object of the system according to the embodiment is to automate the creation of minutes of a meeting and provide an environment in which an employee can freely ask questions.SOLUTION: A system according to an embodiment includes a conversation input unit, a minutes generation unit, and a question association unit. The conversation input unit inputs the conversation of the conference to the generation AI together with the prompt. A minutes generation part analyzes the conversation and prompt of the conference input by the conversation input part, and generates easy-to-understand minutes. The question answering unit provides an appropriate answer to the question of the employee based on the minutes generated by the minutes generation unit and the conversation data of the conference.SELECTED DRAWING: Figure 1

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 techniques have had the drawback of requiring a lot of time and effort to create minutes of meetings, and employees have to rely on the minutes taker when they have questions about the meeting content.

[0005] The system according to the embodiment aims to automate the creation of meeting minutes and provide an environment in which employees can freely ask questions. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation input unit, a minutes generation unit, and a question response unit. The conversation input unit inputs the meeting conversation along with prompts to the generation AI. The minutes generation unit analyzes the meeting conversation and prompts input by the conversation input unit and generates easy-to-understand minutes. The question response unit provides appropriate answers to employees' questions based on the minutes and meeting conversation data generated by the minutes generation unit. [Effects of the Invention]

[0007] The system according to the embodiment automates the creation of meeting minutes and provides an environment in which employees can freely ask questions. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 minutes generation system according to an embodiment of the present invention inputs meeting conversations along with prompts into a generation AI, automatically generating easy-to-understand minutes. Furthermore, if an employee has any questions about the meeting content, they can ask the generation AI directly without asking the minutes maker. This allows the minutes generation system to efficiently record the contents of meetings and quickly resolve employee questions.

[0029] A minutes generation system according to an embodiment includes a conversation input unit, a minutes generation unit, and a question response unit. The conversation input unit inputs the meeting conversation along with prompts to the generation AI. For example, the conversation during the meeting may be recorded and the resulting audio data may be input to the generation AI. The conversation input unit may also input prompts summarizing the contents of the meeting to the generation AI. For example, a prompt such as, "The topic of this meeting is the development plan for a new product. Please prepare minutes that clearly explain the contents of the meeting," may be input to the generation AI. The minutes generation unit analyzes the conversation and prompts input by the conversation input unit and generates easy-to-understand minutes. For example, the generation AI generates minutes that include important points, decisions, action items, etc., based on the input conversation and prompts. For example, minutes may be generated in the format, "The following decisions have been made regarding the new product development plan: 1. Confirm the development schedule. 2. Secure the necessary resources. 3. Adjust the date for the next meeting." The question response unit provides appropriate answers to employees' questions based on the minutes generated by the minutes generation unit and the conversation data from the meeting. For example, if an employee asks the generation AI a question such as, "What is the development schedule for a new product?", the question response unit generates an answer such as, "The development schedule is as follows: 1. Planning stage: January to February 2. Prototype stage: March to April 3. Productization: May to June." As a result, the minutes generation system according to the embodiment can efficiently record the contents of meetings and quickly resolve employees' questions.

[0030] The conversation input unit can transcribe meeting conversations in real time and input the text data sequentially to the generation AI. For example, the conversation input unit can transcribe the audio during a meeting in real time and input the text data sequentially to the generation AI. For example, text data can be generated sequentially as the meeting progresses, and the generation AI analyzes it each time. This makes it possible to generate minutes immediately after the meeting ends.

[0031] The conversation input unit can automatically recognize technical terms and abbreviations contained in meeting conversations and generate appropriate prompts. The conversation input unit will build a system that automatically recognizes technical terms and abbreviations contained in meeting conversations and generates appropriate prompts. For example, it will automatically detect medical and technical terms and input them into the generation AI. This will allow technical terms and abbreviations to be processed appropriately, improving the accuracy of meeting minutes.

[0032] When inputting the conversation of a meeting, the conversation input unit can simultaneously analyze the video data of the video conference and generate prompts that take into account the speaker's facial expressions and gestures. The conversation input unit, for example, builds a system that simultaneously analyzes the audio data and video data of a meeting and generates prompts that take into account the speaker's facial expressions and gestures. For example, it estimates the emotion of the speaker from their facial expression and reflects the result in the prompt. This generates prompts that take into account the speaker's facial expressions and gestures, improving the quality of meeting minutes.

[0033] The conversation input unit can generate minutes in multiple languages ​​by automatically translating meeting conversations held in different languages ​​and inputting them into the generation AI. The conversation input unit, for example, builds a system that automatically translates meeting conversations held in different languages ​​and inputs them into the generation AI. For example, a meeting held in English can be translated into Japanese and input into the generation AI. This makes it possible to generate minutes in multiple languages.

[0034] The minutes generation unit can automatically highlight and visually emphasize important points of a meeting in the minutes it generates. For example, when the generation AI generates minutes, the minutes generation unit adds a function to automatically highlight and visually emphasize important points of a meeting. For example, important decisions and action items can be displayed in bold or color. This makes the minutes easier to understand by visually emphasizing important points.

[0035] The minutes generation unit can generate more consistent minutes by referring to related past meeting records and documents when summarizing the contents of a meeting. For example, the minutes generation unit automatically refers to related past meeting records and documents when summarizing the contents of a meeting, building a system that generates consistent minutes. For example, it searches past minutes and extracts related information. This allows consistent minutes to be generated by referring to past meeting records and documents.

[0036] The minutes generation unit can output the generated minutes in audio or video format, and provide them in a variety of formats that appeal to the visual and auditory senses. The minutes generation unit, for example, builds a system that outputs the generated minutes in audio format and provides them in a variety of formats that appeal to the visual and auditory senses. For example, the minutes are read aloud using speech synthesis technology. This makes it possible to provide information that appeals to the visual and auditory senses by providing the minutes in a variety of formats.

[0037] The minutes generation unit can automatically register tasks and action items included in the generated minutes into a task management tool. The minutes generation unit, for example, builds a system that automatically registers tasks and action items included in the generated minutes into a task management tool. For example, it analyzes the contents of the minutes and adds tasks to the task management tool. This makes task management more efficient by automatically registering tasks and action items into the management tool.

[0038] The question response unit can analyze the intent of the question when an employee asks the generation AI a question and automatically search for additional information to provide the optimal answer. For example, when an employee asks the generation AI a question, the question response unit builds a system that analyzes the intent of the question and automatically searches for additional information to provide the optimal answer. For example, it automatically searches for documents and data related to the content of the question. This improves the accuracy of the answer by analyzing the intent of the question and automatically searching for additional information to provide the optimal answer.

[0039] The question response unit can generate a more accurate answer by referring to related past questions and answers when providing an answer to a question. For example, the question response unit automatically refers to related past questions and answers when providing an answer to a question, and builds a system that generates a more accurate answer. For example, the question response unit searches a database of past questions and extracts related answers. In this way, by referring to past questions and answers, the accuracy of the answer is improved.

[0040] The question response unit can provide an interface that allows employees to ask questions more intuitively by using voice input or a chatbot when asking questions to the generation AI. The question response unit builds a system that provides an interface that allows employees to ask questions more intuitively by using voice input or a chatbot when asking questions to the generation AI, for example. For example, questions can be input by voice using voice recognition technology. This allows employees to ask questions intuitively by using voice input or a chatbot.

[0041] The question response unit can automatically attach related video clips and diagrams when providing an answer to a question, thereby providing an answer that is visually easy to understand. The question response unit, for example, automatically attaches related video clips and diagrams when providing an answer to a question, thereby building a system that provides an answer that is visually easy to understand. For example, the question response unit automatically searches for and attaches video clips related to the answer. In this way, by attaching video clips and diagrams, it is possible to provide an answer that is visually easy to understand.

[0042] The minutes generation unit can automatically tag the generated minutes to improve searchability. The minutes generation unit, for example, builds a system that automatically tags the generated minutes to improve searchability. For example, tags are automatically generated and assigned based on the contents of the minutes. This automatically tags the minutes, improving searchability.

[0043] The minutes generation unit can link the generated minutes to related projects and tasks when saving them, and link them to a project management tool. For example, when saving the generated minutes, the minutes generation unit links them to related projects and tasks, and builds a system that links them to a project management tool. For example, it adds tasks to a project management tool based on the contents of the minutes. In this way, linking the minutes to projects and tasks makes project management more efficient.

[0044] The minutes generation unit can link the generated minutes with an in-house SNS or chat tool to make them easily accessible to employees. The minutes generation unit, for example, builds a system that links the generated minutes with an in-house SNS or chat tool to make them easily accessible to employees. For example, the minutes can be automatically posted to an in-house SNS. In this way, by linking the minutes with an in-house SNS or chat tool, employees can easily access them.

[0045] The minutes generation unit can add a version management function when saving the generated minutes, making it possible to compare them with past minutes and check the change history. The minutes generation unit, for example, adds a version management function when saving the generated minutes, building a system that makes it possible to compare them with past minutes and check the change history. For example, the change history of the minutes is automatically recorded. By adding the version management function, it becomes possible to compare them with past minutes and check the change history.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The minutes generation system can also automatically record the frequency and duration of speech by meeting participants and reflect this in the minutes. For example, it can tally up the number of times each participant spoke and the duration of their speech, and add information to the minutes such as "Participant A spoke 10 times for a total of 15 minutes." This makes it possible to visually grasp the progress of the meeting and the contribution of each participant. It is also possible to evaluate the efficiency of the meeting based on the frequency and duration of speech.

[0048] The minutes generation system can also automatically categorize the contents of meetings and generate summaries for each category. For example, if a meeting has multiple agenda items, a summary can be generated for each agenda item, and the items can be organized as "Agenda 1: New product development plan" and "Agenda 2: Marketing strategy." This makes the minutes more organized, allowing users to quickly find the information they need when referencing them later.

[0049] The minutes generation system can also automatically analyze the content of meetings and extract risks and issues contained in the minutes. For example, it can automatically detect risks and issues discussed during meetings and add them to the minutes as "Risk: Delay in development schedule" or "Issue: Lack of necessary resources." This clarifies the important risks and issues discussed in meetings and can be used as a reference for taking countermeasures.

[0050] The minutes generation system can also automatically analyze the content of meetings and classify the positive and negative elements contained in the minutes. For example, it can automatically detect the positive elements (success stories and good ideas) and negative elements (problems and failures) discussed during a meeting and add them to the minutes as "Positive: Market response to new product was good" or "Negative: Development costs exceeded budget." This allows for a more balanced understanding of the content of meetings.

[0051] The minutes generation system can also automatically analyze the content of meetings, extract and evaluate proposals and ideas included in the minutes. For example, it can automatically detect proposals and ideas raised during a meeting and add them to the minutes as "Proposal: New product promotion campaign" or "Idea: Product improvement utilizing customer feedback." It can also evaluate proposals and ideas, indicating their feasibility and impact. This allows proposals and ideas raised in meetings to be used effectively.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The conversation input unit inputs the meeting conversation along with a prompt into the generation AI. For example, the conversation during the meeting can be recorded and the audio data can be input into the generation AI. The conversation input unit can also input a prompt that summarizes the content of the meeting into the generation AI. For example, a prompt such as, "The topic of this meeting is the development plan for a new product. Please prepare minutes that clearly explain the content of the meeting" can be input into the generation AI. Step 2: The minutes generation section analyzes the meeting conversation and prompts input by the conversation input section and generates easy-to-understand minutes. For example, the generation AI generates minutes that include important points, decisions, and action items from the meeting based on the input conversation and prompts. For example, minutes might be generated in the form of, "The following decisions were made regarding the new product development plan: 1. Confirm the development schedule. 2. Secure the necessary resources. 3. Adjust the date for the next meeting." Step 3: The question response unit provides appropriate answers to employees' questions based on the minutes generated by the minutes generation unit and meeting conversation data. For example, if an employee asks the generation AI, "What is the development schedule for a new product?", the question response unit will generate an answer such as, "The development schedule is as follows: 1. Planning stage: January to February 2. Prototype stage: March to April 3. Productization: May to June."

[0054] (Example 2) The minutes generation system according to an embodiment of the present invention inputs meeting conversations along with prompts into a generation AI, automatically generating easy-to-understand minutes. Furthermore, if an employee has any questions about the meeting content, they can ask the generation AI directly without asking the minutes maker. This allows the minutes generation system to efficiently record the contents of meetings and quickly resolve employee questions.

[0055] A minutes generation system according to an embodiment includes a conversation input unit, a minutes generation unit, and a question response unit. The conversation input unit inputs the meeting conversation along with prompts to the generation AI. For example, the conversation during the meeting may be recorded and the resulting audio data may be input to the generation AI. The conversation input unit may also input prompts summarizing the contents of the meeting to the generation AI. For example, a prompt such as, "The topic of this meeting is the development plan for a new product. Please prepare minutes that clearly explain the contents of the meeting," may be input to the generation AI. The minutes generation unit analyzes the conversation and prompts input by the conversation input unit and generates easy-to-understand minutes. For example, the generation AI generates minutes that include important points, decisions, action items, etc., based on the input conversation and prompts. For example, minutes may be generated in the format, "The following decisions have been made regarding the new product development plan: 1. Confirm the development schedule. 2. Secure the necessary resources. 3. Adjust the date for the next meeting." The question response unit provides appropriate answers to employees' questions based on the minutes generated by the minutes generation unit and the conversation data from the meeting. For example, if an employee asks the generation AI a question such as, "What is the development schedule for a new product?", the question response unit generates an answer such as, "The development schedule is as follows: 1. Planning stage: January to February 2. Prototype stage: March to April 3. Productization: May to June." As a result, the minutes generation system according to the embodiment can efficiently record the contents of meetings and quickly resolve employees' questions.

[0056] The conversation input unit can transcribe meeting conversations in real time and input the text data sequentially to the generation AI. For example, the conversation input unit can transcribe the audio during a meeting in real time and input the text data sequentially to the generation AI. For example, text data can be generated sequentially as the meeting progresses, and the generation AI analyzes it each time. This makes it possible to generate minutes immediately after the meeting ends.

[0057] The conversation input unit can automatically recognize technical terms and abbreviations contained in meeting conversations and generate appropriate prompts. The conversation input unit will build a system that automatically recognizes technical terms and abbreviations contained in meeting conversations and generates appropriate prompts. For example, it will automatically detect medical and technical terms and input them into the generation AI. This will allow technical terms and abbreviations to be processed appropriately, improving the accuracy of meeting minutes.

[0058] The conversation input unit can use the emotion estimation function to analyze the emotions of speakers during a meeting and generate prompts according to changes in their emotions. The conversation input unit, for example, builds a system that analyzes the emotions of speakers during a meeting and generates prompts according to changes in their emotions. For example, it analyzes the speaker's tone of voice and facial expressions and inputs the emotional data into the generation AI. This generates prompts that take the speaker's emotions into consideration, improving the quality of meeting minutes.

[0059] When inputting the conversation of a meeting, the conversation input unit can simultaneously analyze the video data of the video conference and generate prompts that take into account the speaker's facial expressions and gestures. The conversation input unit, for example, builds a system that simultaneously analyzes the audio data and video data of a meeting and generates prompts that take into account the speaker's facial expressions and gestures. For example, it estimates the emotion of the speaker from their facial expression and reflects the result in the prompt. This generates prompts that take into account the speaker's facial expressions and gestures, improving the quality of meeting minutes.

[0060] The conversation input unit can generate minutes in multiple languages ​​by automatically translating meeting conversations held in different languages ​​and inputting them into the generation AI. The conversation input unit, for example, builds a system that automatically translates meeting conversations held in different languages ​​and inputs them into the generation AI. For example, a meeting held in English can be translated into Japanese and input into the generation AI. This makes it possible to generate minutes in multiple languages.

[0061] The minutes generation unit can automatically highlight and visually emphasize important points of a meeting in the minutes it generates. For example, when the generation AI generates minutes, the minutes generation unit adds a function to automatically highlight and visually emphasize important points of a meeting. For example, important decisions and action items can be displayed in bold or color. This makes the minutes easier to understand by visually emphasizing important points.

[0062] The minutes generation unit can generate more consistent minutes by referring to related past meeting records and documents when summarizing the contents of a meeting. For example, the minutes generation unit automatically refers to related past meeting records and documents when summarizing the contents of a meeting, building a system that generates consistent minutes. For example, it searches past minutes and extracts related information. This allows consistent minutes to be generated by referring to past meeting records and documents.

[0063] The minutes generation unit uses the emotion estimation function to generate minutes that reflect the emotions of speakers during a meeting and visually show changes in emotions. The minutes generation unit, for example, uses the emotion estimation function to build a system that generates minutes that reflect the emotions of speakers during a meeting. For example, changes in the emotions of speakers are shown using colors or icons. This allows minutes that reflect the emotions of speakers to be generated and visually show changes in emotions, thereby deepening understanding of the minutes.

[0064] The minutes generation unit can output the generated minutes in audio or video format, and provide them in a variety of formats that appeal to the visual and auditory senses. The minutes generation unit, for example, builds a system that outputs the generated minutes in audio format and provides them in a variety of formats that appeal to the visual and auditory senses. For example, the minutes are read aloud using speech synthesis technology. This makes it possible to provide information that appeals to the visual and auditory senses by providing the minutes in a variety of formats.

[0065] The minutes generation unit can automatically register tasks and action items included in the generated minutes into a task management tool. The minutes generation unit, for example, builds a system that automatically registers tasks and action items included in the generated minutes into a task management tool. For example, it analyzes the contents of the minutes and adds tasks to the task management tool. This makes task management more efficient by automatically registering tasks and action items into the management tool.

[0066] The minutes generation unit uses the emotion estimation function to collect employees' emotional reactions to the contents of the minutes, which can be used to improve the minutes. The minutes generation unit, for example, uses the emotion estimation function to build a system that collects employees' emotional reactions to the contents of the minutes. For example, it analyzes the facial expressions and voices of employees who read the minutes to collect emotional data. This allows employees' emotional reactions to be collected and used to improve the minutes.

[0067] The question response unit can analyze the intent of the question when an employee asks the generation AI a question and automatically search for additional information to provide the optimal answer. For example, when an employee asks the generation AI a question, the question response unit builds a system that analyzes the intent of the question and automatically searches for additional information to provide the optimal answer. For example, it automatically searches for documents and data related to the content of the question. This improves the accuracy of the answer by analyzing the intent of the question and automatically searching for additional information to provide the optimal answer.

[0068] The question response unit can generate a more accurate answer by referring to related past questions and answers when providing an answer to a question. For example, the question response unit automatically refers to related past questions and answers when providing an answer to a question, and builds a system that generates a more accurate answer. For example, the question response unit searches a database of past questions and extracts related answers. In this way, by referring to past questions and answers, the accuracy of the answer is improved.

[0069] The question response unit can use the emotion estimation function to analyze the emotion of the questioner and provide an answer that corresponds to the emotion. For example, the question response unit uses the emotion estimation function to analyze the emotion of the questioner and builds a system that provides an answer that corresponds to the emotion based on the results. For example, if the questioner is feeling anxious, an answer that takes the emotion into consideration is provided. In this way, the questioner's satisfaction is improved by analyzing the emotion of the questioner and providing an answer that corresponds to the emotion.

[0070] The question response unit can provide an interface that allows employees to ask questions more intuitively by using voice input or a chatbot when asking questions to the generation AI. The question response unit builds a system that provides an interface that allows employees to ask questions more intuitively by using voice input or a chatbot when asking questions to the generation AI, for example. For example, questions can be input by voice using voice recognition technology. This allows employees to ask questions intuitively by using voice input or a chatbot.

[0071] The question response unit can automatically attach related video clips and diagrams when providing an answer to a question, thereby providing an answer that is visually easy to understand. The question response unit, for example, automatically attaches related video clips and diagrams when providing an answer to a question, thereby building a system that provides an answer that is visually easy to understand. For example, the question response unit automatically searches for and attaches video clips related to the answer. In this way, by attaching video clips and diagrams, it is possible to provide an answer that is visually easy to understand.

[0072] The question response unit can use the emotion estimation function to analyze the emotion of the questioner in real time and provide an answer based on that emotion. For example, the question response unit uses the emotion estimation function to analyze the emotion of the questioner in real time and builds a system that provides an answer based on that emotion based on the results. For example, if the questioner is nervous, an answer that soothes the questioner's emotions is provided. In this way, the questioner's satisfaction is improved by analyzing the emotion of the questioner in real time and providing an answer based on that emotion.

[0073] The minutes generation unit can automatically tag the generated minutes to improve searchability. The minutes generation unit, for example, builds a system that automatically tags the generated minutes to improve searchability. For example, tags are automatically generated and assigned based on the contents of the minutes. This automatically tags the minutes, improving searchability.

[0074] The minutes generation unit can link the generated minutes to related projects and tasks when saving them, and link them to a project management tool. For example, when saving the generated minutes, the minutes generation unit links them to related projects and tasks, and builds a system that links them to a project management tool. For example, it adds tasks to a project management tool based on the contents of the minutes. In this way, linking the minutes to projects and tasks makes project management more efficient.

[0075] The minutes generation unit uses the emotion estimation function to collect employees' emotional reactions to the contents of the minutes, which can be used to improve the minutes. The minutes generation unit, for example, uses the emotion estimation function to build a system that collects employees' emotional reactions to the contents of the minutes. For example, it analyzes the facial expressions and voices of employees who read the minutes to collect emotional data. This allows employees' emotional reactions to be collected and used to improve the minutes.

[0076] The minutes generation unit can link the generated minutes with an in-house SNS or chat tool to make them easily accessible to employees. The minutes generation unit, for example, builds a system that links the generated minutes with an in-house SNS or chat tool to make them easily accessible to employees. For example, the minutes can be automatically posted to an in-house SNS. In this way, by linking the minutes with an in-house SNS or chat tool, employees can easily access them.

[0077] The minutes generation unit can add a version management function when saving the generated minutes, making it possible to compare them with past minutes and check the change history. The minutes generation unit, for example, adds a version management function when saving the generated minutes, building a system that makes it possible to compare them with past minutes and check the change history. For example, the change history of the minutes is automatically recorded. By adding the version management function, it becomes possible to compare them with past minutes and check the change history.

[0078] The minutes generation unit uses the emotion estimation function to monitor employees' emotional reactions to the contents of the minutes in real time, which can be used to improve the minutes. The minutes generation unit, for example, uses the emotion estimation function to build a system that monitors employees' emotional reactions to the contents of the minutes in real time. For example, it analyzes the facial expressions and voices of employees who read the minutes and collects emotional data in real time. This makes it possible to monitor employees' emotional reactions in real time and use the data to improve the minutes.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] The minutes generation system can also automatically record the frequency and duration of speech by meeting participants and reflect this in the minutes. For example, it can tally up the number of times each participant spoke and the duration of their speech, and add information to the minutes such as "Participant A spoke 10 times for a total of 15 minutes." This makes it possible to visually grasp the progress of the meeting and the contribution of each participant. It is also possible to evaluate the efficiency of the meeting based on the frequency and duration of speech.

[0081] The minutes generation system can also automatically categorize the contents of meetings and generate summaries for each category. For example, if a meeting has multiple agenda items, a summary can be generated for each agenda item, and the items can be organized as "Agenda 1: New product development plan" and "Agenda 2: Marketing strategy." This makes the minutes more organized, allowing users to quickly find the information they need when referencing them later.

[0082] The minutes generation system can also automatically analyze the content of meetings and extract risks and issues contained in the minutes. For example, it can automatically detect risks and issues discussed during meetings and add them to the minutes as "Risk: Delay in development schedule" or "Issue: Lack of necessary resources." This clarifies the important risks and issues discussed in meetings and can be used as a reference for taking countermeasures.

[0083] The minutes generation system can also automatically analyze the content of meetings and classify the positive and negative elements contained in the minutes. For example, it can automatically detect the positive elements (success stories and good ideas) and negative elements (problems and failures) discussed during a meeting and add them to the minutes as "Positive: Market response to new product was good" or "Negative: Development costs exceeded budget." This allows for a more balanced understanding of the content of meetings.

[0084] The minutes generation system can also automatically analyze the content of meetings, extract and evaluate proposals and ideas included in the minutes. For example, it can automatically detect proposals and ideas raised during a meeting and add them to the minutes as "Proposal: New product promotion campaign" or "Idea: Product improvement utilizing customer feedback." It can also evaluate proposals and ideas, indicating their feasibility and impact. This allows proposals and ideas raised in meetings to be used effectively.

[0085] The minutes generation system can also use its emotion estimation function to analyze the emotions of speakers during a meeting and provide feedback according to changes in their emotions. For example, if a speaker is feeling anxious, the system can detect that emotion and add information such as "Speaker A is feeling anxious" to the minutes. This allows the system to grasp changes in emotions during a meeting and provide appropriate feedback.

[0086] The minutes generation system can also use emotion estimation to analyze the emotions of speakers during a meeting and generate action items based on those emotions. For example, if a speaker is feeling dissatisfied, that emotion can be detected and added to the minutes as "an action item to resolve speaker A's dissatisfaction." This allows for the generation of emotion-based action items and effective follow-up of meetings.

[0087] The minutes generation system can also use emotion estimation to analyze the emotions of speakers during the meeting and generate a summary of the minutes based on their emotions. For example, based on the emotions of the speakers, it can generate a summary such as, "The first half of the meeting proceeded in a positive atmosphere, but the second half saw an increase in anxiety and concern." This allows the system to grasp the overall atmosphere and changes in emotions during the meeting.

[0088] The minutes generation system can also use its emotion estimation function to analyze the emotions of speakers during meetings and generate improvement suggestions for the minutes based on their emotions. For example, based on the emotions of speakers, an improvement suggestion such as "To alleviate Speaker A's anxiety, provide a detailed explanation at the next meeting" can be added to the minutes. This allows for the generation of emotion-based improvement suggestions, improving the quality of meetings.

[0089] The minutes generation system can also use its emotion estimation function to analyze the emotions of speakers during meetings and provide feedback to the minutes based on their emotions. For example, based on the speaker's emotions, feedback such as "To alleviate Speaker A's anxiety, we will provide a detailed explanation at the next meeting" can be added to the minutes. This provides emotion-based feedback and improves the quality of meetings.

[0090] The processing flow of the second embodiment will be briefly explained below.

[0091] Step 1: The conversation input unit inputs the meeting conversation along with a prompt into the generation AI. For example, the conversation during the meeting can be recorded and the audio data can be input into the generation AI. The conversation input unit can also input a prompt that summarizes the content of the meeting into the generation AI. For example, a prompt such as, "The topic of this meeting is the development plan for a new product. Please prepare minutes that clearly explain the content of the meeting" can be input into the generation AI. Step 2: The minutes generation section analyzes the meeting conversation and prompts input by the conversation input section and generates easy-to-understand minutes. For example, the generation AI generates minutes that include important points, decisions, and action items from the meeting based on the input conversation and prompts. For example, minutes might be generated in the form of, "The following decisions were made regarding the new product development plan: 1. Confirm the development schedule. 2. Secure the necessary resources. 3. Adjust the date for the next meeting." Step 3: The question response unit provides appropriate answers to employees' questions based on the minutes generated by the minutes generation unit and meeting conversation data. For example, if an employee asks the generation AI, "What is the development schedule for a new product?", the question response unit will generate an answer such as, "The development schedule is as follows: 1. Planning stage: January to February 2. Prototype stage: March to April 3. Productization: May to June."

[0092] 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.

[0093] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0094] 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.

[0095] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0096] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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).

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0105] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0106] 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.

[0107] 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.

[0108] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0109] 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.

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

[0111] 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.

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

[0113] The 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.

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

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

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

[0117] Fig. 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.

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

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0120] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0122] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0124] The data processing system 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.

[0125] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0126] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

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

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0138] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0140] The data processing system 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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."

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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. [Explanation of symbols]

[0159] 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 conversation input unit that inputs the meeting conversation along with prompts into the generation AI; a minutes generation unit that analyzes the conversation and prompts of the meeting input by the conversation input unit and generates easy-to-understand minutes; a question response unit that provides appropriate answers to questions from employees based on the minutes generated by the minutes generation unit and the conversation data of the meeting. A system characterized by:

2. The conversation input unit includes: Automatically recognizes technical terms and abbreviations in meeting conversations and generates appropriate prompts 2. The system of claim 1.

3. The conversation input unit includes: When inputting the conversation, the system simultaneously analyzes the video data from the video conference and generates prompts that take into account the speaker's facial expressions and gestures.

2. The system of claim 1.

4. The minutes generation unit Automatically highlight and visually emphasize key meeting points in the generated minutes The system of claim 1 .

5. The question response unit When an employee asks a question to the generative AI, it analyzes the intent of the question and automatically searches for additional information to provide the best answer.

2. The system of claim 1.

6. The conversation input unit includes: Using emotion estimation, the system analyzes the emotions of speakers during a meeting and generates prompts according to changes in their emotions.

2. The system of claim 1.

7. The minutes generation unit Using emotion estimation, minutes are generated that reflect the emotions of the speakers during the meeting, and changes in emotions are visually displayed.

2. The system of claim 1.

8. The question response unit Using emotion estimation function, the system analyzes the questioner's emotions and provides an answer that matches their emotions.

2. The system of claim 1.

Images