System

Abstract

The object and advantages of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the claims.SOLUTION: A system includes a voice analysis part, a derailment detection part, an idea suggestion part, a time management part, a ToDo generation part, and an agenda suggestion part. The voice analysis unit analyzes the voice data in real time. The derailment detection unit detects a topic deviating from a goal of the meeting from the voice data analyzed by the voice analysis unit. The idea proposal unit proposes an idea and a solution related to the topic detected by the derailment detection unit. The time management unit supports target achievement within a set time. The ToDo generation unit automatically lists up tasks issued during the meeting. The agenda proposing section proposes the next agenda based on the contents of the meeting.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] Existing technologies lack real-time support to maximize meeting productivity and there is room for improvement.

[0005] The system according to the embodiment aims to improve the productivity of meetings. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice analysis unit, a derailment detection unit, an idea proposal unit, a time management unit, a ToDo creation unit, and an agenda proposal unit. The voice analysis unit analyzes voice data in real time. The derailment detection unit detects topics that deviate from the meeting goal from the voice data analyzed by the voice analysis unit. The idea proposal unit proposes ideas and solutions related to the topics detected by the derailment detection unit. The time management unit supports goal achievement within a set time. The ToDo creation unit automatically lists tasks that arise during a meeting. The agenda proposal unit proposes the next agenda based on the content of the meeting. [Effects of the Invention]

[0007] The system according to the embodiment can improve the productivity of meetings. [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 assistant service according to an embodiment of the present invention is a system that utilizes generative AI to dramatically improve meeting productivity. This system starts by setting the purpose of the meeting, analyzes audio data in real time, and provides a function to optimize the flow of the meeting. This allows the assistant service to use meeting time effectively and increase productivity.

[0029] The assistant service according to the embodiment includes a voice analysis unit, a derailment detection unit, an idea proposal unit, a time management unit, a to-do list generation unit, and an agenda proposal unit. The voice analysis unit analyzes voice data in real time. For example, the voice analysis unit uses a generation AI to analyze the voice data and analyze the speaker's emotions and tone in real time. The voice analysis unit can also translate voice data from different languages ​​in real time, making it useful for international meetings. The derailment detection unit detects topics that deviate from the meeting's goals from the voice data analyzed by the voice analysis unit. For example, the derailment detection unit uses a generation AI to learn from past meeting data, predict derailment patterns, and issue an alert in advance. The derailment detection unit can also analyze participants' emotions during derailments using an emotion estimation function and issue an alert at the optimal time. The idea proposal unit proposes ideas and solutions related to the topics detected by the derailment detection unit. For example, the idea proposal unit uses a generation AI to learn from past idea data and propose optimal ideas in real time. The idea suggestion unit can also use the emotion estimation function to analyze participants' emotional states and suggest ideas that will motivate them the most. The time management unit supports goal achievement within the set time frame and prevents overruns. For example, the time management unit uses generation AI to learn from past meeting data and suggest optimal time allocation in real time. The time management unit can also analyze participants' emotional states and suggest the most efficient time allocation using the emotion estimation function. The to-do generation unit automatically lists tasks raised during a meeting and shares them with participants. For example, the to-do generation unit uses generation AI to learn from past task data and suggest optimal tasks in real time. The to-do generation unit can also analyze participants' emotional states and suggest the most motivating tasks using the emotion estimation function. The agenda suggestion unit suggests the next agenda based on the content of the meeting. For example, the agenda suggestion unit uses generation AI to learn from past meeting data and suggest the optimal agenda in real time.The agenda suggestion unit can also use an emotion estimation function to analyze the emotional state of participants and suggest the most motivating agenda. As a result, the assistant service according to the embodiment can dramatically improve the productivity of meetings. For example, the digression detection function can reduce wasted time, and idea generation support can stimulate discussions. Furthermore, the time management function can ensure that meetings proceed as planned, and the automatic ToDo generation function can prevent tasks from being overlooked. Furthermore, the next agenda suggestion function can efficiently prepare for the next meeting.

[0030] The derailment detection unit can alert participants to take notice when a topic deviates from the meeting's goal. For example, the generation AI can issue an alert such as "The current topic is deviating from the purpose of the meeting," allowing participants to return to the topic. The derailment detection unit also needs to clarify the specific format and notification method of the alert. For example, an audio alert, a visual alert, and the timing of the notification. This can improve the efficiency of meetings.

[0031] The idea proposal section can propose related ideas and solutions when a discussion reaches an impasse. For example, the generation AI can suggest, "Here are some ideas for solving this problem," allowing participants to gain a new perspective. The idea proposal section also needs to clarify specific criteria and methods for detecting when a discussion reaches an impasse. For example, the frequency of comments, the length of time the discussion stagnates, etc. This can help stimulate discussion.

[0032] The time management section supports achieving goals within the set time and can prevent overruns. For example, the generation AI can issue an alert such as "10 minutes remaining," allowing participants to proceed with the discussion while being aware of time. The time management section also needs to clarify the specific criteria and detection methods for overruns. For example, exceeding the set time or using a timer. This can make meeting time management more efficient.

[0033] The ToDo generator can automatically list tasks that arise during a meeting and share them with participants. For example, the ToDo generator can generate a list such as "The following tasks have been newly added" using the generation AI and share it with participants, preventing tasks from being missed. The ToDo generator also needs to clarify the method and format for sharing tasks. For example, email notifications, sharing via chat tools, etc. This can prevent tasks from being missed.

[0034] The agenda proposal department can propose the next agenda based on the content of the meeting. For example, the generation AI can generate a list such as "We propose the following items for the next meeting agenda," allowing participants to smoothly prepare for the next meeting. The agenda proposal department also needs to clarify the specific method and criteria for proposing the next agenda. For example, past minutes, participant feedback, etc. This allows for efficient preparation for the next meeting.

[0035] The audio analysis unit can visualize the progress of the discussion based on the results of analyzing the audio data and provide feedback to the participants. The audio analysis unit, for example, builds a system that visualizes the progress of the discussion based on the results of analyzing the audio data. For example, it displays the progress of the discussion in graphs or charts and provides feedback to the participants. The audio analysis unit also needs to clarify the method and criteria for visualizing the progress. For example, a graph display, a progress bar, etc. This allows the progress of the discussion to be visually grasped.

[0036] The speech analysis unit can integrate the results of speech data analysis with text data and visual data to perform multimodal analysis. For example, the speech analysis unit can integrate the results of speech data analysis with text data and build a system that performs multimodal analysis. For example, the content of the speech data can be converted into text and integrated with the analysis results. The speech analysis unit also needs to clarify the specific methods and standards for multimodal analysis, such as the data integration method and analysis algorithm. This allows speech data to be integrated with other data for analysis.

[0037] The speech analysis unit can translate speech data in different languages ​​in real time, making it usable in international meetings. For example, the speech analysis unit builds a system that translates speech data in different languages ​​in real time. For example, English speech data can be translated into Japanese and shared with participants. The speech analysis unit also needs to clarify the specific technology and method for real-time translation, such as the translation algorithm and supported languages. This can support communication in international meetings.

[0038] The derailment detection unit can learn from past meeting data, predict derailment patterns, and issue alerts in advance. For example, the derailment detection unit constructs a system in which a generation AI learns from past meeting data and predicts derailment patterns. For example, if a specific topic is likely to cause a derailment, an alert will be issued when that topic comes up. The derailment detection unit also needs to clarify the specific type and collection method of past meeting data. For example, minutes data, audio data, etc. This will allow derailment to be prevented in advance.

[0039] The derailment detection unit can analyze the cause of derailment and propose specific improvement measures. For example, the derailment detection unit constructs a system in which a generative AI analyzes the cause of derailment and proposes specific improvement measures. For example, if a specific topic causes derailment, it can suggest avoiding that topic. The derailment detection unit also needs to clarify the specific analysis method and criteria for the cause of derailment. For example, an analysis of the topic, the content of participants' comments, etc. This allows the cause of derailment to be identified and improvement measures to be proposed.

[0040] The derailment detection unit can provide the derailment detection function in the form of at least one of a visual alert and an audio alert. The derailment detection unit, for example, builds a system that provides the derailment detection function in the form of a visual alert. For example, the derailment detection unit may notify the user of a derailment by displaying a pop-up message on the screen. The derailment detection unit must also clarify the specific format and display method of the visual alert. For example, a pop-up notification, a color change, etc. This allows the user to be notified of a derailment in a variety of formats.

[0041] The derailment detection unit can improve the accuracy of derailment detection by referring to meeting data from different industries and fields. For example, the derailment detection unit collects meeting data from different industries and fields and builds a system to improve the accuracy of derailment detection. For example, it analyzes data from the technical field and the marketing field to identify common derailment patterns. In addition, the derailment detection unit needs to clarify the specific definitions and scopes of different industries and fields. For example, the IT industry, the medical field, etc. This can improve the accuracy of derailment detection.

[0042] The idea proposal unit can learn from past idea data and propose optimal ideas in real time. For example, the idea proposal unit will build a system in which a generative AI learns from past idea data and proposes optimal ideas in real time. For example, it proposes new ideas based on past success stories. The idea proposal unit also needs to clarify the specific types of past idea data and how they are collected. For example, an idea database, meeting minutes data, etc. This will allow it to propose optimal ideas based on past data.

[0043] The idea proposal department can evaluate the quality of ideas and prioritize the proposal of the most promising ideas. For example, the idea proposal department can build a system in which generative AI evaluates the quality of ideas and prioritizes the proposal of the most promising ideas. For example, evaluation can be based on technical feasibility or market demand. The idea proposal department also needs to clarify the specific evaluation criteria and methods for the quality of ideas. For example, feasibility, innovativeness, etc. This allows the most promising ideas to be prioritized.

[0044] The idea suggestion unit can convert ideas into visual notes or mind maps to promote visual understanding. For example, the idea suggestion unit can convert ideas into visual notes and build a system that makes them easier to understand visually. For example, the idea suggestion unit can display ideas in graphs or charts to make them easier to understand visually. The idea suggestion unit also needs to clarify the specific format and creation method of the visual notes. For example, handwritten notes, digital notes, etc. This makes it easier to understand ideas visually.

[0045] The idea proposal department can refer to ideas from different industries and fields and propose crossover ideas. For example, the idea proposal department could register ideas from different industries and fields in a database and use them as reference to build a system that proposes crossover ideas. For example, combining ideas from the technical field and the marketing field. The idea proposal department also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows innovative ideas to be proposed by referring to ideas from different industries and fields.

[0046] The time management unit can learn from past meeting data and propose optimal time allocation in real time. For example, the time management unit will build a system in which a generative AI learns from past meeting data and proposes optimal time allocation in real time. For example, it proposes time allocation based on past success stories. The time management unit also needs to clarify the specific types of past meeting data and how they are collected. For example, minutes data, audio data, etc. This will allow it to propose optimal time allocation based on past data.

[0047] The time management unit can visualize the progress of time management and provide feedback to participants. The time management unit, for example, builds a system that visualizes the progress of time management and provides feedback to participants. For example, the progress can be displayed in a graph or chart and feedback can be provided to participants. The time management unit also needs to clarify the method and criteria for visualizing the progress. For example, a graph display, a progress bar, etc. This allows participants to visually grasp the progress of time management.

[0048] The time management unit can provide time management in various formats, such as a visual timer or audio alerts. For example, the time management unit builds a system that provides time management using a visual timer. For example, a timer is displayed on the screen to visually indicate the passage of time. The time management unit also needs to clarify the specific format and display method of the visual timer. For example, a digital timer, an analog timer, etc. This allows time management to be notified in various formats.

[0049] The time management department can refer to time management methods from different industries and fields to perform crossover time management. For example, the time management department could register time management methods from different industries and fields in a database and use them as reference to build a system for crossover time management. For example, it could combine time management methods from the technical field and the marketing field. The time management department also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows for effective time management by referring to time management methods from different industries and fields.

[0050] The ToDo generation unit can learn from past task data and suggest optimal tasks in real time. For example, the ToDo generation unit builds a system in which the generation AI learns from past task data and suggests optimal tasks in real time. For example, it suggests new tasks based on past success stories. The ToDo generation unit also needs to clarify the specific types of past task data and how they are collected. For example, data from task management tools, meeting minutes data, etc. This allows it to suggest optimal tasks based on past data.

[0051] The ToDo generation unit can evaluate the priority of tasks and prioritize the list of the most important tasks. For example, the ToDo generation unit can build a system in which the generation AI evaluates the priority of tasks and prioritizes the list of the most important tasks. For example, it can evaluate based on technical importance or deadlines. The ToDo generation unit also needs to clarify the specific evaluation criteria and methods for task priority. For example, urgency, importance, etc. This allows the most important tasks to be prioritized.

[0052] The ToDo generator can convert the ToDo list into a visual note or mind map to promote visual understanding. The ToDo generator, for example, converts the ToDo list into a visual note, building a system that makes it easier to understand visually. For example, it can display tasks in graphs or charts to make them easier to understand visually. The ToDo generator also needs to clarify the specific format and creation method of the visual note. For example, it can be a handwritten note, a digital note, etc. This makes it easier to understand the tasks visually.

[0053] The ToDo generation unit can refer to task management methods from different industries and fields to perform crossover task management. For example, the ToDo generation unit registers task management methods from different industries and fields in a database and uses them as reference to build a system for crossover task management. For example, it combines task management methods from the technical field and the marketing field. The ToDo generation unit also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows for effective task management by referring to task management methods from different industries and fields.

[0054] The agenda proposal unit can learn from past meeting data and propose optimal agendas in real time. For example, the agenda proposal unit will build a system in which a generation AI learns from past meeting data and proposes optimal agendas in real time. For example, it will propose a new agenda based on past success stories. The agenda proposal unit also needs to clarify the specific types of past meeting data and how they are collected. For example, minutes data, audio data, etc. This will allow it to propose optimal agendas based on past data.

[0055] The Agenda Proposal Department can evaluate the quality of agendas and prioritize the proposal of the most promising agendas. For example, the Agenda Proposal Department could build a system in which a generative AI evaluates the quality of agendas and prioritizes the proposal of the most promising agendas. For example, evaluation could be based on technical feasibility or importance of the discussion. The Agenda Proposal Department also needs to clarify the specific evaluation criteria and methods for the quality of agendas. For example, feasibility, innovativeness, etc. This would allow the most promising agendas to be prioritized.

[0056] The agenda suggestion unit can convert the agenda into a visual note or a mind map to promote visual understanding. The agenda suggestion unit, for example, converts the agenda into a visual note and builds a system that makes it easier to understand visually. For example, the agenda can be displayed in a graph or chart to make it easier to understand visually. The agenda suggestion unit also needs to clarify the specific format and creation method of the visual note. For example, handwritten notes, digital notes, etc. This makes it easier to understand the agenda visually.

[0057] The agenda proposal unit can refer to agendas from different industries and fields and propose crossover agendas. For example, the agenda proposal unit could register agendas from different industries and fields in a database and build a system that uses them as reference to propose crossover agendas. For example, combining agendas from the technical field and the marketing field. The agenda proposal unit also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows it to propose innovative agendas by referring to agendas from different industries and fields.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The assistant service can also be equipped with a summary section that summarizes what participants say and displays it in real time. For example, the summary section could use generative AI to create a short summary of what is said and display it to participants. The summary section also needs to clearly define the method and criteria for summarizing what is said. For example, it could extract important keywords, frequency of comments, etc. This allows participants to quickly grasp the main points of the discussion.

[0060] The derailment detection unit can analyze the content of participants' comments and make suggestions to support the progress of the discussion. For example, the derailment detection unit can use generative AI to analyze the content of comments and make suggestions to correct the direction of the discussion. The derailment detection unit also needs to clarify the method and criteria for analyzing the content of comments. For example, the frequency of comments, the frequency of keyword appearances, etc. This can effectively support the progress of the discussion.

[0061] The idea proposal department can propose optimal ideas by taking into account the participants' expertise and skills. For example, the idea proposal department could use generative AI to analyze participants' profile data and propose ideas based on their expertise. The idea proposal department also needs to clarify specific evaluation criteria and methods for expertise and skills, such as educational background, work history, and past projects. This allows the department to propose ideas that make the most of the participants' expertise.

[0062] The time management unit can propose optimal meeting times by taking into account the schedules of participants. For example, the time management unit uses generative AI to analyze participants' calendar data and propose a time slot when everyone can attend. The time management unit also needs to clarify the method and criteria for analyzing schedules. For example, available time on the calendar, high-priority schedules, etc. This allows it to propose meeting times that are easy for everyone to attend.

[0063] The ToDo generator can track task progress in real time and visualize it. For example, the ToDo generator can use generation AI to analyze task progress data and display the progress in graphs and charts. The ToDo generator also needs to clarify the analysis method and criteria for progress. For example, task completion rate, deadline compliance, etc. This allows the task progress to be visually grasped.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The voice analysis unit analyzes voice data in real time. For example, it uses generative AI to analyze voice data and analyze the speaker's emotions and tone in real time. It also translates voice data in different languages ​​in real time, making it useful for international meetings. Step 2: The derailment detection unit uses the audio data analyzed by the audio analysis unit to detect topics that deviate from the meeting's goals. For example, it can use generative AI to learn from past meeting data, predict derailment patterns, and issue alerts in advance. It can also use emotion estimation to analyze participants' emotions during derailments and issue alerts at the optimal time. Step 3: The idea proposal unit proposes ideas and solutions related to the topics detected by the digression detection unit. For example, it uses generation AI to learn from past idea data and propose optimal ideas in real time. It can also use emotion estimation to analyze participants' emotional states and propose ideas that will motivate them the most. Step 4: The time management section helps achieve goals within the set time frame and prevents overruns. For example, it uses generative AI to learn from past meeting data and propose optimal time allocation in real time. It can also use emotion estimation to analyze participants' emotional states and propose the most efficient time allocation. Step 5: The ToDo generator automatically lists tasks that arise during the meeting and shares them with participants. For example, it uses generation AI to learn from past task data and suggest optimal tasks in real time. It can also use emotion estimation to analyze participants' emotional states and suggest tasks that will motivate them the most. Step 6: The agenda suggestion unit proposes the next agenda based on the content of the meeting. For example, it uses generative AI to learn from past meeting data and propose the optimal agenda in real time. It can also use emotion estimation to analyze the emotional state of participants and propose the most motivating agenda.

[0066] (Example 2) The assistant service according to an embodiment of the present invention is a system that utilizes generative AI to dramatically improve meeting productivity. This system starts by setting the purpose of the meeting, analyzes audio data in real time, and provides a function to optimize the flow of the meeting. This allows the assistant service to use meeting time effectively and increase productivity.

[0067] The assistant service according to the embodiment includes a voice analysis unit, a derailment detection unit, an idea proposal unit, a time management unit, a to-do list generation unit, and an agenda proposal unit. The voice analysis unit analyzes voice data in real time. For example, the voice analysis unit uses a generation AI to analyze the voice data and analyze the speaker's emotions and tone in real time. The voice analysis unit can also translate voice data from different languages ​​in real time, making it useful for international meetings. The derailment detection unit detects topics that deviate from the meeting's goals from the voice data analyzed by the voice analysis unit. For example, the derailment detection unit uses a generation AI to learn from past meeting data, predict derailment patterns, and issue an alert in advance. The derailment detection unit can also analyze participants' emotions during derailments using an emotion estimation function and issue an alert at the optimal time. The idea proposal unit proposes ideas and solutions related to the topics detected by the derailment detection unit. For example, the idea proposal unit uses a generation AI to learn from past idea data and propose optimal ideas in real time. The idea suggestion unit can also use the emotion estimation function to analyze participants' emotional states and suggest ideas that will motivate them the most. The time management unit supports goal achievement within the set time frame and prevents overruns. For example, the time management unit uses generation AI to learn from past meeting data and suggest optimal time allocation in real time. The time management unit can also analyze participants' emotional states and suggest the most efficient time allocation using the emotion estimation function. The to-do generation unit automatically lists tasks raised during a meeting and shares them with participants. For example, the to-do generation unit uses generation AI to learn from past task data and suggest optimal tasks in real time. The to-do generation unit can also analyze participants' emotional states and suggest the most motivating tasks using the emotion estimation function. The agenda suggestion unit suggests the next agenda based on the content of the meeting. For example, the agenda suggestion unit uses generation AI to learn from past meeting data and suggest the optimal agenda in real time.The agenda suggestion unit can also use an emotion estimation function to analyze the emotional state of participants and suggest the most motivating agenda. As a result, the assistant service according to the embodiment can dramatically improve the productivity of meetings. For example, the digression detection function can reduce wasted time, and idea generation support can stimulate discussions. Furthermore, the time management function can ensure that meetings proceed as planned, and the automatic ToDo generation function can prevent tasks from being overlooked. Furthermore, the next agenda suggestion function can efficiently prepare for the next meeting.

[0068] The derailment detection unit can alert participants to take notice when a topic deviates from the meeting's goal. For example, the generation AI can issue an alert such as "The current topic is deviating from the purpose of the meeting," allowing participants to return to the topic. The derailment detection unit also needs to clarify the specific format and notification method of the alert. For example, an audio alert, a visual alert, and the timing of the notification. This can improve the efficiency of meetings.

[0069] The idea proposal section can propose related ideas and solutions when a discussion reaches an impasse. For example, the generation AI can suggest, "Here are some ideas for solving this problem," allowing participants to gain a new perspective. The idea proposal section also needs to clarify specific criteria and methods for detecting when a discussion reaches an impasse. For example, the frequency of comments, the length of time the discussion stagnates, etc. This can help stimulate discussion.

[0070] The time management section supports achieving goals within the set time and can prevent overruns. For example, the generation AI can issue an alert such as "10 minutes remaining," allowing participants to proceed with the discussion while being aware of time. The time management section also needs to clarify the specific criteria and detection methods for overruns. For example, exceeding the set time or using a timer. This can make meeting time management more efficient.

[0071] The ToDo generator can automatically list tasks that arise during a meeting and share them with participants. For example, the ToDo generator can generate a list such as "The following tasks have been newly added" using the generation AI and share it with participants, preventing tasks from being missed. The ToDo generator also needs to clarify the method and format for sharing tasks. For example, email notifications, sharing via chat tools, etc. This can prevent tasks from being missed.

[0072] The agenda proposal department can propose the next agenda based on the content of the meeting. For example, the generation AI can generate a list such as "We propose the following items for the next meeting agenda," allowing participants to smoothly prepare for the next meeting. The agenda proposal department also needs to clarify the specific method and criteria for proposing the next agenda. For example, past minutes, participant feedback, etc. This allows for efficient preparation for the next meeting.

[0073] The voice analysis unit can analyze participants' emotions and tone in real time. For example, a system can be built in which a generative AI analyzes voice data in real time to analyze the speaker's emotions and tone. For example, the voice analysis unit can analyze the speaker's tone and pitch to identify their emotional state. The voice analysis unit also needs to clarify the specific analysis methods and criteria for emotions and tone. For example, a voice analysis algorithm, emotion recognition technology, etc. This allows participants' emotions and tone to be grasped in real time.

[0074] The audio analysis unit can visualize the progress of the discussion based on the results of analyzing the audio data and provide feedback to the participants. The audio analysis unit, for example, builds a system that visualizes the progress of the discussion based on the results of analyzing the audio data. For example, it displays the progress of the discussion in graphs or charts and provides feedback to the participants. The audio analysis unit also needs to clarify the method and criteria for visualizing the progress. For example, a graph display, a progress bar, etc. This allows the progress of the discussion to be visually grasped.

[0075] The speech analysis unit can use the emotion estimation function to track the speaker's emotional changes in real time and adjust the direction of the discussion. For example, the speech analysis unit uses the emotion estimation function to build a system that tracks the speaker's emotional changes in real time. For example, it can issue an alert when the speaker's emotions change. In addition, the speech analysis unit needs to clarify the specific technology and method of the emotion estimation function. For example, machine learning algorithms, emotion datasets, etc. This allows the direction of the discussion to be adjusted appropriately.

[0076] The speech analysis unit can integrate the results of speech data analysis with text data and visual data to perform multimodal analysis. For example, the speech analysis unit can integrate the results of speech data analysis with text data and build a system that performs multimodal analysis. For example, the content of the speech data can be converted into text and integrated with the analysis results. The speech analysis unit also needs to clarify the specific methods and standards for multimodal analysis, such as the data integration method and analysis algorithm. This allows speech data to be integrated with other data for analysis.

[0077] The speech analysis unit can translate speech data in different languages ​​in real time, making it usable in international meetings. For example, the speech analysis unit builds a system that translates speech data in different languages ​​in real time. For example, English speech data can be translated into Japanese and shared with participants. The speech analysis unit also needs to clarify the specific technology and method for real-time translation, such as the translation algorithm and supported languages. This can support communication in international meetings.

[0078] The voice analysis unit uses generative AI to analyze voice data, monitor participants' emotions in real time, and make suggestions to elicit positive emotions. For example, the voice analysis unit builds a system in which generative AI analyzes voice data and monitors participants' emotions in real time. For example, it analyzes the tone and pitch of participants' voices to identify their emotional state. The voice analysis unit also needs to clarify the specific technology and usage of the generative AI, such as the AI ​​model and training data used. This will enable participants to elicit positive emotions.

[0079] The derailment detection unit can learn from past meeting data, predict derailment patterns, and issue alerts in advance. For example, the derailment detection unit constructs a system in which a generation AI learns from past meeting data and predicts derailment patterns. For example, if a specific topic is likely to cause a derailment, an alert will be issued when that topic comes up. The derailment detection unit also needs to clarify the specific type and collection method of past meeting data. For example, minutes data, audio data, etc. This will allow derailment to be prevented in advance.

[0080] The derailment detection unit can analyze the cause of derailment and propose specific improvement measures. For example, the derailment detection unit constructs a system in which a generative AI analyzes the cause of derailment and proposes specific improvement measures. For example, if a specific topic causes derailment, it can suggest avoiding that topic. The derailment detection unit also needs to clarify the specific analysis method and criteria for the cause of derailment. For example, an analysis of the topic, the content of participants' comments, etc. This allows the cause of derailment to be identified and improvement measures to be proposed.

[0081] The derailment detection unit can use the emotion estimation function to analyze the emotions of participants at the time of derailment and issue an alert at the optimal timing. The derailment detection unit, for example, uses the emotion estimation function to build a system that analyzes the emotions of participants at the time of derailment and issues an alert at the optimal timing. For example, if a participant has negative emotions, an alert is issued at that timing. The derailment detection unit also needs to clarify specific criteria and detection methods for the optimal timing. For example, changes in emotions, the progress of the discussion, etc. This allows derailment to be effectively prevented by issuing an alert at the optimal timing.

[0082] The derailment detection unit can provide the derailment detection function in the form of at least one of a visual alert and an audio alert. The derailment detection unit, for example, builds a system that provides the derailment detection function in the form of a visual alert. For example, the derailment detection unit may notify the user of a derailment by displaying a pop-up message on the screen. The derailment detection unit must also clarify the specific format and display method of the visual alert. For example, a pop-up notification, a color change, etc. This allows the user to be notified of a derailment in a variety of formats.

[0083] The derailment detection unit can improve the accuracy of derailment detection by referring to meeting data from different industries and fields. For example, the derailment detection unit collects meeting data from different industries and fields and builds a system to improve the accuracy of derailment detection. For example, it analyzes data from the technical field and the marketing field to identify common derailment patterns. In addition, the derailment detection unit needs to clarify the specific definitions and scopes of different industries and fields. For example, the IT industry, the medical field, etc. This can improve the accuracy of derailment detection.

[0084] The derailment detection unit can use the generative AI to monitor the emotions of participants in real time during a derailment and make suggestions to elicit positive emotions. For example, the derailment detection unit could build a system in which the generative AI monitors the emotions of participants in real time during a derailment and makes suggestions to elicit positive emotions. For example, it could select a topic that participants can discuss in a relaxed state. The derailment detection unit also needs to clarify the specific technology and usage of the generative AI, such as the AI ​​model and training data to be used. This will enable it to elicit positive emotions from participants during a derailment.

[0085] The idea proposal unit can learn from past idea data and propose optimal ideas in real time. For example, the idea proposal unit will build a system in which a generative AI learns from past idea data and proposes optimal ideas in real time. For example, it proposes new ideas based on past success stories. The idea proposal unit also needs to clarify the specific types of past idea data and how they are collected. For example, an idea database, meeting minutes data, etc. This will allow it to propose optimal ideas based on past data.

[0086] The idea proposal department can evaluate the quality of ideas and prioritize the proposal of the most promising ideas. For example, the idea proposal department can build a system in which generative AI evaluates the quality of ideas and prioritizes the proposal of the most promising ideas. For example, evaluation can be based on technical feasibility or market demand. The idea proposal department also needs to clarify the specific evaluation criteria and methods for the quality of ideas. For example, feasibility, innovativeness, etc. This allows the most promising ideas to be prioritized.

[0087] The idea proposal unit can use the emotion estimation function to analyze the emotional state of participants and propose ideas that will motivate them the most. For example, the idea proposal unit can use the emotion estimation function to build a system that analyzes the emotional state of participants in real time and proposes ideas that will motivate them the most. For example, it can select themes that participants have positive emotions about. The idea proposal unit also needs to clarify the specific technology and method of the emotion estimation function. For example, machine learning algorithms, emotion datasets, etc. This allows it to propose ideas that will motivate participants.

[0088] The idea suggestion unit can convert ideas into visual notes or mind maps to promote visual understanding. For example, the idea suggestion unit can convert ideas into visual notes and build a system that makes them easier to understand visually. For example, the idea suggestion unit can display ideas in graphs or charts to make them easier to understand visually. The idea suggestion unit also needs to clarify the specific format and creation method of the visual notes. For example, handwritten notes, digital notes, etc. This makes it easier to understand ideas visually.

[0089] The idea proposal department can refer to ideas from different industries and fields and propose crossover ideas. For example, the idea proposal department could register ideas from different industries and fields in a database and use them as reference to build a system that proposes crossover ideas. For example, combining ideas from the technical field and the marketing field. The idea proposal department also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows innovative ideas to be proposed by referring to ideas from different industries and fields.

[0090] The idea proposal department can use generative AI to monitor participants' emotions in real time and make suggestions that elicit positive emotions. For example, the idea proposal department could build a system in which generative AI monitors participants' emotions in real time and suggests ideas that elicit positive emotions. For example, it could select a topic that participants can discuss in a relaxed state. The idea proposal department also needs to clarify the specific technology and usage of the generative AI, such as the AI ​​model and training data to be used. This will allow it to propose ideas that elicit positive emotions in participants.

[0091] The time management unit can learn from past meeting data and propose optimal time allocation in real time. For example, the time management unit will build a system in which a generative AI learns from past meeting data and proposes optimal time allocation in real time. For example, it proposes time allocation based on past success stories. The time management unit also needs to clarify the specific types of past meeting data and how they are collected. For example, minutes data, audio data, etc. This will allow it to propose optimal time allocation based on past data.

[0092] The time management unit can visualize the progress of time management and provide feedback to participants. The time management unit, for example, builds a system that visualizes the progress of time management and provides feedback to participants. For example, the progress can be displayed in a graph or chart and feedback can be provided to participants. The time management unit also needs to clarify the method and criteria for visualizing the progress. For example, a graph display, a progress bar, etc. This allows participants to visually grasp the progress of time management.

[0093] The time management unit can use the emotion estimation function to analyze the emotional state of participants and propose the most efficient time allocation. For example, the time management unit can use the emotion estimation function to analyze the emotional state of participants in real time and build a system that proposes the most efficient time allocation. For example, it can select time periods when participants have positive emotions. In addition, the time management unit needs to clarify the specific technology and method of the emotion estimation function. For example, machine learning algorithms, emotion datasets, etc. This allows it to propose efficient time allocation that takes into account the emotional state of participants.

[0094] The time management unit can provide time management in various formats, such as a visual timer or audio alerts. For example, the time management unit builds a system that provides time management using a visual timer. For example, a timer is displayed on the screen to visually indicate the passage of time. The time management unit also needs to clarify the specific format and display method of the visual timer. For example, a digital timer, an analog timer, etc. This allows time management to be notified in various formats.

[0095] The time management department can refer to time management methods from different industries and fields to perform crossover time management. For example, the time management department could register time management methods from different industries and fields in a database and use them as reference to build a system for crossover time management. For example, it could combine time management methods from the technical field and the marketing field. The time management department also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows for effective time management by referring to time management methods from different industries and fields.

[0096] The time management unit can use generative AI to monitor participants' emotions in real time and make suggestions to elicit positive emotions. For example, the time management unit could build a system in which generative AI monitors participants' emotions in real time and suggests time management that elicits positive emotions. For example, it could select a time period when participants can discuss in a relaxed state. The time management unit also needs to clarify the specific technology and usage of the generative AI, such as the AI ​​model to be used and training data. This will enable time management that elicits positive emotions from participants.

[0097] The ToDo generation unit can learn from past task data and suggest optimal tasks in real time. For example, the ToDo generation unit builds a system in which the generation AI learns from past task data and suggests optimal tasks in real time. For example, it suggests new tasks based on past success stories. The ToDo generation unit also needs to clarify the specific types of past task data and how they are collected. For example, data from task management tools, meeting minutes data, etc. This allows it to suggest optimal tasks based on past data.

[0098] The ToDo generation unit can evaluate the priority of tasks and prioritize the list of the most important tasks. For example, the ToDo generation unit can build a system in which the generation AI evaluates the priority of tasks and prioritizes the list of the most important tasks. For example, it can evaluate based on technical importance or deadlines. The ToDo generation unit also needs to clarify the specific evaluation criteria and methods for task priority. For example, urgency, importance, etc. This allows the most important tasks to be prioritized.

[0099] The ToDo generator can use the emotion estimation function to analyze the emotional state of participants and suggest tasks that will motivate them the most. For example, the ToDo generator can use the emotion estimation function to build a system that analyzes the emotional state of participants in real time and suggests tasks that will motivate them the most. For example, it can select tasks that participants have positive emotions about. In addition, the ToDo generator needs to clarify the specific technology and method of the emotion estimation function. For example, machine learning algorithms, emotion datasets, etc. This allows it to suggest tasks that will motivate participants.

[0100] The ToDo generator can convert the ToDo list into a visual note or mind map to promote visual understanding. The ToDo generator, for example, converts the ToDo list into a visual note, building a system that makes it easier to understand visually. For example, it can display tasks in graphs or charts to make them easier to understand visually. The ToDo generator also needs to clarify the specific format and creation method of the visual note. For example, it can be a handwritten note, a digital note, etc. This makes it easier to understand the tasks visually.

[0101] The ToDo generation unit can refer to task management methods from different industries and fields to perform crossover task management. For example, the ToDo generation unit registers task management methods from different industries and fields in a database and uses them as reference to build a system for crossover task management. For example, it combines task management methods from the technical field and the marketing field. The ToDo generation unit also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows for effective task management by referring to task management methods from different industries and fields.

[0102] The ToDo generation unit can use a generation AI to monitor participants' emotions in real time and make suggestions that elicit positive emotions. For example, the ToDo generation unit can build a system in which the generation AI monitors participants' emotions in real time and suggests task management that elicits positive emotions. For example, it can select tasks that participants can work on in a relaxed state. The ToDo generation unit also needs to clarify the specific technology and usage of the generation AI, such as the AI ​​model and training data to be used. This will enable task management that elicits positive emotions in participants.

[0103] The agenda proposal unit can learn from past meeting data and propose optimal agendas in real time. For example, the agenda proposal unit will build a system in which a generation AI learns from past meeting data and proposes optimal agendas in real time. For example, it will propose a new agenda based on past success stories. The agenda proposal unit also needs to clarify the specific types of past meeting data and how they are collected. For example, minutes data, audio data, etc. This will allow it to propose optimal agendas based on past data.

[0104] The Agenda Proposal Department can evaluate the quality of agendas and prioritize the proposal of the most promising agendas. For example, the Agenda Proposal Department could build a system in which a generative AI evaluates the quality of agendas and prioritizes the proposal of the most promising agendas. For example, evaluation could be based on technical feasibility or importance of the discussion. The Agenda Proposal Department also needs to clarify the specific evaluation criteria and methods for the quality of agendas. For example, feasibility, innovativeness, etc. This would allow the most promising agendas to be prioritized.

[0105] The agenda proposal unit can use the emotion estimation function to analyze the emotional state of participants and propose the most motivating agenda. For example, the agenda proposal unit can use the emotion estimation function to analyze the emotional state of participants in real time and build a system that proposes the most motivating agenda. For example, it can select agenda items that participants have positive emotions about. In addition, the agenda proposal unit needs to clarify the specific technology and method of the emotion estimation function. For example, machine learning algorithms, emotion datasets, etc. This allows it to propose an agenda that will motivate participants.

[0106] The agenda suggestion unit can convert the agenda into a visual note or a mind map to promote visual understanding. The agenda suggestion unit, for example, converts the agenda into a visual note and builds a system that makes it easier to understand visually. For example, the agenda can be displayed in a graph or chart to make it easier to understand visually. The agenda suggestion unit also needs to clarify the specific format and creation method of the visual note. For example, handwritten notes, digital notes, etc. This makes it easier to understand the agenda visually.

[0107] The agenda proposal unit can refer to agendas from different industries and fields and propose crossover agendas. For example, the agenda proposal unit could register agendas from different industries and fields in a database and build a system that uses them as reference to propose crossover agendas. For example, combining agendas from the technical field and the marketing field. The agenda proposal unit also needs to clarify the specific definitions and scope of different industries and fields. For example, the IT industry, the medical field, etc. This allows it to propose innovative agendas by referring to agendas from different industries and fields.

[0108] The agenda proposal unit can use a generative AI to monitor participants' emotions in real time and make proposals that elicit positive emotions. For example, the agenda proposal unit could build a system in which the generative AI monitors participants' emotions in real time and proposes agendas that elicit positive emotions. For example, it could select agenda items that participants can discuss in a relaxed state. The agenda proposal unit also needs to clarify the specific technology and usage of the generative AI, such as the AI ​​model and training data to be used. This allows it to propose agendas that elicit positive emotions in participants.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The assistant service can also be equipped with a summary section that summarizes what participants say and displays it in real time. For example, the summary section could use generative AI to create a short summary of what is said and display it to participants. The summary section also needs to clearly define the method and criteria for summarizing what is said. For example, it could extract important keywords, frequency of comments, etc. This allows participants to quickly grasp the main points of the discussion.

[0111] The derailment detection unit can analyze the content of participants' comments and make suggestions to support the progress of the discussion. For example, the derailment detection unit can use generative AI to analyze the content of comments and make suggestions to correct the direction of the discussion. The derailment detection unit also needs to clarify the method and criteria for analyzing the content of comments. For example, the frequency of comments, the frequency of keyword appearances, etc. This can effectively support the progress of the discussion.

[0112] The idea proposal department can propose optimal ideas by taking into account the participants' expertise and skills. For example, the idea proposal department could use generative AI to analyze participants' profile data and propose ideas based on their expertise. The idea proposal department also needs to clarify specific evaluation criteria and methods for expertise and skills, such as educational background, work history, and past projects. This allows the department to propose ideas that make the most of the participants' expertise.

[0113] The time management unit can propose optimal meeting times by taking into account the schedules of participants. For example, the time management unit uses generative AI to analyze participants' calendar data and propose a time slot when everyone can attend. The time management unit also needs to clarify the method and criteria for analyzing schedules. For example, available time on the calendar, high-priority schedules, etc. This allows it to propose meeting times that are easy for everyone to attend.

[0114] The ToDo generator can track task progress in real time and visualize it. For example, the ToDo generator can use generation AI to analyze task progress data and display the progress in graphs and charts. The ToDo generator also needs to clarify the analysis method and criteria for progress. For example, task completion rate, deadline compliance, etc. This allows the task progress to be visually grasped.

[0115] The agenda suggestion unit can estimate participants' emotions and adjust the priority of agenda items based on their emotions. For example, the agenda suggestion unit can use the emotion estimation function to analyze participants' emotional states in real time and prioritize agenda items that elicit positive emotions. The agenda suggestion unit also needs to clarify the specific technology and methodology for the emotion estimation function, such as a machine learning algorithm or emotion dataset. This allows it to propose an agenda that takes participants' emotions into consideration.

[0116] The speech analysis unit can estimate the emotions of participants and adjust the order of speech based on their emotions. For example, the speech analysis unit can use an emotion estimation function to analyze the emotional state of participants in real time and prioritize participants with positive emotions to speak. The speech analysis unit also needs to clarify the specific technology and method of the emotion estimation function, such as a machine learning algorithm or emotion dataset. This allows the order of speech to be adjusted taking participants' emotions into account.

[0117] The derailment detection unit can estimate the emotions of participants and assess the risk of derailment based on their emotions. For example, the derailment detection unit can use an emotion estimation function to analyze the emotional state of participants in real time and determine that the risk of derailment is high when negative emotions increase. The derailment detection unit also needs to clarify the specific technology and methodology for the emotion estimation function, such as a machine learning algorithm or an emotion dataset. This will enable the evaluation of the risk of derailment based on emotions.

[0118] The idea proposal unit can estimate the emotions of participants and adjust the timing of idea proposals based on their emotions. For example, the idea proposal unit can use an emotion estimation function to analyze participants' emotional states in real time and propose ideas at a time when positive emotions are at their peak. The idea proposal unit also needs to clarify the specific technology and methodology of the emotion estimation function, such as a machine learning algorithm or emotion dataset. This allows ideas to be proposed at the optimal timing based on emotions.

[0119] The time management unit can estimate participants' emotions and suggest break times based on their emotions. For example, the time management unit can use an emotion estimation function to analyze participants' emotional states in real time and suggest breaks when negative emotions are rising. The time management unit also needs to clarify the specific technology and methodology for the emotion estimation function, such as a machine learning algorithm or emotion dataset. This allows it to suggest optimal break times based on emotions.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The voice analysis unit analyzes voice data in real time. For example, it uses generative AI to analyze voice data and analyze the speaker's emotions and tone in real time. It also translates voice data in different languages ​​in real time, making it useful for international meetings. Step 2: The derailment detection unit uses the audio data analyzed by the audio analysis unit to detect topics that deviate from the meeting's goals. For example, it can use generative AI to learn from past meeting data, predict derailment patterns, and issue alerts in advance. It can also use emotion estimation to analyze participants' emotions during derailments and issue alerts at the optimal time. Step 3: The idea proposal unit proposes ideas and solutions related to the topics detected by the digression detection unit. For example, it uses generation AI to learn from past idea data and propose optimal ideas in real time. It can also use emotion estimation to analyze participants' emotional states and propose ideas that will motivate them the most. Step 4: The time management section helps achieve goals within the set time frame and prevents overruns. For example, it uses generative AI to learn from past meeting data and propose optimal time allocation in real time. It can also use emotion estimation to analyze participants' emotional states and propose the most efficient time allocation. Step 5: The ToDo generator automatically lists tasks that arise during the meeting and shares them with participants. For example, it uses generation AI to learn from past task data and suggest optimal tasks in real time. It can also use emotion estimation to analyze participants' emotional states and suggest tasks that will motivate them the most. Step 6: The agenda suggestion unit proposes the next agenda based on the content of the meeting. For example, it uses generative AI to learn from past meeting data and propose the optimal agenda in real time. It can also use emotion estimation to analyze the emotional state of participants and propose the most motivating agenda.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0126] 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.

[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 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.

[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 (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).

[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] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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."

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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]

[0189] 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 analysis unit that analyzes voice data in real time; a digression detection unit that detects topics that deviate from the goal of the meeting from the voice data analyzed by the voice analysis unit; an idea suggestion unit that suggests ideas and solutions related to the topic detected by the derailment detection unit; A time management department that supports the achievement of goals within a set time frame; A ToDo generator that automatically lists tasks that come up during meetings, An agenda proposal department that proposes the next agenda based on the content of the meeting. A system characterized by:

2. The derailment detection unit When a topic comes up that deviates from the goal of the meeting, an alert is sent to participants to warn them.

2. The system of claim 1.

3. The idea suggestion unit When a discussion reaches an impasse, propose relevant ideas or solutions.

2. The system of claim 1.

4. The ToDo generation unit Automatically list the tasks that come up during the meeting and share them with participants 2. The system of claim 1.

5. The voice analysis unit Analyze participants' emotions and tone in real time 2. The system of claim 1.

6. The idea suggestion unit Analyze participants' emotional states using emotion estimation functionality and suggest the most motivating ideas 2. The system of claim 1.

7. The time management unit Analyze participants' emotional states using emotion estimation function and propose the most efficient time allocation.

2. The system of claim 1.

8. The agenda proposal unit Analyze participants' emotional states using an emotion estimation function and propose the most motivating agenda.

2. The system of claim 1.

Images