system

Abstract

The system according to this embodiment aims to set a goal for the discussion and to effectively control the discussion toward that goal. [Solution] The system according to the embodiment comprises a goal setting unit, a discussion control unit, a data analysis unit, and a progress support unit. The goal setting unit sets the goals of the discussion. The discussion control unit controls the discussion based on the goals set by the goal setting unit. The data analysis unit analyzes the data instructed by the discussion control unit. The progress support unit supports the progress of the discussion as instructed by the discussion control unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to clearly set the goal of the discussion and effectively control the discussion towards that goal.

[0005] The system according to the embodiment aims to set the goal of the discussion and effectively control the discussion towards that goal.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a goal setting unit, a discussion control unit, a data analysis unit, and a progress support unit. The goal setting unit sets the goals of the discussion. The discussion control unit controls the discussion based on the goals set by the goal setting unit. The data analysis unit analyzes the data instructed by the discussion control unit. The progress support unit supports the progress of the discussion as instructed by the discussion control unit. [Effects of the Invention]

[0007] The system according to this embodiment can set a goal for the discussion and effectively control the discussion toward that goal. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0028] (Example of form 1) An agent system according to an embodiment of the present invention is a system that uses generative AI to facilitate discussions and achieve goals. First, this agent system sets a goal for a discussion. Next, the agent uses generative AI and experts (humans) as participants to control the discussion so that the goal can be achieved. For example, in an idea discussion via chat about adding a new feature to a service business, the participants include a moderating AI agent, multiple generative AIs (models that freely generate ideas and analyze data), and multiple people involved in the service. In this case, the AI ​​agent recognizes the human participants as service experts, while the participants remain anonymous. The moderating AI agent plays the following roles to ensure the discussion moves in a positive direction: it asks questions that delve deeper into opinions or provide new perspectives, and if there are conflicting opinions, it offers opinions that can be developed and unified. It also instructs the generative AI to analyze data when analysis or evidence is needed. Towards the end of the discussion, the AI ​​agent specifically directs the discussion to the experts (humans) and summarizes the opinions. This mechanism allows the discussion to proceed efficiently and achieve the goal. Thus, the agent system sets a goal for the discussion, controls the discussion using generative AI and experts, and achieves the goal.

[0029] The agent system according to this embodiment comprises a goal setting unit, a discussion control unit, a data analysis unit, and a progress support unit. The goal setting unit sets the goals of the discussion. The goals of the discussion include, for example, the results to be achieved and the scope of the discussion, but are not limited to such examples. The goal setting unit sets specific goals based on the theme of the discussion, for example. The discussion control unit controls the discussion based on the goals set by the goal setting unit. The discussion control unit manages, for example, the order of speaking and the time allocation. The discussion control unit can also support the progress of the discussion using generative AI. The data analysis unit analyzes the data instructed by the discussion control unit. The data analysis unit analyzes the data based on, for example, the analysis tools used and the purpose of the analysis. The data analysis unit can also perform data analysis using generative AI. The progress support unit supports the progress of the discussion by the discussion control unit. The progress support unit supports the discussion based on, for example, a progress checklist and the timing of support. The progress support unit can also support the progress of the discussion using generative AI. As a result, the agent system according to this embodiment can consistently perform everything from setting the goals of the discussion to supporting its progress.

[0030] The goal-setting unit sets the objectives of the discussion. These objectives include, but are not limited to, the outcomes to be achieved and the scope of the discussion. For example, the goal-setting unit sets specific objectives based on the discussion topic. Specifically, if the discussion topic is the development of a new product, the goal-setting unit clarifies the characteristics of the product to be developed and the target market based on market research results and analysis of competing products. Furthermore, by setting the scope of the discussion, it prevents the discussion from going off track and promotes efficient discussion. The goal-setting unit can also use generative AI to analyze past discussion data and relevant literature and propose optimal objectives. For example, the generative AI learns from past successes and failures and sets the most appropriate objectives for the current situation based on that. This allows the goal-setting unit to clarify the direction of the discussion and enable participants to efficiently discuss towards a common goal. In addition, the goal-setting unit provides indicators for evaluating the degree of achievement of the set objectives, allowing for a quantitative understanding of the progress of the discussion. This makes it possible to monitor the progress of the discussion in real time and revise the objectives as needed.

[0031] The discussion control unit controls the discussion based on the goals set by the goal setting unit. For example, the discussion control unit manages the order of speaking and the allocation of time. Specifically, to ensure the smooth progress of the discussion, it evenly distributes speaking time to each participant and adjusts it to prevent any particular participant from speaking excessively. It can also change the agenda or narrow the focus of the discussion at an appropriate time depending on the progress of the discussion. The discussion control unit can also support the progress of the discussion using generative AI. The generative AI uses natural language processing technology to analyze the content of participants' statements in real time and grasp the progress of the discussion. For example, the generative AI evaluates the progress of the discussion from the content of participants' statements and suggests correcting the direction of the discussion as needed. The generative AI can also generate appropriate questions according to the progress of the discussion and support deepening the discussion. In this way, the discussion control unit can conduct the discussion efficiently and effectively. Furthermore, the discussion control unit provides tools to visualize the progress of the discussion, allowing participants to grasp the progress of the discussion at a glance. This allows participants to check the progress of the discussion in real time and correct the direction of the discussion as needed.

[0032] The Data Analysis Department analyzes data as instructed by the Discussion Control Department. The Data Analysis Department analyzes data based on, for example, the analytical tools used and the purpose of the analysis. Specifically, it collects data related to the discussion topic and analyzes it using statistical analysis and machine learning algorithms. For example, in a discussion about new product development, it would collect market research data and customer feedback data, and use this data to forecast product demand and conduct competitive analysis. The Data Analysis Department can also use generative AI to analyze data. Generative AI analyzes large amounts of data quickly and accurately, providing the information necessary for the discussion. For example, generative AI can analyze text data using natural language processing technology to extract important keywords and trends. Generative AI can also analyze image data using image recognition technology to provide visual information. This allows the Data Analysis Department to quickly and accurately provide the information necessary for the discussion, improving its quality. Furthermore, the Data Analysis Department provides tools to visualize the analysis results, enabling participants to intuitively understand the results. This allows participants to deepen the discussion based on the analysis results.

[0033] The discussion support unit, in turn, supports the progress of the discussion through the discussion control unit. The discussion support unit supports the discussion based, for example, on progress checklists and timing of support. Specifically, it monitors the progress of the discussion in real time and intervenes at the appropriate time if the discussion is falling behind or going off track. The discussion support unit also provides necessary materials and information to help participants proceed smoothly. The discussion support unit can also assist the discussion using generative AI. The generative AI analyzes the progress of the discussion in real time and suggests appropriate interventions if the discussion is falling behind or going off track. Furthermore, the generative AI automatically provides necessary materials and information to help participants proceed smoothly. This allows the discussion support unit to efficiently and effectively support the progress of the discussion. In addition, the discussion support unit provides tools to visualize the progress of the discussion, allowing participants to grasp the progress at a glance. This allows participants to check the progress of the discussion in real time and adjust the direction of the discussion as needed.

[0034] The agent system includes an anonymization unit that ensures the anonymity of participants. The anonymization unit ensures the anonymity of participants by, for example, hiding personal information or using anonymization technologies. The anonymization unit can also perform anonymization processing using generative AI. This ensures the anonymity of participants, thereby enabling free exchange of opinions.

[0035] The agent system includes a questioning unit that asks questions to delve deeper into opinions and provide new perspectives. The questioning unit asks questions based on factors such as the type of question and the timing of the question. The questioning unit can also generate questions using generative AI. This enables deeper discussion and the provision of new perspectives.

[0036] The agent system includes an opinion unification unit that develops and unifies potentially conflicting opinions. The opinion unification unit unifies opinions based, for example, on the process of consensus building or finding common ground. The opinion unification unit can also propose methods of opinion unification using generative AI. This makes it possible to unify conflicting opinions.

[0037] The agent system includes a summarization unit that brings in experts to discuss the final stages of a discussion and summarizes their opinions. This unit summarizes opinions based on criteria such as summarization methods and standards. It can also use generative AI to summarize opinions. This enables the summarization of opinions at the end of a discussion.

[0038] The goal-setting unit analyzes the results of past discussions and sets optimal goals. For example, it sets new goals by referencing successful goals from past discussions. It also sets goals to avoid those that failed in past discussions. Finally, it analyzes data from past discussions and sets the most effective goals. This enables goal setting that leverages the results of past discussions.

[0039] The goal-setting unit customizes the goals based on the expertise and experience of the discussion participants. For example, if the participants are experts, the goal-setting unit sets advanced goals. If the participants are beginners, the goal-setting unit sets basic goals. The goal-setting unit sets goals of appropriate difficulty according to the participants' experience. This makes it possible to set goals that are tailored to the expertise and experience of the participants.

[0040] The goal-setting unit considers the latest research and trends related to the discussion topic when setting goals. For example, the goal-setting unit sets goals by referring to the latest research findings. The goal-setting unit sets goals considering current trends. The goal-setting unit collects the latest information related to the discussion topic and sets goals. This makes it possible to set goals that take the latest research and trends into consideration.

[0041] The goal-setting unit dynamically updates the goals during goal setting, in accordance with the progress of the discussion. For example, the goal-setting unit updates the goals as the discussion progresses. The goal-setting unit adjusts the goals to reflect the opinions of the participants. The goal-setting unit flexibly changes the goals according to the progress of the discussion. This enables dynamic updating of goals in accordance with the progress of the discussion.

[0042] The discussion control unit analyzes the progress of the discussion in real time and intervenes at the optimal time. For example, if the discussion is stalled, the discussion control unit intervenes at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the discussion control unit intervenes to keep it calm. If the discussion is progressing smoothly, the discussion control unit intervenes at the appropriate time to move to the next step. This makes it possible to intervene at the optimal time according to the progress of the discussion.

[0043] The discussion control unit analyzes the speaking history of the discussion participants and controls their contributions to maintain a balance. For example, it encourages participants who speak infrequently to speak more. It also controls participants who speak frequently to give other participants opportunities to speak. The discussion control unit adjusts contributions at appropriate times to maintain a balance. This balance improves the fairness of the discussion.

[0044] The discussion control unit considers the geographical and cultural backgrounds of the participants during the discussion. For example, the discussion control unit adopts an appropriate method of discussion, taking into account the participants' geographical backgrounds. The discussion control unit adopts an appropriate method of discussion, taking into account the participants' cultural backgrounds. The discussion control unit adjusts the method of discussion, taking into account the participants' geographical and cultural backgrounds. This makes it possible to conduct discussions while considering the geographical and cultural backgrounds of the participants.

[0045] The discussion control unit adjusts the depth of the discussion according to the participants' level of expertise as the discussion progresses. For example, if a participant is an expert, the discussion control unit will deepen the discussion. If a participant is a beginner, the discussion control unit will shallow the discussion. The discussion control unit appropriately adjusts the depth of the discussion according to the participants' level of expertise. This makes it possible to adjust the depth of the discussion according to the participants' level of expertise.

[0046] The Data Analysis Department collects and analyzes relevant data in real time based on the content of the discussion. For example, the Data Analysis Department collects and analyzes data related to the topic of the discussion in real time. The Data Analysis Department collects and analyzes necessary data in real time as the discussion progresses. The Data Analysis Department collects and analyzes the most suitable data in real time based on the content of the discussion. This enables real-time data collection and analysis based on the content of the discussion.

[0047] The data analysis department selects the most suitable analytical method for the current discussion by referring to past data analysis results. For example, the data analysis department selects the optimal analytical method based on past data analysis results. The data analysis department selects an analytical method suitable for the current discussion by referring to past data analysis results. The data analysis department selects the most effective analytical method by referring to past data analysis results. This makes it possible to select the optimal analytical method by utilizing past data analysis results.

[0048] The data analysis department refers to external data sources related to the discussion topic when performing data analysis. For example, the data analysis department performs data analysis by referring to external data sources related to the discussion topic. The data analysis department uses external data sources to collect and analyze data related to the discussion topic. The data analysis department utilizes external data sources related to the discussion topic to perform optimal data analysis. As a result, the accuracy of data analysis is improved by referring to external data sources related to the discussion topic.

[0049] The data analysis department dynamically changes the focus of its analysis during data analysis, in accordance with the progress of the discussion. For example, the data analysis department appropriately changes the focus of the data analysis according to the progress of the discussion. The data analysis department adjusts the focus of the data analysis to reflect the opinions of the participants. The data analysis department flexibly changes the focus of the data analysis in accordance with the progress of the discussion. This makes it possible to dynamically change the focus of the data analysis in accordance with the progress of the discussion.

[0050] The discussion support unit monitors the progress of the discussion in real time and provides support as needed. For example, if the discussion is stalled, the support unit provides support at the appropriate time. If the discussion is becoming heated, the support unit provides support to keep it calm. If the discussion is progressing smoothly, the support unit provides support to move on to the next step. This enables the provision of real-time support according to the progress of the discussion.

[0051] The progress support unit selects the optimal progress support method by referring to the progress data of past discussions. For example, the progress support unit selects the optimal progress support method based on the progress data of past discussions. The progress support unit selects a progress support method suitable for the current discussion by referring to the progress data of past discussions. The progress support unit selects the most effective progress support method by referring to the progress data of past discussions. This makes it possible to select the optimal progress support method by utilizing the progress data of past discussions.

[0052] The progress support unit provides external resources related to the discussion topic during progress support. For example, the progress support unit provides progress support by providing external resources related to the discussion topic. The progress support unit provides information related to the discussion topic using external resources. The progress support unit provides optimal progress support by utilizing external resources related to the discussion topic. As a result, the accuracy of progress support is improved by providing external resources related to the discussion topic.

[0053] The discussion support unit dynamically changes the support provided during discussion support according to the progress of the discussion. For example, the discussion support unit appropriately changes the support provided according to the progress of the discussion. The discussion support unit adjusts the support provided by reflecting the opinions of the participants. The discussion support unit flexibly changes the support provided according to the progress of the discussion. This makes it possible to dynamically change the support provided according to the progress of the discussion.

[0054] The anonymization unit analyzes the attribute information of the discussion participants and selects the optimal anonymization method. For example, the anonymization unit selects the optimal anonymization method based on the participants' attribute information. The anonymization unit selects an anonymization method suitable for the current discussion by referring to the participants' attribute information. The anonymization unit selects the most effective anonymization method by referring to the participants' attribute information. This makes it possible to select the optimal anonymization method based on the participants' attribute information.

[0055] The anonymization unit improves the accuracy of anonymization by referring to external data related to the discussion topic during the anonymization process. For example, the anonymization unit improves the accuracy of anonymization by referring to external data related to the discussion topic. The anonymization unit uses external data to anonymize information related to the discussion topic. The anonymization unit utilizes external data related to the discussion topic to perform optimal anonymization. This improves the accuracy of anonymization by referring to external data related to the discussion topic.

[0056] The questioning team analyzes the progress of the discussion in real time and asks questions at the optimal time. For example, if the discussion is stalled, the questioning team will ask questions at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the questioning team will ask questions to keep it calm. If the discussion is progressing smoothly, the questioning team will ask questions to move to the next step. This makes it possible to ask questions at the optimal time according to the progress of the discussion.

[0057] The questioning team enriches the content of their questions by referring to external resources related to the discussion topic. For example, the questioning team enriches the content of their questions by referring to external resources related to the discussion topic. The questioning team uses external resources to reflect information related to the discussion topic in their questions. The questioning team utilizes external resources related to the discussion topic to ask the most appropriate questions. As a result, the content of the questions is enriched by referring to external resources related to the discussion topic.

[0058] The consensus-building department analyzes the progress of the discussion in real time and brings consensus at the optimal time. For example, if the discussion is stalled, the consensus-building department will bring consensus at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the consensus-building department will bring consensus to ensure it proceeds calmly. If the discussion is progressing smoothly, the consensus-building department will bring consensus to move to the next step. This makes it possible to bring consensus at the optimal time according to the progress of the discussion.

[0059] The opinion unification department, when unifying opinions, enriches the content of the unification process by referring to external resources related to the discussion topic. For example, the opinion unification department enriches the content of the unification process by referring to external resources related to the discussion topic. The opinion unification department uses external resources to reflect information related to the discussion topic in the unification process. The opinion unification department utilizes external resources related to the discussion topic to achieve optimal unification. As a result, the content of the unification process is enriched by referring to external resources related to the discussion topic.

[0060] The opinion summarization team analyzes the progress of the discussion in real time and summarizes opinions at the optimal time. For example, if the discussion is stalled, the opinion summarization team summarizes opinions at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the opinion summarization team summarizes opinions to keep it calm. If the discussion is progressing smoothly, the opinion summarization team summarizes opinions to move on to the next step. This makes it possible to summarize opinions at the optimal time according to the progress of the discussion.

[0061] The opinion summarization team enriches the content of the opinion summary by referring to external resources related to the discussion topic when summarizing opinions. For example, the opinion summarization team enriches the content of the opinion summary by referring to external resources related to the discussion topic. The opinion summarization team uses external resources to reflect information related to the discussion topic in the opinion summary. The opinion summarization team utilizes external resources related to the discussion topic to create the optimal opinion summary. As a result, the content of the opinion summary is enriched by referring to external resources related to the discussion topic.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] The discussion control unit can dynamically change the roles of participants according to the progress of the discussion. For example, if the discussion is stalled, it can change the role to allow a specific participant to take on a leadership role. If the discussion is heated, a calm participant can be assigned the role of mediator. Furthermore, if the discussion is progressing smoothly, a specific participant can be given the role of providing a new perspective. This allows for flexible role changes according to the progress of the discussion.

[0064] The anonymization function can adjust the level of anonymization according to the topic of discussion. For example, for sensitive topics, personal information can be completely hidden to enhance anonymity. On the other hand, for general topics, anonymity can be reduced and some participant attribute information can be displayed. Furthermore, the level of anonymization can be dynamically changed according to the progress of the discussion. This enables flexible anonymization that is appropriate for the topic and progress of the discussion.

[0065] The questioning section can change the format of questions according to the progress of the discussion. For example, if the discussion is stalled, open-ended questions can be used to elicit free opinions from participants. If the discussion is heated, closed-ended questions can be used to organize the discussion. Furthermore, if the discussion is progressing smoothly, follow-up questions can be used to deepen the discussion. This allows for flexible changes in the questioning format according to the progress of the discussion.

[0066] The consensus-building department can change its consensus-building methods according to the progress of the discussion. For example, if the discussion is stalled, brainstorming can be conducted to generate new ideas. If the discussion is heated, a debate format can be adopted to clarify conflicting opinions. Furthermore, if the discussion is progressing smoothly, consensus-building can be conducted to facilitate agreement. This allows for flexible changes in consensus-building methods according to the progress of the discussion.

[0067] The opinion summarization section can change the format of the opinion summary according to the progress of the discussion. For example, if the discussion is stalled, opinions can be summarized in a summary format to indicate the direction of the discussion. Also, if the discussion is heated, opinions can be organized in a bulleted list format to keep the discussion calm. Furthermore, if the discussion is progressing smoothly, opinions can be summarized in a storytelling format to deepen the discussion. This allows for flexible changes in the opinion summarization format according to the progress of the discussion.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The goal-setting unit sets the objectives of the discussion. These objectives include the results to be achieved and the scope of the discussion. The goal-setting unit sets specific objectives based on the discussion topic. Step 2: The discussion control unit controls the discussion based on the goals set by the goal setting unit. The discussion control unit can also manage the order of speaking and time allocation, and can support the progress of the discussion using generative AI. Step 3: The Data Analysis Department analyzes the data as instructed by the Discussion Control Department. The Data Analysis Department analyzes the data based on the analytical tools used and the purpose of the analysis, and may also perform data analysis using generative AI. Step 4: The progress support unit supports the progress of the discussion through the discussion control unit. The progress support unit supports the discussion based on progress checklists and support timing, and can also support the progress of the discussion using generative AI.

[0070] (Example of form 2) An agent system according to an embodiment of the present invention is a system that uses generative AI to facilitate discussions and achieve goals. First, this agent system sets a goal for a discussion. Next, the agent uses generative AI and experts (humans) as participants to control the discussion so that the goal can be achieved. For example, in an idea discussion via chat about adding a new feature to a service business, the participants include a moderating AI agent, multiple generative AIs (models that freely generate ideas and analyze data), and multiple people involved in the service. In this case, the AI ​​agent recognizes the human participants as service experts, while the participants remain anonymous. The moderating AI agent plays the following roles to ensure the discussion moves in a positive direction: it asks questions that delve deeper into opinions or provide new perspectives, and if there are conflicting opinions, it offers opinions that can be developed and unified. It also instructs the generative AI to analyze data when analysis or evidence is needed. Towards the end of the discussion, the AI ​​agent specifically directs the discussion to the experts (humans) and summarizes the opinions. This mechanism allows the discussion to proceed efficiently and achieve the goal. Thus, the agent system sets a goal for the discussion, controls the discussion using generative AI and experts, and achieves the goal.

[0071] The agent system according to this embodiment comprises a goal setting unit, a discussion control unit, a data analysis unit, and a progress support unit. The goal setting unit sets the goals of the discussion. The goals of the discussion include, for example, the results to be achieved and the scope of the discussion, but are not limited to such examples. The goal setting unit sets specific goals based on the theme of the discussion, for example. The discussion control unit controls the discussion based on the goals set by the goal setting unit. The discussion control unit manages, for example, the order of speaking and the time allocation. The discussion control unit can also support the progress of the discussion using generative AI. The data analysis unit analyzes the data instructed by the discussion control unit. The data analysis unit analyzes the data based on, for example, the analysis tools used and the purpose of the analysis. The data analysis unit can also perform data analysis using generative AI. The progress support unit supports the progress of the discussion by the discussion control unit. The progress support unit supports the discussion based on, for example, a progress checklist and the timing of support. The progress support unit can also support the progress of the discussion using generative AI. As a result, the agent system according to this embodiment can consistently perform everything from setting the goals of the discussion to supporting its progress.

[0072] The goal-setting unit sets the objectives of the discussion. These objectives include, but are not limited to, the outcomes to be achieved and the scope of the discussion. For example, the goal-setting unit sets specific objectives based on the discussion topic. Specifically, if the discussion topic is the development of a new product, the goal-setting unit clarifies the characteristics of the product to be developed and the target market based on market research results and analysis of competing products. Furthermore, by setting the scope of the discussion, it prevents the discussion from going off track and promotes efficient discussion. The goal-setting unit can also use generative AI to analyze past discussion data and relevant literature and propose optimal objectives. For example, the generative AI learns from past successes and failures and sets the most appropriate objectives for the current situation based on that. This allows the goal-setting unit to clarify the direction of the discussion and enable participants to efficiently discuss towards a common goal. In addition, the goal-setting unit provides indicators for evaluating the degree of achievement of the set objectives, allowing for a quantitative understanding of the progress of the discussion. This makes it possible to monitor the progress of the discussion in real time and revise the objectives as needed.

[0073] The discussion control unit controls the discussion based on the goals set by the goal setting unit. For example, the discussion control unit manages the order of speaking and the allocation of time. Specifically, to ensure the smooth progress of the discussion, it evenly distributes speaking time to each participant and adjusts it to prevent any particular participant from speaking excessively. It can also change the agenda or narrow the focus of the discussion at an appropriate time depending on the progress of the discussion. The discussion control unit can also support the progress of the discussion using generative AI. The generative AI uses natural language processing technology to analyze the content of participants' statements in real time and grasp the progress of the discussion. For example, the generative AI evaluates the progress of the discussion from the content of participants' statements and suggests correcting the direction of the discussion as needed. The generative AI can also generate appropriate questions according to the progress of the discussion and support deepening the discussion. In this way, the discussion control unit can conduct the discussion efficiently and effectively. Furthermore, the discussion control unit provides tools to visualize the progress of the discussion, allowing participants to grasp the progress of the discussion at a glance. This allows participants to check the progress of the discussion in real time and correct the direction of the discussion as needed.

[0074] The Data Analysis Department analyzes data as instructed by the Discussion Control Department. The Data Analysis Department analyzes data based on, for example, the analytical tools used and the purpose of the analysis. Specifically, it collects data related to the discussion topic and analyzes it using statistical analysis and machine learning algorithms. For example, in a discussion about new product development, it would collect market research data and customer feedback data, and use this data to forecast product demand and conduct competitive analysis. The Data Analysis Department can also use generative AI to analyze data. Generative AI analyzes large amounts of data quickly and accurately, providing the information necessary for the discussion. For example, generative AI can analyze text data using natural language processing technology to extract important keywords and trends. Generative AI can also analyze image data using image recognition technology to provide visual information. This allows the Data Analysis Department to quickly and accurately provide the information necessary for the discussion, improving its quality. Furthermore, the Data Analysis Department provides tools to visualize the analysis results, enabling participants to intuitively understand the results. This allows participants to deepen the discussion based on the analysis results.

[0075] The discussion support unit, in turn, supports the progress of the discussion through the discussion control unit. The discussion support unit supports the discussion based, for example, on progress checklists and timing of support. Specifically, it monitors the progress of the discussion in real time and intervenes at the appropriate time if the discussion is falling behind or going off track. The discussion support unit also provides necessary materials and information to help participants proceed smoothly. The discussion support unit can also assist the discussion using generative AI. The generative AI analyzes the progress of the discussion in real time and suggests appropriate interventions if the discussion is falling behind or going off track. Furthermore, the generative AI automatically provides necessary materials and information to help participants proceed smoothly. This allows the discussion support unit to efficiently and effectively support the progress of the discussion. In addition, the discussion support unit provides tools to visualize the progress of the discussion, allowing participants to grasp the progress at a glance. This allows participants to check the progress of the discussion in real time and adjust the direction of the discussion as needed.

[0076] The agent system includes an anonymization unit that ensures the anonymity of participants. The anonymization unit ensures the anonymity of participants by, for example, hiding personal information or using anonymization technologies. The anonymization unit can also perform anonymization processing using generative AI. This ensures the anonymity of participants, thereby enabling free exchange of opinions.

[0077] The agent system includes a questioning unit that asks questions to delve deeper into opinions and provide new perspectives. The questioning unit asks questions based on factors such as the type of question and the timing of the question. The questioning unit can also generate questions using generative AI. This enables deeper discussion and the provision of new perspectives.

[0078] The agent system includes an opinion unification unit that develops and unifies potentially conflicting opinions. The opinion unification unit unifies opinions based, for example, on the process of consensus building or finding common ground. The opinion unification unit can also propose methods of opinion unification using generative AI. This makes it possible to unify conflicting opinions.

[0079] The agent system includes a summarization unit that brings in experts to discuss the final stages of a discussion and summarizes their opinions. This unit summarizes opinions based on criteria such as summarization methods and standards. It can also use generative AI to summarize opinions. This enables the summarization of opinions at the end of a discussion.

[0080] The goal-setting unit estimates the user's emotions and adjusts the discussion goals based on those estimates. For example, if the user is stressed, the goal-setting unit adjusts the goals to be easily achievable. If the user is relaxed, the goal-setting unit sets higher goals to encourage a more challenging discussion. If the user is in a hurry, the goal-setting unit sets goals that can be achieved in a short amount of time. This enables goal setting that is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The goal-setting unit analyzes the results of past discussions and sets optimal goals. For example, it sets new goals by referencing successful goals from past discussions. It also sets goals to avoid those that failed in past discussions. Finally, it analyzes data from past discussions and sets the most effective goals. This enables goal setting that leverages the results of past discussions.

[0082] The goal-setting unit customizes the goals based on the expertise and experience of the discussion participants. For example, if the participants are experts, the goal-setting unit sets advanced goals. If the participants are beginners, the goal-setting unit sets basic goals. The goal-setting unit sets goals of appropriate difficulty according to the participants' experience. This makes it possible to set goals that are tailored to the expertise and experience of the participants.

[0083] The goal-setting unit estimates the user's emotions and determines goal priorities based on those estimated emotions. For example, if the user is stressed, the goal-setting unit prioritizes easy goals. If the user is relaxed, the goal-setting unit prioritizes challenging goals. If the user is in a hurry, the goal-setting unit prioritizes goals that can be achieved in a short time. This makes it possible to prioritize goals according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The goal-setting unit considers the latest research and trends related to the discussion topic when setting goals. For example, the goal-setting unit sets goals by referring to the latest research findings. The goal-setting unit sets goals considering current trends. The goal-setting unit collects the latest information related to the discussion topic and sets goals. This makes it possible to set goals that take the latest research and trends into consideration.

[0085] The goal-setting unit dynamically updates the goals during goal setting, in accordance with the progress of the discussion. For example, the goal-setting unit updates the goals as the discussion progresses. The goal-setting unit adjusts the goals to reflect the opinions of the participants. The goal-setting unit flexibly changes the goals according to the progress of the discussion. This enables dynamic updating of goals in accordance with the progress of the discussion.

[0086] The discussion control unit estimates the user's emotions and adjusts the discussion's progress based on those emotions. For example, if the user is tense, the discussion control unit adjusts the pace to help them relax. If the user is relaxed, the discussion control unit adopts a pace that encourages active discussion. If the user is in a hurry, the discussion control unit adopts a pace that speeds up the discussion. This makes it possible to adjust the discussion's pace according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The discussion control unit analyzes the progress of the discussion in real time and intervenes at the optimal time. For example, if the discussion is stalled, the discussion control unit intervenes at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the discussion control unit intervenes to keep it calm. If the discussion is progressing smoothly, the discussion control unit intervenes at the appropriate time to move to the next step. This makes it possible to intervene at the optimal time according to the progress of the discussion.

[0088] The discussion control unit analyzes the speaking history of the discussion participants and controls their contributions to maintain a balance. For example, it encourages participants who speak infrequently to speak more. It also controls participants who speak frequently to give other participants opportunities to speak. The discussion control unit adjusts contributions at appropriate times to maintain a balance. This balance improves the fairness of the discussion.

[0089] The discussion control unit estimates the user's emotions and adjusts the pace of the discussion based on the estimated emotions. For example, if the user is tense, the discussion control unit slows down the pace. If the user is relaxed, the discussion control unit speeds up the pace. If the user is in a hurry, the discussion control unit speeds up the pace. This makes it possible to adjust the pace of the discussion according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The discussion control unit considers the geographical and cultural backgrounds of the participants during the discussion. For example, the discussion control unit adopts an appropriate method of discussion, taking into account the participants' geographical backgrounds. The discussion control unit adopts an appropriate method of discussion, taking into account the participants' cultural backgrounds. The discussion control unit adjusts the method of discussion, taking into account the participants' geographical and cultural backgrounds. This makes it possible to conduct discussions while considering the geographical and cultural backgrounds of the participants.

[0091] The discussion control unit adjusts the depth of the discussion according to the participants' level of expertise as the discussion progresses. For example, if a participant is an expert, the discussion control unit will deepen the discussion. If a participant is a beginner, the discussion control unit will shallow the discussion. The discussion control unit appropriately adjusts the depth of the discussion according to the participants' level of expertise. This makes it possible to adjust the depth of the discussion according to the participants' level of expertise.

[0092] The data analysis department estimates the user's emotions and adjusts the perspective of the data analysis based on the estimated emotions. For example, if the user is relaxed, the data analysis department performs a detailed data analysis. If the user is in a hurry, the data analysis department performs a concise data analysis. If the user is excited, the data analysis department performs a visually stimulating data analysis. This allows for adjustment of the perspective of the data analysis according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The Data Analysis Department collects and analyzes relevant data in real time based on the content of the discussion. For example, the Data Analysis Department collects and analyzes data related to the topic of the discussion in real time. The Data Analysis Department collects and analyzes necessary data in real time as the discussion progresses. The Data Analysis Department collects and analyzes the most suitable data in real time based on the content of the discussion. This enables real-time data collection and analysis based on the content of the discussion.

[0094] The data analysis department selects the most suitable analytical method for the current discussion by referring to past data analysis results. For example, the data analysis department selects the optimal analytical method based on past data analysis results. The data analysis department selects an analytical method suitable for the current discussion by referring to past data analysis results. The data analysis department selects the most effective analytical method by referring to past data analysis results. This makes it possible to select the optimal analytical method by utilizing past data analysis results.

[0095] The data analysis department estimates the user's emotions and prioritizes data analysis based on the estimated emotions. For example, if the user is stressed, the data analysis department prioritizes simple data analysis. If the user is relaxed, the data analysis department prioritizes detailed data analysis. If the user is in a hurry, the data analysis department prioritizes rapid data analysis. This enables the prioritization of data analysis according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The data analysis department refers to external data sources related to the discussion topic when performing data analysis. For example, the data analysis department performs data analysis by referring to external data sources related to the discussion topic. The data analysis department uses external data sources to collect and analyze data related to the discussion topic. The data analysis department utilizes external data sources related to the discussion topic to perform optimal data analysis. As a result, the accuracy of data analysis is improved by referring to external data sources related to the discussion topic.

[0097] The data analysis department dynamically changes the focus of its analysis during data analysis, in accordance with the progress of the discussion. For example, the data analysis department appropriately changes the focus of the data analysis according to the progress of the discussion. The data analysis department adjusts the focus of the data analysis to reflect the opinions of the participants. The data analysis department flexibly changes the focus of the data analysis in accordance with the progress of the discussion. This makes it possible to dynamically change the focus of the data analysis in accordance with the progress of the discussion.

[0098] The progress support unit estimates the user's emotions and adjusts its progress support methods based on the estimated emotions. For example, if the user is nervous, the progress support unit adjusts its progress support methods to help the user relax. If the user is relaxed, the progress support unit adopts methods that encourage active discussion. If the user is in a hurry, the progress support unit adopts methods that expedite the discussion. This makes it possible to adjust the progress support methods according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The discussion support unit monitors the progress of the discussion in real time and provides support as needed. For example, if the discussion is stalled, the support unit provides support at the appropriate time. If the discussion is becoming heated, the support unit provides support to keep it calm. If the discussion is progressing smoothly, the support unit provides support to move on to the next step. This enables the provision of real-time support according to the progress of the discussion.

[0100] The progress support unit selects the optimal progress support method by referring to the progress data of past discussions. For example, the progress support unit selects the optimal progress support method based on the progress data of past discussions. The progress support unit selects a progress support method suitable for the current discussion by referring to the progress data of past discussions. The progress support unit selects the most effective progress support method by referring to the progress data of past discussions. This makes it possible to select the optimal progress support method by utilizing the progress data of past discussions.

[0101] The progress support unit estimates the user's emotions and determines the priority of progress support based on the estimated emotions. For example, if the user is stressed, the progress support unit prioritizes simple progress support. If the user is relaxed, the progress support unit prioritizes detailed progress support. If the user is in a hurry, the progress support unit prioritizes quick progress support. This makes it possible to prioritize progress support according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The progress support unit provides external resources related to the discussion topic during progress support. For example, the progress support unit provides progress support by providing external resources related to the discussion topic. The progress support unit provides information related to the discussion topic using external resources. The progress support unit provides optimal progress support by utilizing external resources related to the discussion topic. As a result, the accuracy of progress support is improved by providing external resources related to the discussion topic.

[0103] The discussion support unit dynamically changes the support provided during discussion support according to the progress of the discussion. For example, the discussion support unit appropriately changes the support provided according to the progress of the discussion. The discussion support unit adjusts the support provided by reflecting the opinions of the participants. The discussion support unit flexibly changes the support provided according to the progress of the discussion. This makes it possible to dynamically change the support provided according to the progress of the discussion.

[0104] The anonymization unit estimates the user's emotions and adjusts the anonymization method based on the estimated emotions. For example, if the user is nervous, the anonymization unit adopts a method that increases anonymity. If the user is relaxed, the anonymization unit adopts a method that decreases anonymity. If the user is in a hurry, the anonymization unit adopts a method that performs anonymization quickly. This makes it possible to adjust the anonymization method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The anonymization unit analyzes the attribute information of the discussion participants and selects the optimal anonymization method. For example, the anonymization unit selects the optimal anonymization method based on the participants' attribute information. The anonymization unit selects an anonymization method suitable for the current discussion by referring to the participants' attribute information. The anonymization unit selects the most effective anonymization method by referring to the participants' attribute information. This makes it possible to select the optimal anonymization method based on the participants' attribute information.

[0106] The anonymization unit estimates the user's emotions and determines the priority of anonymization based on the estimated emotions. For example, if the user is stressed, the anonymization unit prioritizes methods that increase anonymity. If the user is relaxed, the anonymization unit prioritizes methods that decrease anonymity. If the user is in a hurry, the anonymization unit prioritizes methods that perform anonymization quickly. This makes it possible to determine the priority of anonymization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The anonymization unit improves the accuracy of anonymization by referring to external data related to the discussion topic during the anonymization process. For example, the anonymization unit improves the accuracy of anonymization by referring to external data related to the discussion topic. The anonymization unit uses external data to anonymize information related to the discussion topic. The anonymization unit utilizes external data related to the discussion topic to perform optimal anonymization. This improves the accuracy of anonymization by referring to external data related to the discussion topic.

[0108] The questioning unit estimates the user's emotions and adjusts the content of the questions based on the estimated emotions. For example, if the user is nervous, the questioning unit will ask questions that help them relax. If the user is relaxed, the questioning unit will ask questions that encourage active discussion. If the user is in a hurry, the questioning unit will ask questions that can be answered quickly. This makes it possible to adjust the content of questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0109] The questioning team analyzes the progress of the discussion in real time and asks questions at the optimal time. For example, if the discussion is stalled, the questioning team will ask questions at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the questioning team will ask questions to keep it calm. If the discussion is progressing smoothly, the questioning team will ask questions to move to the next step. This makes it possible to ask questions at the optimal time according to the progress of the discussion.

[0110] The questioning unit estimates the user's emotions and prioritizes questions based on those emotions. For example, if the user is stressed, the questioning unit prioritizes simple questions. If the user is relaxed, the questioning unit prioritizes detailed questions. If the user is in a hurry, the questioning unit prioritizes questions that can be answered quickly. This makes it possible to prioritize questions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The questioning team enriches the content of their questions by referring to external resources related to the discussion topic. For example, the questioning team enriches the content of their questions by referring to external resources related to the discussion topic. The questioning team uses external resources to reflect information related to the discussion topic in their questions. The questioning team utilizes external resources related to the discussion topic to ask the most appropriate questions. As a result, the content of the questions is enriched by referring to external resources related to the discussion topic.

[0112] The opinion unification unit estimates the user's emotions and adjusts the opinion unification method based on the estimated emotions. For example, if the user is tense, the opinion unification unit adjusts the method to help them relax. If the user is relaxed, the opinion unification unit adopts an opinion unification method that encourages active discussion. If the user is in a hurry, the opinion unification unit adopts a method that enables rapid opinion unification. This makes it possible to adjust the opinion unification method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0113] The consensus-building department analyzes the progress of the discussion in real time and brings consensus at the optimal time. For example, if the discussion is stalled, the consensus-building department will bring consensus at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the consensus-building department will bring consensus to ensure it proceeds calmly. If the discussion is progressing smoothly, the consensus-building department will bring consensus to move to the next step. This makes it possible to bring consensus at the optimal time according to the progress of the discussion.

[0114] The opinion unification unit estimates the user's emotions and determines the priority of opinion unification based on the estimated emotions. For example, if the user is stressed, the opinion unification unit prioritizes simple opinion unification. If the user is relaxed, the opinion unification unit prioritizes detailed opinion unification. If the user is in a hurry, the opinion unification unit prioritizes methods for quick opinion unification. This makes it possible to determine the priority of opinion unification according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The opinion unification department, when unifying opinions, enriches the content of the unification process by referring to external resources related to the discussion topic. For example, the opinion unification department enriches the content of the unification process by referring to external resources related to the discussion topic. The opinion unification department uses external resources to reflect information related to the discussion topic in the unification process. The opinion unification department utilizes external resources related to the discussion topic to achieve optimal unification. As a result, the content of the unification process is enriched by referring to external resources related to the discussion topic.

[0116] The opinion summarization unit estimates the user's emotions and adjusts the opinion summarization method based on the estimated emotions. For example, if the user is tense, the opinion summarization unit adjusts the method to help them relax. If the user is relaxed, the opinion summarization unit adopts a method that encourages active discussion. If the user is in a hurry, the opinion summarization unit adopts a method that summarizes opinions quickly. This makes it possible to adjust the opinion summarization method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The opinion summarization team analyzes the progress of the discussion in real time and summarizes opinions at the optimal time. For example, if the discussion is stalled, the opinion summarization team summarizes opinions at the appropriate time to revitalize the discussion. If the discussion is becoming heated, the opinion summarization team summarizes opinions to keep it calm. If the discussion is progressing smoothly, the opinion summarization team summarizes opinions to move on to the next step. This makes it possible to summarize opinions at the optimal time according to the progress of the discussion.

[0118] The opinion summarization unit estimates the user's emotions and determines the priority of opinion summarization based on the estimated emotions. For example, if the user is stressed, the opinion summarization unit prioritizes simple opinions. If the user is relaxed, the opinion summarization unit prioritizes detailed opinions. If the user is in a hurry, the opinion summarization unit prioritizes methods for quick opinion summarization. This makes it possible to prioritize opinion summarization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The opinion summarization team enriches the content of the opinion summary by referring to external resources related to the discussion topic when summarizing opinions. For example, the opinion summarization team enriches the content of the opinion summary by referring to external resources related to the discussion topic. The opinion summarization team uses external resources to reflect information related to the discussion topic in the opinion summary. The opinion summarization team utilizes external resources related to the discussion topic to create the optimal opinion summary. As a result, the content of the opinion summary is enriched by referring to external resources related to the discussion topic.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The discussion control unit can dynamically change the roles of participants according to the progress of the discussion. For example, if the discussion is stalled, it can change the role to allow a specific participant to take on a leadership role. If the discussion is heated, a calm participant can be assigned the role of mediator. Furthermore, if the discussion is progressing smoothly, a specific participant can be given the role of providing a new perspective. This allows for flexible role changes according to the progress of the discussion.

[0122] The anonymization function can adjust the level of anonymization according to the topic of discussion. For example, for sensitive topics, personal information can be completely hidden to enhance anonymity. On the other hand, for general topics, anonymity can be reduced and some participant attribute information can be displayed. Furthermore, the level of anonymization can be dynamically changed according to the progress of the discussion. This enables flexible anonymization tailored to the topic and progress of the discussion.

[0123] The questioning section can change the format of questions according to the progress of the discussion. For example, if the discussion is stalled, open-ended questions can be used to elicit free opinions from participants. If the discussion is heated, closed-ended questions can be used to organize the discussion. Furthermore, if the discussion is progressing smoothly, follow-up questions can be used to deepen the discussion. This allows for flexible changes in the questioning format according to the progress of the discussion.

[0124] The consensus-building department can change its consensus-building methods according to the progress of the discussion. For example, if the discussion is stalled, brainstorming can be conducted to generate new ideas. If the discussion is heated, a debate format can be adopted to clarify conflicting opinions. Furthermore, if the discussion is progressing smoothly, consensus-building can be conducted to facilitate agreement. This allows for flexible changes in consensus-building methods according to the progress of the discussion.

[0125] The opinion summarization section can change the format of the opinion summary according to the progress of the discussion. For example, if the discussion is stalled, opinions can be summarized in a summary format to indicate the direction of the discussion. Also, if the discussion is heated, opinions can be organized in a bulleted list format to keep the discussion calm. Furthermore, if the discussion is progressing smoothly, opinions can be summarized in a storytelling format to deepen the discussion. This allows for flexible changes in the opinion summarization format according to the progress of the discussion.

[0126] The goal-setting unit can estimate the user's emotions and adjust the discussion goals based on those emotions. For example, if the user is stressed, the goals can be adjusted to be easily achievable. Conversely, if the user is relaxed, the goals can be set higher to encourage a more challenging discussion. Furthermore, if the user is in a hurry, goals that can be achieved in a short time can be set. This enables goal setting that is tailored to the user's emotions.

[0127] The discussion control unit can estimate the user's emotions and adjust the discussion process based on those emotions. For example, if the user is tense, the process can be adjusted to help them relax. If the user is relaxed, a process that encourages active discussion can be adopted. Furthermore, if the user is in a hurry, a process that speeds up the discussion can be adopted. This makes it possible to adjust the discussion process according to the user's emotions.

[0128] The data analysis department can estimate the user's emotions and adjust the perspective of the data analysis based on those emotions. For example, if the user is relaxed, a detailed data analysis can be performed. If the user is in a hurry, a concise data analysis can be performed. Furthermore, if the user is excited, a visually stimulating data analysis can be performed. This allows for adjustment of the data analysis perspective according to the user's emotions.

[0129] The progress support unit can estimate the user's emotions and adjust its progress support methods based on those estimates. For example, if the user is nervous, it can adjust its progress support methods to help them relax. If the user is relaxed, it can adopt methods that encourage active discussion. Furthermore, if the user is in a hurry, it can adopt methods that expedite the discussion. This makes it possible to adjust progress support methods according to the user's emotions.

[0130] The anonymization unit can estimate the user's emotions and adjust the anonymization method based on those emotions. For example, if the user is nervous, a method that increases anonymity can be adopted. Conversely, if the user is relaxed, a method that decreases anonymity can be adopted. Furthermore, if the user is in a hurry, a method that performs rapid anonymization can be adopted. This makes it possible to adjust the anonymization method according to the user's emotions.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The goal-setting unit sets the objectives of the discussion. These objectives include the results to be achieved and the scope of the discussion. The goal-setting unit sets specific objectives based on the discussion topic. Step 2: The discussion control unit controls the discussion based on the goals set by the goal setting unit. The discussion control unit can also manage the order of speaking and time allocation, and can support the progress of the discussion using generative AI. Step 3: The Data Analysis Department analyzes the data as instructed by the Discussion Control Department. The Data Analysis Department analyzes the data based on the analytical tools used and the purpose of the analysis, and may also perform data analysis using generative AI. Step 4: The progress support unit supports the progress of the discussion through the discussion control unit. The progress support unit supports the discussion based on progress checklists and support timing, and can also support the progress of the discussion using generative AI.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0135] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] Each of the multiple elements described above, including the goal-setting unit, discussion control unit, data analysis unit, and progress support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the goal-setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the goals of the discussion. The discussion control unit is implemented by the control unit 46A of the smart device 14 and controls the progress of the discussion. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data. The progress support unit is implemented by the control unit 46A of the smart device 14 and supports the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0140] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0141] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0143] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0144] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0145] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0146] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0147] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] Each of the multiple elements described above, including the goal-setting unit, discussion control unit, data analysis unit, and progress support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the goal-setting unit is implemented by the specific processing unit 290 of the data processing device 12 and sets the goals of the discussion. The discussion control unit is implemented, for example, by the control unit 46A of the smart glasses 214 and controls the progress of the discussion. The data analysis unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the data. The progress support unit is implemented, for example, by the control unit 46A of the smart glasses 214 and supports the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0156] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0157] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0159] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0160] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0161] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0162] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0163] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0168] Each of the multiple elements described above, including the goal-setting unit, discussion control unit, data analysis unit, and progress support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the goal-setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the goals of the discussion. The discussion control unit is implemented by the control unit 46A of the headset terminal 314 and controls the progress of the discussion. The data analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the data. The progress support unit is implemented by the control unit 46A of the headset terminal 314 and supports the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0173] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0175] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0176] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0177] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0178] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0179] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0180] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0181] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0183] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0185] Each of the multiple elements described above, including the goal setting unit, discussion control unit, data analysis unit, and progress support unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the goal setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the goal of the discussion. The discussion control unit is implemented by, for example, the control unit 46A of the robot 414 and controls the progress of the discussion. The data analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the data. The progress support unit is implemented by, for example, the control unit 46A of the robot 414 and supports the progress of the discussion. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0186] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0188] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0189] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0190] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0193] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0194] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0195] 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.

[0196] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0197] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0198] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0199] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0201] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0202] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0203] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0204] (Note 1) The goal-setting section sets the objectives of the discussion, A discussion control unit controls the discussion based on the goals set by the aforementioned goal setting unit, A data analysis unit that analyzes the data instructed by the discussion control unit, The discussion control unit provides a progress support unit that supports the progress of the discussion. A system characterized by the following features. (Note 2) It includes an anonymization unit to ensure the anonymity of participants. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a questioning section that asks questions to delve deeper into opinions and provide new perspectives. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a unification department to develop and unify potentially conflicting opinions. The system described in Appendix 1, characterized by the features described herein. (Note 5) Towards the end of the discussion, there is a section to summarize opinions by directing the conversation to experts. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned target setting unit, It estimates user sentiment and adjusts the discussion goals based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned target setting unit, Analyze the results of past discussions and set optimal goals. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned target setting unit, Customize the objectives based on the expertise and experience of the discussion participants. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned target setting unit, It estimates user emotions and determines goal priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned target setting unit, When setting goals, consider the latest research and trends related to the topic of discussion. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned target setting unit, When setting goals, dynamically update the goals according to the progress of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned discussion control unit, It estimates the user's emotions and adjusts the discussion process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned discussion control unit, Analyze the progress of the discussion in real time and intervene at the optimal time. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned discussion control unit, Analyze the speaking history of participants in the discussion and control their contributions to maintain a balance. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned discussion control unit, It estimates the user's emotions and adjusts the pace of the discussion based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned discussion control unit, When conducting the discussion, we will take into account the geographical and cultural backgrounds of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned discussion control unit, During the discussion, adjust the depth of the discussion according to the level of expertise of the participants. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned data analysis unit, We estimate user emotions and adjust the perspective of data analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned data analysis unit, Based on the content of the discussion, relevant data will be collected and analyzed in real time. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned data analysis unit, Refer to past data analysis results to select the most suitable analytical method for the current discussion. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned data analysis unit, We estimate user sentiment and prioritize data analysis based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned data analysis unit, When analyzing data, refer to external data sources related to the topic of discussion. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned data analysis unit, During data analysis, dynamically change the focus of the analysis according to the progress of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned progress support unit is: The system estimates the user's emotions and adjusts the support methods based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned progress support unit is: We monitor the progress of the discussion in real time and provide support as needed. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned progress support unit is: We will select the most suitable support method for the discussion by referring to data from past discussions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned progress support unit is: The system estimates the user's emotions and prioritizes progress support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned progress support unit is: When providing support for the discussion, we will provide external resources related to the topic of discussion. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned progress support unit is: During discussion support, the support provided will dynamically change according to the progress of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 30) The anonymization unit is, The system estimates the user's emotions and adjusts the anonymization method based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The anonymization unit is, Analyze the attribute information of the discussion participants and select the optimal anonymization method. The system described in Appendix 2, characterized by the features described herein. (Note 32) The anonymization unit is, The system estimates the user's emotions and determines the priority of anonymization based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The anonymization unit is, During anonymization, external data related to the discussion topic is referenced to improve the accuracy of anonymization. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned question section is, The system estimates the user's emotions and adjusts the content of the questions based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned question section is, Analyze the progress of the discussion in real time and ask questions at the optimal time. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned question section is, The system estimates the user's emotions and prioritizes questions based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned question section is, When asking questions, enrich the content of your questions by referring to external resources related to the topic of discussion. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned opinion unification department, We estimate the user's emotions and adjust the method of consensus building based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned opinion unification department, Analyze the progress of the discussion in real time and reach a consensus at the optimal time. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned opinion unification department, It estimates user sentiment and determines priorities for consensus-building based on the estimated user sentiment. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned opinion unification department, When reaching a consensus, enrich the content of the consensus by referring to external resources related to the discussion topic. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned opinion compilation department, We estimate the user's emotions and adjust the method of summarizing opinions based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned opinion compilation department, We analyze the progress of the discussion in real time and summarize opinions at the optimal time. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned opinion compilation department, The system estimates user sentiment and determines the priority of opinion summaries based on the estimated user sentiment. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned opinion compilation department, When summarizing opinions, enrich the content of the summary by referring to external resources related to the discussion topic. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0205] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The goal-setting section sets the objectives of the discussion, A discussion control unit controls the discussion based on the goals set by the aforementioned goal setting unit, A data analysis unit that analyzes the data instructed by the discussion control unit, The discussion control unit provides a progress support unit that supports the progress of the discussion. A system characterized by the following features.

2. It includes an anonymization unit to ensure the anonymity of participants. The system according to feature 1.

3. It includes a questioning section that asks questions to delve deeper into opinions and provide new perspectives. The system according to feature 1.

4. It is equipped with a unification department to develop and unify potentially conflicting opinions. The system according to feature 1.

5. Towards the end of the discussion, there is a section to summarize opinions by directing the conversation to experts. The system according to feature 1.

6. The aforementioned target setting unit, It estimates user sentiment and adjusts the discussion goals based on the estimated user sentiment. The system according to feature 1.

7. The aforementioned target setting unit, Analyze the results of past discussions and set optimal goals. The system according to feature 1.

8. The aforementioned target setting unit, Customize the objectives based on the expertise and experience of the discussion participants. The system according to feature 1.

9. The aforementioned target setting unit, It estimates user emotions and determines goal priorities based on those estimated emotions. The system according to feature 1.

Images