system

Abstract

The system according to this embodiment aims to make decisions efficiently while reflecting the opinions of all members of the group. [Solution] The system according to the embodiment comprises a collection unit, a creation unit, a discussion unit, and a decision unit. The collection unit collects the opinions of each member. The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. The discussion unit has the avatar AI agents created by the creation unit engage in discussions with each other. The decision unit makes a final decision based on the results obtained by the discussion 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

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 efficiently collect and reflect the opinions of all members of a group and then make a decision.

[0005] The system according to the embodiment aims to efficiently make a decision after reflecting the opinions of all members of a group.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a creation unit, a discussion unit, and a decision unit. The collection unit collects the opinions of each member. The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. The discussion unit has the avatar AI agents created by the creation unit engage in discussions with each other. The decision unit makes a final decision based on the results obtained by the discussion unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently make decisions while reflecting the opinions of all group members. [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 including 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  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 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) The decision-making support system according to an embodiment of the present invention is a system in which avatar AI agents, each reflecting the thoughts of a group member, make decisions on behalf of the members. This decision-making support system collects the opinions of each member and creates avatar AI agents that reflect the collected opinions. These avatar AI agents participate in meetings as avatars of each member, think autonomously, listen to others, and present their own opinions. Next, the avatar AI agents discuss among themselves and find a compromise that satisfies all of them. Through this process, opinion adjustments and consensus building are carried out smoothly, resulting in efficient and harmonious decision-making. For example, the decision-making support system can be applied not only in business settings but also in homes and local communities. For example, it can be used in various scenarios such as decision-making within the family or planning events in local communities. In this way, by using avatar AI agents, efficient and harmonious decision-making is achieved, and a process is established in which the user's intentions are accurately reflected. Furthermore, an environment that is easy for everyone to participate in is created, improving satisfaction. This platform can be used to realize a new style of decision-making. This enables decision support systems to achieve efficient and harmonious decision-making.

[0029] The decision support system according to this embodiment comprises a collection unit, a creation unit, a discussion unit, and a decision unit. The collection unit collects the opinions of each member. The collection unit can collect, for example, oral opinions, written opinions, electronic opinions, etc. The collection unit collects the opinions of members using, for example, questionnaires. The collection unit can also collect opinions using online forms. Furthermore, the collection unit can also collect opinions through interviews. For example, the collection unit collects the opinions of members using questionnaires and stores the results in a database. When using online forms, the collection unit collects the opinions entered by members in real time and stores them in a database. When collecting opinions through interviews, the collection unit has an interviewer listen to the opinions of members and records the content. The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. The creation unit sets the appearance and behavior of the avatar AI agent based on the collected opinions, for example. The creation unit sets the conversational capabilities of the avatar AI agent based on the collected opinions, for example. The creation unit can also set the personality of the avatar AI agent based on the collected opinions. For example, the creation unit can set the appearance of the avatar AI agent based on the collected opinions, reflecting the characteristics of the members. The creation unit can set the behavior of the avatar AI agent based on the collected opinions, reproducing the behavior of the members. The creation unit can set the conversational ability of the avatar AI agent based on the collected opinions, reproducing the way the members speak. The discussion unit allows the avatar AI agents created by the creation unit to engage in discussions with each other. For example, the discussion unit allows the avatar AI agents to exchange opinions and reach a consensus. For example, the discussion unit allows the avatar AI agents to adjust their opinions and find the optimal solution. The discussion unit can also allow the avatar AI agents to clash opinions and deepen the discussion. For example, the discussion unit records the process of the avatar AI agents exchanging opinions and reaching a consensus. The discussion unit records the process of the avatar AI agents adjusting their opinions and finding the optimal solution. The discussion unit records the process of the avatar AI agents clashing opinions and deepening the discussion.The decision-making unit makes a final decision based on the results obtained by the discussion unit. For example, the decision-making unit makes a final decision by voting based on the results of the discussion. For example, the decision-making unit makes a final decision by reaching a consensus based on the results of the discussion. Alternatively, the decision-making unit can make a final decision using an algorithm based on the results of the discussion. For example, the decision-making unit records the process of voting and making a final decision based on the results of the discussion. The decision-making unit records the process of reaching a consensus and making a final decision based on the results of the discussion. The decision-making unit records the process of making a final decision using an algorithm based on the results of the discussion. As a result, the decision support system according to the embodiment can achieve efficient and harmonious decision-making.

[0030] The collection department collects opinions from each member. This can include oral, written, and electronic opinions. Specifically, the collection department uses questionnaires to gather member opinions. Questionnaires may be distributed on paper, or online via email or a dedicated questionnaire form. Questionnaire questions may ask about specific matters related to decision-making, and can be in various formats, such as multiple-choice or open-ended. The collection department compiles the questionnaire responses and stores them in a database. When using online forms, the collection department collects member input in real time and stores it in the database. Online forms are provided through websites or dedicated applications, allowing members to submit their opinions anytime, anywhere. The collection department automatically compiles the online form data and stores it in the database. When collecting opinions through interviews, the collection department has interviewers listen to members' opinions and record the content. Interviews may be conducted in person, or via telephone or video call. The interviewer conducts the interview based on a pre-prepared list of questions and meticulously records the members' opinions. The data collection department stores the interview records in a database for later analysis. This allows the data collection department to collect members' opinions in various ways and manage them centrally in the database. The data collection department organizes the collected opinions and conducts analysis in collaboration with other departments as needed. For example, the data collection department categorizes the collected opinions to understand trends and commonalities. The data collection department can also visualize the collected opinions, creating graphs and charts to visually show the distribution and trends of opinions. This allows the data collection department to efficiently and effectively collect members' opinions and utilize them in the decision-making process.

[0031] The creation team creates an avatar AI agent that reflects the opinions collected by the collection team. For example, the creation team sets the appearance and behavior of the avatar AI agent based on the collected opinions. Specifically, the creation team analyzes the collected opinions and understands the characteristics and opinion tendencies of each member. Based on this, they set the appearance of the avatar AI agent. The appearance settings include face shape, hairstyle, clothing, etc., reflecting the characteristics of the members. The creation team sets the behavior of the avatar AI agent based on the collected opinions. The behavior settings include gestures, facial expressions, speaking style, etc., reproducing the actions of the members. The creation team sets the conversational ability of the avatar AI agent based on the collected opinions. Setting conversational ability uses natural language processing technology to reproduce the speaking style and word choice of the members. The creation team can also set the personality of the avatar AI agent based on the collected opinions. Setting the personality reflects the opinion tendencies and values ​​of the members, so that the avatar AI agent can represent the opinions of the members. For example, the creation team sets the appearance of the avatar AI agent based on the collected opinions, reflecting the characteristics of the members. The creation team sets the behavior of the avatar AI agent based on the collected opinions and reproduces the behavior of the members. The creation team also sets the conversational capabilities of the avatar AI agent based on the collected opinions and reproduces the way the members speak. This allows the creation team to create an avatar AI agent that reflects the collected opinions and use it in discussions in the discussion team. Furthermore, the creation team uses the collected opinions as feedback to continuously improve the behavior and conversational capabilities of the avatar AI agent. For example, based on the discussion results in the discussion team and feedback from members, they adjust the behavior and conversational capabilities of the avatar AI agent to enable more natural and effective discussions. This allows the creation team to improve the quality of the avatar AI agent and enhance the quality of discussions in the decision-making process.

[0032] The discussion unit facilitates discussions between avatar AI agents created by the creation unit. For example, the discussion unit allows avatar AI agents to exchange opinions and reach a consensus. Specifically, the discussion unit sets up a virtual meeting room for the avatar AI agents to exchange opinions. In this virtual meeting room, the avatar AI agents engage in real-time dialogue and exchange opinions. The discussion unit monitors the process by which the avatar AI agents reconcile their opinions and find the optimal solution. The avatar AI agents use natural language processing technology to advance the discussion based on the collected opinions. The discussion unit can also allow avatar AI agents to clash opinions and deepen the discussion. For example, the discussion unit records the process by which avatar AI agents exchange opinions and reach a consensus. The discussion unit records the process by which avatar AI agents reconcile their opinions and find the optimal solution. The discussion unit records the process by which avatar AI agents clash opinions and deepen the discussion. This allows the discussion unit to enable avatar AI agents to discuss efficiently and effectively and find the optimal solution. Furthermore, the discussion team stores the insights and agreements gained during the discussion process in a database and utilizes them in subsequent decision-making processes. For example, the discussion team analyzes the records of the discussions to evaluate the progress of the discussions and the consensus-building process. The discussion team can also visualize the results of the discussions, creating graphs and charts to visually represent the content and results of the discussions. This allows the discussion team to conduct discussions efficiently and effectively and utilize them in the decision-making process.

[0033] The decision-making unit makes the final decision based on the results obtained by the discussion unit. For example, the decision-making unit makes the final decision by voting based on the results of the discussion. Specifically, the decision-making unit compiles the results of the discussion in the discussion unit and conducts a vote that reflects the opinions of each member. The vote is conducted through an online form or a dedicated voting system, and members vote for their opinions. The decision-making unit compiles the voting results and makes the final decision. For example, the decision-making unit makes the final decision by reaching a consensus based on the results of the discussion. Consensus is reached through the adjustment and compromise of opinions among members until a final agreement is reached. The decision-making unit records the consensus-building process for future reference. The decision-making unit can also make the final decision using an algorithm based on the results of the discussion. The algorithm derives the optimal decision based on the discussion results and the opinions of the members. The decision-making unit checks the results of the algorithm and makes the final decision. For example, the decision-making unit records the process of voting based on the results of the discussion and making the final decision. The decision-making unit records the process of reaching a consensus based on the results of the discussion and making the final decision. The decision-making unit records the process of making final decisions using algorithms based on the results of discussions. This allows the decision-making unit to make efficient and transparent decisions and improve the reliability of the decision-making process. Furthermore, the decision-making unit notifies members of the decision results and provides instructions for implementation. For example, the decision-making unit documents the content of the final decision and distributes it to members. The decision-making unit also develops specific procedures and schedules for implementing the decision results and provides instructions to members. This allows the decision-making unit to make and implement decisions efficiently and effectively.

[0034] The discussion unit includes a recording unit that records the process of discussions between avatar AI agents. The discussion unit can, for example, record the audio of the discussion between avatar AI agents. The discussion unit can, for example, record the text of the discussion between avatar AI agents. The discussion unit can also record the video of the discussion between avatar AI agents. For example, the discussion unit can record the audio of the discussion between avatar AI agents so that it can be played back later. The discussion unit can record the text of the discussion between avatar AI agents so that it can be referenced later. The discussion unit can record the video of the discussion between avatar AI agents so that it can be viewed later. This improves the transparency of decision-making by recording the discussion process.

[0035] The collection unit analyzes members' past opinion submission history and selects the optimal collection method. For example, the collection unit analyzes the frequency of opinions previously submitted by members to determine the optimal collection timing. For example, the collection unit analyzes the content of opinions previously submitted by members and prioritizes collecting relevant topics. The collection unit can also select the optimal collection method (email, chat, etc.) based on members' past opinion submission history. For example, by analyzing the frequency of opinions previously submitted by members and determining the optimal collection timing, the collection unit achieves efficient opinion collection. By analyzing the content of opinions previously submitted by members and prioritizing the collection of relevant topics, the collection unit collects high-quality opinions. The collection unit reduces the burden on members by selecting the optimal collection method based on their past opinion submission history. This allows for the selection of the optimal collection method by analyzing past opinion submission history. Some or all of the above processes in the collection unit may be performed using AI, or not. For example, the collection unit can input members' past opinion submission history data into a generating AI and have the generating AI select the optimal collection method.

[0036] The collection unit filters opinions based on the members' current projects and areas of interest. For example, the collection unit prioritizes collecting opinions related to projects the members are currently working on. The collection unit filters and collects relevant opinions based on the members' areas of interest. The collection unit can also collect the most relevant opinions based on the members' current work. For example, the collection unit achieves efficient opinion collection by prioritizing the collection of opinions related to projects the members are currently working on. The collection unit collects high-quality opinions by filtering and collecting relevant opinions based on the members' areas of interest. The collection unit reduces the burden on members by collecting the most relevant opinions based on their current work. This allows for the collection of highly relevant opinions by filtering them based on current projects and areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input members' project data and area of ​​interest data into a generating AI and have the generating AI perform the opinion filtering.

[0037] The collection unit prioritizes collecting highly relevant opinions by considering the geographical location of the members when gathering opinions. For example, if a member is in a specific region, the collection unit prioritizes collecting opinions related to that region. For example, if a member is on a business trip, the collection unit prioritizes collecting opinions related to the business trip destination. The collection unit can also prioritize collecting opinions related to remote work if a member is working remotely. For example, if a member is in a specific region, the collection unit achieves efficient opinion collection by prioritizing the collection of opinions related to that region. If a member is on a business trip, the collection unit collects high-quality opinions by prioritizing the collection of opinions related to the business trip destination. If a member is working remotely, the collection unit reduces the burden on members by prioritizing the collection of opinions related to remote work. This allows for the priority collection of highly relevant opinions by considering geographical location. Some or all of the above processing in the collection unit may be performed using AI, for example, or without the use of AI. For example, the data collection unit can input members' geographical location data into a generating AI and have the generating AI perform opinion filtering.

[0038] The collection unit analyzes members' social media activity and collects relevant opinions when gathering opinions. For example, the collection unit analyzes what members post on social media and collects relevant opinions. For example, the collection unit collects relevant opinions based on the topics members follow on social media. The collection unit can also analyze members' social media activity history and collect the most relevant opinions. For example, the collection unit achieves efficient opinion collection by analyzing what members post on social media and collecting relevant opinions. The collection unit collects high-quality opinions by collecting relevant opinions based on the topics members follow on social media. The collection unit reduces the burden on members by analyzing their social media activity history and collecting the most relevant opinions. This allows for the collection of relevant opinions by analyzing social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input members' social media data into a generating AI and have the generating AI perform opinion filtering.

[0039] The creation unit adjusts the level of detail of avatars based on the importance of the opinions when creating avatar AI agents. For example, the creation unit will give detailed representations to avatar AI agents of members with important opinions. For example, the creation unit will give simplified representations to avatar AI agents of members with less important opinions. The creation unit can also adjust the representation of avatar AI agents in stages according to the importance of the opinions. For example, the creation unit will reflect the importance of the opinions by giving detailed representations to avatar AI agents of members with important opinions. The creation unit will reflect the importance of the opinions by giving simplified representations to avatar AI agents of members with less important opinions. The creation unit will reflect the importance of the opinions by adjusting the representation of avatar AI agents in stages according to the importance of the opinions. In this way, by adjusting the level of detail of avatars based on the importance of the opinions, avatars of members with important opinions can be represented in detail. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion importance data into the generating AI and have the generating AI adjust the level of detail of the avatar.

[0040] The creation unit applies different creation algorithms depending on the category of opinion when creating avatar AI agents. For example, the creation unit applies an algorithm with technical expression to avatar AI agents of members with technical opinions. For example, the creation unit applies an algorithm with creative expression to avatar AI agents of members with creative opinions. The creation unit can also apply an algorithm with business expression to avatar AI agents of members with business opinions. For example, the creation unit reflects the category of opinion by applying an algorithm with technical expression to avatar AI agents of members with technical opinions. The creation unit reflects the category of opinion by applying an algorithm with creative expression to avatar AI agents of members with creative opinions. The creation unit reflects the category of opinion by applying an algorithm with business expression to avatar AI agents of members with business opinions. In this way, by applying different creation algorithms depending on the category of opinion, it is possible to create avatars suitable for each category. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion category data into the generation AI and have the generation AI execute the avatar creation algorithm.

[0041] The creation unit determines the priority of avatars based on the submission timing of members when creating avatar AI agents. For example, the creation unit will prioritize creating avatar AI agents for members who submitted their opinions early. For example, the creation unit will prioritize creating avatar AI agents for members whose opinions are close to the submission deadline. The creation unit can also adjust the creation order of avatar AI agents according to the submission timing. For example, the creation unit reflects the submission timing of opinions by prioritizing the creation of avatar AI agents for members who submitted their opinions early. The creation unit reflects the submission timing of opinions by prioritizing the creation of avatar AI agents according to the submission timing. This makes it possible to create avatars that are appropriate for the submission timing by determining the priority of avatars based on the submission timing. Some or all of the above processing in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input data on the timing of opinion submissions into the generation AI, and have the generation AI determine the priority of avatars.

[0042] The creation unit adjusts the order of avatars based on the relevance of the members when creating avatar AI agents. For example, the creation unit prioritizes creating avatar AI agents for members with highly relevant opinions. For example, the creation unit postpones creating avatar AI agents for members with less relevant opinions. The creation unit can also adjust the creation order of avatar AI agents according to the relevance of the opinions. For example, the creation unit reflects the relevance of opinions by prioritizing the creation of avatar AI agents for members with highly relevant opinions. The creation unit reflects the relevance of opinions by postponing the creation of avatar AI agents for members with less relevant opinions. The creation unit reflects the relevance of opinions by adjusting the creation order of avatar AI agents according to the relevance of the opinions. In this way, by adjusting the order of avatars based on relevance, highly relevant opinions can be reflected preferentially. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion relevance data into the generating AI and have the generating AI adjust the order of the avatars.

[0043] The discussion unit improves the accuracy of discussions by considering the interrelationships of opinions. For example, the discussion unit analyzes the interrelationships of opinions and combines related opinions to conduct discussions. For example, the discussion unit adjusts the progress of the discussion by considering the interrelationships of opinions. The discussion unit can also narrow the focus of the discussion based on the interrelationships of opinions. For example, the discussion unit improves the accuracy of discussions by analyzing the interrelationships of opinions and combining related opinions to conduct discussions. The discussion unit achieves efficient discussions by adjusting the progress of the discussion by considering the interrelationships of opinions. The discussion unit conducts high-quality discussions by narrowing the focus of the discussion based on the interrelationships of opinions. As a result, the accuracy of discussions is improved by considering the interrelationships of opinions. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without AI. For example, the discussion unit can input interrelationship data of opinions into a generating AI and have the generating AI adjust the progress of the discussion.

[0044] The discussion unit conducts discussions while considering the attribute information of the members. The discussion unit adjusts the progress of the discussion, for example, by considering the members' expertise. The discussion unit adjusts the progress of the discussion, for example, by considering the members' positions. The discussion unit can also adjust the progress of the discussion, for example, by considering the members' experience. For example, by adjusting the progress of the discussion, the discussion unit can achieve efficient discussions by considering the members' expertise. By adjusting the progress of the discussion, the discussion unit can conduct high-quality discussions by considering the members' positions. By adjusting the progress of the discussion, the discussion unit can reduce the burden on members by considering the members' experience. This makes it possible to have more appropriate discussions by considering the attribute information of the members. Some or all of the above processing in the discussion unit may be performed using AI, for example, or not using AI. For example, the discussion unit can input member attribute information data into a generating AI and have the generating AI perform the adjustment of the discussion progress.

[0045] The discussion unit conducts discussions while considering the geographical distribution of opinions. For example, the discussion unit analyzes the geographical distribution of opinions and conducts discussions while considering opinions from each region. For example, the discussion unit conducts discussions while coordinating the opinions of geographically distant members. The discussion unit can also adjust the progress of the discussion while considering differences in opinions from each region. For example, the discussion unit achieves efficient discussions by analyzing the geographical distribution of opinions and conducting discussions while considering opinions from each region. The discussion unit conducts high-quality discussions by coordinating the opinions of geographically distant members. The discussion unit reduces the burden on members by adjusting the progress of the discussion while considering differences in opinions from each region. As a result, by considering the geographical distribution of opinions, it becomes possible to conduct discussions that reflect opinions from each region. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without using AI. For example, the discussion unit can input geographical distribution data of opinions into a generating AI and have the generating AI perform adjustments to the progress of the discussion.

[0046] The discussion unit improves the accuracy of its arguments by referring to relevant literature on the opinions during the discussion. For example, the discussion unit strengthens the basis of its arguments by referring to relevant literature on the opinions. For example, the discussion unit adjusts the progress of the discussion based on relevant literature. The discussion unit can also narrow the focus of the discussion by referring to relevant literature. For example, the discussion unit improves the accuracy of its arguments by strengthening the basis of its arguments by referring to relevant literature on the opinions. The discussion unit achieves efficient discussion by adjusting the progress of the discussion based on relevant literature. The discussion unit conducts high-quality discussions by narrowing the focus of the discussion by referring to relevant literature. In this way, the basis of the argument can be strengthened and its accuracy improved by referring to relevant literature. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without using AI. For example, the discussion unit can input relevant literature data on the opinions into a generating AI and have the generating AI adjust the progress of the discussion.

[0047] The decision-making unit optimizes the current decision by referring to past decision-making data when making a decision. For example, the decision-making unit analyzes past decision-making data and reflects it in the current decision. For example, the decision-making unit optimizes the current decision based on past successful decision-making examples. The decision-making unit can also improve the current decision based on past failures. For example, the decision-making unit achieves efficient decision-making by analyzing past decision-making data and reflecting it in the current decision. The decision-making unit makes high-quality decisions by optimizing the current decision based on past successful decision-making examples. The decision-making unit reduces the burden on members by improving the current decision based on past failures. This allows the current decision to be optimized by referring to past decision-making data. Some or all of the above processes in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input past decision-making data into a generating AI and have the generating AI perform the optimization of the current decision.

[0048] The decision-making unit applies different decision-making methods to each category of opinion when making a decision. For example, the decision-making unit applies a technical decision-making method to technical opinions. For example, the decision-making unit applies a creative decision-making method to creative opinions. The decision-making unit can also apply a business decision-making method to business opinions. For example, the decision-making unit reflects the category of opinion by applying a technical decision-making method to technical opinions. For example, the decision-making unit reflects the category of opinion by applying a creative decision-making method to creative opinions. For example, the decision-making unit reflects the category of opinion by applying a business decision-making method to business opinions. This makes it possible to make decisions appropriate to each category by applying different decision-making methods to each category of opinion. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input opinion category data into a generating AI and have the generating AI execute the application of the decision-making method.

[0049] The decision-making unit analyzes changes in decision-making based on the timing of opinion submissions. For example, the decision-making unit analyzes changes in decision-making based on the timing of opinion submissions. For example, the decision-making unit makes decisions by prioritizing opinions submitted earlier. Alternatively, the decision-making unit can also postpone decisions based on opinions submitted later. For example, by analyzing changes in decision-making based on the timing of opinion submissions, the decision-making unit can achieve efficient decision-making. By prioritizing opinions submitted earlier, the decision-making unit can make high-quality decisions. By postponing decisions based on opinions submitted later, the decision-making unit can reduce the burden on members. This makes it possible to make more appropriate decisions by analyzing changes in decision-making based on the timing of opinion submissions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input opinion submission timing data into a generating AI and have the generating AI perform the analysis of changes in decision-making.

[0050] The decision-making unit analyzes the decision by referring to relevant market data for the opinion during the decision-making process. For example, the decision-making unit strengthens the rationale for the decision by referring to relevant market data for the opinion. For example, the decision-making unit adjusts the progress of the decision-making process based on market data. The decision-making unit can also narrow the focus of the decision by referring to market data. For example, the decision-making unit improves the accuracy of the decision by strengthening the rationale for the decision by referring to relevant market data for the opinion. The decision-making unit achieves efficient decision-making by adjusting the progress of the decision-making process based on market data. The decision-making unit makes high-quality decisions by narrowing the focus of the decision-making process by referring to market data. This allows the rationale for the decision to be strengthened and the accuracy to be improved by referring to relevant market data. Some or all of the above processes in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input relevant market data for the opinion into a generating AI and have the generating AI perform the analysis of the decision.

[0051] The recording unit optimizes its recording algorithm by referring to past discussion data during recording. For example, the recording unit analyzes past discussion data and reflects it in the current recording. For example, the recording unit optimizes the current recording algorithm based on successful past discussions. The recording unit can also improve the current recording algorithm based on unsuccessful past discussions. For example, the recording unit achieves efficient recording by analyzing past discussion data and reflecting it in the current recording. The recording unit produces high-quality recordings by optimizing the current recording algorithm based on successful past discussions. The recording unit reduces the burden on members by improving the current recording algorithm based on unsuccessful past discussions. This allows the recording algorithm to be optimized by referring to past discussion data. Some or all of the above processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input past discussion data into a generating AI and have the generating AI perform the optimization of the recording algorithm.

[0052] The recording unit weights the recorded data based on when the discussions were submitted. For example, the recording unit may weight discussion data submitted earlier, or lighter discussion data submitted later. The recording unit can also adjust the weighting of the discussion data according to the submission date. For example, by weighting discussion data submitted earlier, the recording unit reflects the importance of the discussion. By lighter discussion data submitted later, the recording unit reflects the importance of the discussion. By adjusting the weighting of the discussion data according to the submission date, the recording unit reflects the importance of the discussion. This allows for more appropriate recording by weighting the recorded data based on when the discussions were submitted. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the discussion submission date data into a generating AI and have the generating AI perform the weighting of the recorded data.

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

[0054] The data collection unit can analyze members' past statements and assess the consistency of their opinions when gathering them. For example, the unit can compare a member's past opinions with their current opinions and evaluate their consistency. If past and current opinions match, the unit can prioritize collecting those opinions. Furthermore, if past and current opinions contradict each other, the unit can point out the inconsistencies and encourage the member to reconsider. By evaluating the consistency of opinions, the unit can collect more reliable opinions.

[0055] The discussion unit includes a recording unit that records the process of discussions between avatar AI agents. The recording unit can, for example, not only record the audio of the discussion but also summarize its content and extract key points. The recording unit automatically generates a summary of the discussion for later reference. Furthermore, the recording unit can record a video of the discussion, allowing for visual confirmation of its progress. This detailed recording of the discussion process improves the transparency of decision-making and makes it easier to review the discussion content later.

[0056] The collection team analyzes members' past opinion submission history and selects the optimal collection method. For example, the collection team analyzes the content of opinions previously submitted by members and prioritizes collecting related topics. The collection team can also select the most suitable collection method (email, chat, etc.) based on members' past opinion submission history. Furthermore, the collection team can adjust the timing of opinion collection based on members' past opinion submission history. This allows for the selection of the optimal collection method by analyzing past opinion submission history.

[0057] The collection department filters opinions based on members' current projects and areas of interest. For example, it prioritizes collecting opinions related to projects members are currently working on. It can also filter and collect relevant opinions based on members' areas of interest. Furthermore, it can collect the most relevant opinions based on members' current work responsibilities. This allows for the collection of highly relevant opinions by filtering them based on current projects and areas of interest.

[0058] The collection department prioritizes collecting highly relevant opinions by considering the geographical location of the members during the opinion gathering process. For example, if a member is in a specific region, opinions related to that region will be prioritized. Similarly, if a member is on a business trip, opinions related to their destination will be prioritized. Furthermore, if a member is working remotely, opinions related to remote work will be prioritized. This allows for the collection of highly relevant opinions by considering geographical location.

[0059] The collection department analyzes members' social media activity when gathering opinions and collects relevant opinions. For example, the collection department analyzes what members have posted on social media and collects relevant opinions. The collection department can also collect relevant opinions based on the topics members follow on social media. Furthermore, the collection department can analyze members' social media activity history and collect the most relevant opinions. This allows for the collection of relevant opinions by analyzing social media activity.

[0060] The creation department adjusts the level of detail of avatars based on the importance of the opinions expressed when creating avatar AI agents. For example, avatar AI agents of members with important opinions will have a detailed representation. Conversely, avatar AI agents of members with less important opinions may have a simplified representation. Furthermore, the representation of avatar AI agents can be adjusted in stages according to the importance of the opinions. This allows for detailed representation of avatars of members with important opinions by adjusting the level of detail based on the importance of the opinions.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The collection department gathers opinions from each member. The collection department can collect opinions verbally, in writing, or electronically. For example, opinions can be collected using questionnaires, online forms, or interviews, and the results can be stored in a database. Step 2: The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. Based on the collected opinions, the creation unit sets the appearance, behavior, conversational abilities, and personality of the avatar AI agent. Step 3: The discussion section is where the avatar AI agents created by the creation section engage in discussions with each other. The discussion section records the process in which the avatar AI agents exchange opinions, reach consensus, find the optimal solution, and deepen the discussion by creating conflicting opinions. Step 4: The decision-making unit makes a final decision based on the results obtained by the discussion unit. The decision-making unit makes a final decision based on the results of the discussion, using voting, consensus building, and algorithms, and records the process.

[0063] (Example of form 2) The decision-making support system according to an embodiment of the present invention is a system in which avatar AI agents, each reflecting the thoughts of a group member, make decisions on behalf of the members. This decision-making support system collects the opinions of each member and creates avatar AI agents that reflect the collected opinions. These avatar AI agents participate in meetings as avatars of each member, think autonomously, listen to others, and present their own opinions. Next, the avatar AI agents discuss among themselves and find a compromise that satisfies all of them. Through this process, opinion adjustments and consensus building are carried out smoothly, resulting in efficient and harmonious decision-making. For example, the decision-making support system can be applied not only in business settings but also in homes and local communities. For example, it can be used in various scenarios such as decision-making within the family or planning events in local communities. In this way, by using avatar AI agents, efficient and harmonious decision-making is achieved, and a process is established in which the user's intentions are accurately reflected. Furthermore, an environment that is easy for everyone to participate in is created, improving satisfaction. This platform can be used to realize a new style of decision-making. This enables decision support systems to achieve efficient and harmonious decision-making.

[0064] The decision support system according to this embodiment comprises a collection unit, a creation unit, a discussion unit, and a decision unit. The collection unit collects the opinions of each member. The collection unit can collect, for example, oral opinions, written opinions, electronic opinions, etc. The collection unit collects the opinions of members using, for example, questionnaires. The collection unit can also collect opinions using online forms. Furthermore, the collection unit can also collect opinions through interviews. For example, the collection unit collects the opinions of members using questionnaires and stores the results in a database. When using online forms, the collection unit collects the opinions entered by members in real time and stores them in a database. When collecting opinions through interviews, the collection unit has an interviewer listen to the opinions of members and records the content. The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. The creation unit sets the appearance and behavior of the avatar AI agent based on the collected opinions, for example. The creation unit sets the conversational capabilities of the avatar AI agent based on the collected opinions, for example. The creation unit can also set the personality of the avatar AI agent based on the collected opinions. For example, the creation unit can set the appearance of the avatar AI agent based on the collected opinions, reflecting the characteristics of the members. The creation unit can set the behavior of the avatar AI agent based on the collected opinions, reproducing the behavior of the members. The creation unit can set the conversational ability of the avatar AI agent based on the collected opinions, reproducing the way the members speak. The discussion unit allows the avatar AI agents created by the creation unit to engage in discussions with each other. For example, the discussion unit allows the avatar AI agents to exchange opinions and reach a consensus. For example, the discussion unit allows the avatar AI agents to adjust their opinions and find the optimal solution. The discussion unit can also allow the avatar AI agents to clash opinions and deepen the discussion. For example, the discussion unit records the process of the avatar AI agents exchanging opinions and reaching a consensus. The discussion unit records the process of the avatar AI agents adjusting their opinions and finding the optimal solution. The discussion unit records the process of the avatar AI agents clashing opinions and deepening the discussion.The decision-making unit makes a final decision based on the results obtained by the discussion unit. For example, the decision-making unit makes a final decision by voting based on the results of the discussion. For example, the decision-making unit makes a final decision by reaching a consensus based on the results of the discussion. Alternatively, the decision-making unit can make a final decision using an algorithm based on the results of the discussion. For example, the decision-making unit records the process of voting and making a final decision based on the results of the discussion. The decision-making unit records the process of reaching a consensus and making a final decision based on the results of the discussion. The decision-making unit records the process of making a final decision using an algorithm based on the results of the discussion. As a result, the decision support system according to the embodiment can achieve efficient and harmonious decision-making.

[0065] The collection department collects opinions from each member. This can include oral, written, and electronic opinions. Specifically, the collection department uses questionnaires to gather member opinions. Questionnaires may be distributed on paper, or online via email or a dedicated questionnaire form. Questionnaire questions may ask about specific matters related to decision-making, and can be in various formats, such as multiple-choice or open-ended. The collection department compiles the questionnaire responses and stores them in a database. When using online forms, the collection department collects member input in real time and stores it in the database. Online forms are provided through websites or dedicated applications, allowing members to submit their opinions anytime, anywhere. The collection department automatically compiles the online form data and stores it in the database. When collecting opinions through interviews, the collection department has interviewers listen to members' opinions and record the content. Interviews may be conducted in person, or via telephone or video call. The interviewer conducts the interview based on a pre-prepared list of questions and meticulously records the members' opinions. The data collection department stores the interview records in a database for later analysis. This allows the data collection department to collect members' opinions in various ways and manage them centrally in the database. The data collection department organizes the collected opinions and conducts analysis in collaboration with other departments as needed. For example, the data collection department categorizes the collected opinions to understand trends and commonalities. The data collection department can also visualize the collected opinions, creating graphs and charts to visually show the distribution and trends of opinions. This allows the data collection department to efficiently and effectively collect members' opinions and utilize them in the decision-making process.

[0066] The creation team creates an avatar AI agent that reflects the opinions collected by the collection team. For example, the creation team sets the appearance and behavior of the avatar AI agent based on the collected opinions. Specifically, the creation team analyzes the collected opinions and understands the characteristics and opinion tendencies of each member. Based on this, they set the appearance of the avatar AI agent. The appearance settings include face shape, hairstyle, clothing, etc., reflecting the characteristics of the members. The creation team sets the behavior of the avatar AI agent based on the collected opinions. The behavior settings include gestures, facial expressions, speaking style, etc., reproducing the actions of the members. The creation team sets the conversational ability of the avatar AI agent based on the collected opinions. Setting conversational ability uses natural language processing technology to reproduce the speaking style and word choice of the members. The creation team can also set the personality of the avatar AI agent based on the collected opinions. Setting the personality reflects the opinion tendencies and values ​​of the members, so that the avatar AI agent can represent the opinions of the members. For example, the creation team sets the appearance of the avatar AI agent based on the collected opinions, reflecting the characteristics of the members. The creation team sets the behavior of the avatar AI agent based on the collected opinions and reproduces the behavior of the members. The creation team also sets the conversational capabilities of the avatar AI agent based on the collected opinions and reproduces the way the members speak. This allows the creation team to create an avatar AI agent that reflects the collected opinions and use it in discussions in the discussion team. Furthermore, the creation team uses the collected opinions as feedback to continuously improve the behavior and conversational capabilities of the avatar AI agent. For example, based on the discussion results in the discussion team and feedback from members, they adjust the behavior and conversational capabilities of the avatar AI agent to enable more natural and effective discussions. This allows the creation team to improve the quality of the avatar AI agent and enhance the quality of discussions in the decision-making process.

[0067] The discussion unit facilitates discussions between avatar AI agents created by the creation unit. For example, the discussion unit allows avatar AI agents to exchange opinions and reach a consensus. Specifically, the discussion unit sets up a virtual meeting room for the avatar AI agents to exchange opinions. In this virtual meeting room, the avatar AI agents engage in real-time dialogue and exchange opinions. The discussion unit monitors the process by which the avatar AI agents reconcile their opinions and find the optimal solution. The avatar AI agents use natural language processing technology to advance the discussion based on the collected opinions. The discussion unit can also allow avatar AI agents to clash opinions and deepen the discussion. For example, the discussion unit records the process by which avatar AI agents exchange opinions and reach a consensus. The discussion unit records the process by which avatar AI agents reconcile their opinions and find the optimal solution. The discussion unit records the process by which avatar AI agents clash opinions and deepen the discussion. This allows the discussion unit to enable avatar AI agents to discuss efficiently and effectively and find the optimal solution. Furthermore, the discussion team stores the insights and agreements gained during the discussion process in a database and utilizes them in subsequent decision-making processes. For example, the discussion team analyzes the records of the discussions to evaluate the progress of the discussions and the consensus-building process. The discussion team can also visualize the results of the discussions, creating graphs and charts to visually represent the content and results of the discussions. This allows the discussion team to conduct discussions efficiently and effectively and utilize them in the decision-making process.

[0068] The decision-making unit makes the final decision based on the results obtained by the discussion unit. For example, the decision-making unit makes the final decision by voting based on the results of the discussion. Specifically, the decision-making unit compiles the results of the discussion in the discussion unit and conducts a vote that reflects the opinions of each member. The vote is conducted through an online form or a dedicated voting system, and members vote for their opinions. The decision-making unit compiles the voting results and makes the final decision. For example, the decision-making unit makes the final decision by reaching a consensus based on the results of the discussion. Consensus is reached through the adjustment and compromise of opinions among members until a final agreement is reached. The decision-making unit records the consensus-building process for future reference. The decision-making unit can also make the final decision using an algorithm based on the results of the discussion. The algorithm derives the optimal decision based on the discussion results and the opinions of the members. The decision-making unit checks the results of the algorithm and makes the final decision. For example, the decision-making unit records the process of voting based on the results of the discussion and making the final decision. The decision-making unit records the process of reaching a consensus based on the results of the discussion and making the final decision. The decision-making unit records the process of making final decisions using algorithms based on the results of discussions. This allows the decision-making unit to make efficient and transparent decisions and improve the reliability of the decision-making process. Furthermore, the decision-making unit notifies members of the decision results and provides instructions for implementation. For example, the decision-making unit documents the content of the final decision and distributes it to members. The decision-making unit also develops specific procedures and schedules for implementing the decision results and provides instructions to members. This allows the decision-making unit to make and implement decisions efficiently and effectively.

[0069] The discussion unit includes a recording unit that records the process of discussions between avatar AI agents. The discussion unit can, for example, record the audio of the discussion between avatar AI agents. The discussion unit can, for example, record the text of the discussion between avatar AI agents. The discussion unit can also record the video of the discussion between avatar AI agents. For example, the discussion unit can record the audio of the discussion between avatar AI agents so that it can be played back later. The discussion unit can record the text of the discussion between avatar AI agents so that it can be referenced later. The discussion unit can record the video of the discussion between avatar AI agents so that it can be viewed later. This improves the transparency of decision-making by recording the discussion process.

[0070] The collection unit estimates the emotions of the members and adjusts the timing of opinion collection based on the estimated emotions. For example, if a member is feeling stressed, the collection unit will temporarily delay opinion collection. For example, if a member is relaxed, the collection unit will collect opinions quickly. The collection unit can also collect opinions at the optimal time if a member is focused. For example, if a member is feeling stressed, the collection unit will reduce the burden on the member by temporarily delaying opinion collection. If a member is relaxed, the collection unit will collect opinions quickly, achieving efficient opinion collection. If a member is focused, the collection unit will collect opinions at the optimal time, resulting in the collection of high-quality opinions. This allows for more appropriate opinion collection by adjusting the timing of opinion collection according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the members' facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0071] The collection unit analyzes members' past opinion submission history and selects the optimal collection method. For example, the collection unit analyzes the frequency of opinions previously submitted by members to determine the optimal collection timing. For example, the collection unit analyzes the content of opinions previously submitted by members and prioritizes collecting relevant topics. The collection unit can also select the optimal collection method (email, chat, etc.) based on members' past opinion submission history. For example, by analyzing the frequency of opinions previously submitted by members and determining the optimal collection timing, the collection unit achieves efficient opinion collection. By analyzing the content of opinions previously submitted by members and prioritizing the collection of relevant topics, the collection unit collects high-quality opinions. The collection unit reduces the burden on members by selecting the optimal collection method based on their past opinion submission history. This allows for the selection of the optimal collection method by analyzing past opinion submission history. Some or all of the above processes in the collection unit may be performed using AI, or not. For example, the collection unit can input members' past opinion submission history data into a generating AI and have the generating AI select the optimal collection method.

[0072] The collection unit filters opinions based on the members' current projects and areas of interest. For example, the collection unit prioritizes collecting opinions related to projects the members are currently working on. The collection unit filters and collects relevant opinions based on the members' areas of interest. The collection unit can also collect the most relevant opinions based on the members' current work. For example, the collection unit achieves efficient opinion collection by prioritizing the collection of opinions related to projects the members are currently working on. The collection unit collects high-quality opinions by filtering and collecting relevant opinions based on the members' areas of interest. The collection unit reduces the burden on members by collecting the most relevant opinions based on their current work. This allows for the collection of highly relevant opinions by filtering them based on current projects and areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input members' project data and area of ​​interest data into a generating AI and have the generating AI perform the opinion filtering.

[0073] The collection unit estimates the emotions of the members and determines the priority of opinions to collect based on the estimated emotions. For example, if a member is excited, the collection unit will prioritize collecting their opinion. For example, if a member is calm, the collection unit will postpone collecting their opinion. The collection unit can also quickly collect opinions if a member is feeling anxious. For example, if a member is excited, the collection unit can quickly collect important opinions by prioritizing their opinion. If a member is calm, the collection unit can improve the efficiency of opinion collection by postponing their opinion. If a member is feeling anxious, the collection unit can reduce the burden on the member by quickly collecting their opinion. This allows for the priority collection of important opinions by determining the priority of opinions according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the members' facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0074] The collection unit prioritizes collecting highly relevant opinions by considering the geographical location of the members when gathering opinions. For example, if a member is in a specific region, the collection unit prioritizes collecting opinions related to that region. For example, if a member is on a business trip, the collection unit prioritizes collecting opinions related to the business trip destination. The collection unit can also prioritize collecting opinions related to remote work if a member is working remotely. For example, if a member is in a specific region, the collection unit achieves efficient opinion collection by prioritizing the collection of opinions related to that region. If a member is on a business trip, the collection unit collects high-quality opinions by prioritizing the collection of opinions related to the business trip destination. If a member is working remotely, the collection unit reduces the burden on members by prioritizing the collection of opinions related to remote work. This allows for the priority collection of highly relevant opinions by considering geographical location. Some or all of the above processing in the collection unit may be performed using AI, for example, or without the use of AI. For example, the data collection unit can input members' geographical location data into a generating AI and have the generating AI perform opinion filtering.

[0075] The collection unit analyzes members' social media activity and collects relevant opinions when gathering opinions. For example, the collection unit analyzes what members post on social media and collects relevant opinions. For example, the collection unit collects relevant opinions based on the topics members follow on social media. The collection unit can also analyze members' social media activity history and collect the most relevant opinions. For example, the collection unit achieves efficient opinion collection by analyzing what members post on social media and collecting relevant opinions. The collection unit collects high-quality opinions by collecting relevant opinions based on the topics members follow on social media. The collection unit reduces the burden on members by analyzing their social media activity history and collecting the most relevant opinions. This allows for the collection of relevant opinions by analyzing social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input members' social media data into a generating AI and have the generating AI perform opinion filtering.

[0076] The creation unit estimates the emotions of the members and adjusts the expression of the avatar AI agent based on the estimated emotions. For example, if a member is relaxed, the creation unit softens the expression of the avatar AI agent. For example, if a member is tense, the creation unit calms the expression of the avatar AI agent. The creation unit can also make the expression of the avatar AI agent more lively if a member is excited. For example, if a member is relaxed, the creation unit achieves a natural expression by softening the expression of the avatar AI agent. If a member is tense, the creation unit reflects the member's emotions by calming the expression of the avatar AI agent. If a member is excited, the creation unit reflects the member's emotions by making the expression of the avatar AI agent more lively. In this way, by adjusting the expression of the avatar AI agent according to the emotions of the members, a more natural expression becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the above-described processes in the creation unit may be performed using AI, or not using AI. For example, the creation unit can input the members' facial expression data into the generating AI and have the generating AI perform emotion estimation.

[0077] The creation unit adjusts the level of detail of avatars based on the importance of the opinions when creating avatar AI agents. For example, the creation unit will give detailed representations to avatar AI agents of members with important opinions. For example, the creation unit will give simplified representations to avatar AI agents of members with less important opinions. The creation unit can also adjust the representation of avatar AI agents in stages according to the importance of the opinions. For example, the creation unit will reflect the importance of the opinions by giving detailed representations to avatar AI agents of members with important opinions. The creation unit will reflect the importance of the opinions by giving simplified representations to avatar AI agents of members with less important opinions. The creation unit will reflect the importance of the opinions by adjusting the representation of avatar AI agents in stages according to the importance of the opinions. In this way, by adjusting the level of detail of avatars based on the importance of the opinions, avatars of members with important opinions can be represented in detail. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion importance data into the generating AI and have the generating AI adjust the level of detail of the avatar.

[0078] The creation unit applies different creation algorithms depending on the category of opinion when creating avatar AI agents. For example, the creation unit applies an algorithm with technical expression to avatar AI agents of members with technical opinions. For example, the creation unit applies an algorithm with creative expression to avatar AI agents of members with creative opinions. The creation unit can also apply an algorithm with business expression to avatar AI agents of members with business opinions. For example, the creation unit reflects the category of opinion by applying an algorithm with technical expression to avatar AI agents of members with technical opinions. The creation unit reflects the category of opinion by applying an algorithm with creative expression to avatar AI agents of members with creative opinions. The creation unit reflects the category of opinion by applying an algorithm with business expression to avatar AI agents of members with business opinions. In this way, by applying different creation algorithms depending on the category of opinion, it is possible to create avatars suitable for each category. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion category data into the generation AI and have the generation AI execute the avatar creation algorithm.

[0079] The creation unit estimates the emotions of the members and adjusts the appearance of the avatar AI agent based on the estimated emotions. For example, if a member is relaxed, the creation unit softens the appearance of the avatar AI agent. For example, if a member is tense, the creation unit calms the appearance of the avatar AI agent. The creation unit can also make the appearance of the avatar AI agent more lively if a member is excited. For example, if a member is relaxed, the creation unit achieves a natural appearance by softening the appearance of the avatar AI agent. If a member is tense, the creation unit reflects the member's emotions by calming the appearance of the avatar AI agent. If a member is excited, the creation unit reflects the member's emotions by making the appearance of the avatar AI agent more lively. This allows for a more natural appearance by adjusting the appearance of the avatar AI agent according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the above-described processes in the creation unit may be performed using AI, or not using AI. For example, the creation unit can input the members' facial expression data into the generating AI and have the generating AI perform emotion estimation.

[0080] The creation unit determines the priority of avatars based on the submission timing of members when creating avatar AI agents. For example, the creation unit will prioritize creating avatar AI agents for members who submitted their opinions early. For example, the creation unit will prioritize creating avatar AI agents for members whose opinions are close to the submission deadline. The creation unit can also adjust the creation order of avatar AI agents according to the submission timing. For example, the creation unit reflects the submission timing of opinions by prioritizing the creation of avatar AI agents for members who submitted their opinions early. The creation unit reflects the submission timing of opinions by prioritizing the creation of avatar AI agents according to the submission timing. This makes it possible to create avatars that are appropriate for the submission timing by determining the priority of avatars based on the submission timing. Some or all of the above processing in the creation unit may be performed using AI, for example, or not using AI. For example, the creation unit can input data on the timing of opinion submissions into the generation AI, and have the generation AI determine the priority of avatars.

[0081] The creation unit adjusts the order of avatars based on the relevance of the members when creating avatar AI agents. For example, the creation unit prioritizes creating avatar AI agents for members with highly relevant opinions. For example, the creation unit postpones creating avatar AI agents for members with less relevant opinions. The creation unit can also adjust the creation order of avatar AI agents according to the relevance of the opinions. For example, the creation unit reflects the relevance of opinions by prioritizing the creation of avatar AI agents for members with highly relevant opinions. The creation unit reflects the relevance of opinions by postponing the creation of avatar AI agents for members with less relevant opinions. The creation unit reflects the relevance of opinions by adjusting the creation order of avatar AI agents according to the relevance of the opinions. In this way, by adjusting the order of avatars based on relevance, highly relevant opinions can be reflected preferentially. Some or all of the above processing in the creation unit may be performed using AI, for example, or without using AI. For example, the creation unit can input opinion relevance data into the generating AI and have the generating AI adjust the order of the avatars.

[0082] The discussion unit estimates the emotions of its members and adjusts the discussion criteria based on the estimated emotions. For example, if members are relaxed, the discussion unit will loosen the discussion criteria. If members are tense, the discussion unit will tighten the discussion criteria. The discussion unit can also be flexible if members are excited. For example, if members are relaxed, the discussion unit will loosen the discussion criteria to facilitate a natural discussion. If members are tense, the discussion unit will tighten the discussion criteria to reflect their emotions. If members are excited, the discussion unit will be flexible in its discussion criteria to reflect their emotions. This allows for more appropriate discussions by adjusting the discussion criteria according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the discussion section may be performed using AI, for example, or without AI. For example, the discussion section can input members' facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0083] The discussion unit improves the accuracy of discussions by considering the interrelationships of opinions. For example, the discussion unit analyzes the interrelationships of opinions and combines related opinions to conduct discussions. For example, the discussion unit adjusts the progress of the discussion by considering the interrelationships of opinions. The discussion unit can also narrow the focus of the discussion based on the interrelationships of opinions. For example, the discussion unit improves the accuracy of discussions by analyzing the interrelationships of opinions and combining related opinions to conduct discussions. The discussion unit achieves efficient discussions by adjusting the progress of the discussion by considering the interrelationships of opinions. The discussion unit conducts high-quality discussions by narrowing the focus of the discussion based on the interrelationships of opinions. As a result, the accuracy of discussions is improved by considering the interrelationships of opinions. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without AI. For example, the discussion unit can input interrelationship data of opinions into a generating AI and have the generating AI adjust the progress of the discussion.

[0084] The discussion unit conducts discussions while considering the attribute information of the members. The discussion unit adjusts the progress of the discussion, for example, by considering the members' expertise. The discussion unit adjusts the progress of the discussion, for example, by considering the members' positions. The discussion unit can also adjust the progress of the discussion, for example, by considering the members' experience. For example, by adjusting the progress of the discussion, the discussion unit can achieve efficient discussions by considering the members' expertise. By adjusting the progress of the discussion, the discussion unit can conduct high-quality discussions by considering the members' positions. By adjusting the progress of the discussion, the discussion unit can reduce the burden on members by considering the members' experience. This makes it possible to have more appropriate discussions by considering the attribute information of the members. Some or all of the above processing in the discussion unit may be performed using AI, for example, or not using AI. For example, the discussion unit can input member attribute information data into a generating AI and have the generating AI perform the adjustment of the discussion progress.

[0085] The discussion unit estimates the emotions of the members and adjusts the order in which the discussion results are displayed based on the estimated emotions of the members. For example, if the members are relaxed, the discussion unit will display the discussion results in an orderly manner. If the members are tense, the discussion unit will display the discussion results in a summarized manner. The discussion unit can also display the discussion results in detail if the members are excited. For example, if the members are relaxed, the discussion unit achieves a natural display by displaying the discussion results in an orderly manner. If the members are tense, the discussion unit reflects the members' emotions by displaying the discussion results in a summarized manner. If the members are excited, the discussion unit reflects the members' emotions by displaying the discussion results in detail. This allows for a more appropriate display of discussion results by adjusting the order in which the discussion results are displayed according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the discussion section may be performed using AI, for example, or without AI. For example, the discussion section can input members' facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0086] The discussion unit conducts discussions while considering the geographical distribution of opinions. For example, the discussion unit analyzes the geographical distribution of opinions and conducts discussions while considering opinions from each region. For example, the discussion unit conducts discussions while coordinating the opinions of geographically distant members. The discussion unit can also adjust the progress of the discussion while considering differences in opinions from each region. For example, the discussion unit achieves efficient discussions by analyzing the geographical distribution of opinions and conducting discussions while considering opinions from each region. The discussion unit conducts high-quality discussions by coordinating the opinions of geographically distant members. The discussion unit reduces the burden on members by adjusting the progress of the discussion while considering differences in opinions from each region. As a result, by considering the geographical distribution of opinions, it becomes possible to conduct discussions that reflect opinions from each region. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without using AI. For example, the discussion unit can input geographical distribution data of opinions into a generating AI and have the generating AI perform adjustments to the progress of the discussion.

[0087] The discussion unit improves the accuracy of its arguments by referring to relevant literature on the opinions during the discussion. For example, the discussion unit strengthens the basis of its arguments by referring to relevant literature on the opinions. For example, the discussion unit adjusts the progress of the discussion based on relevant literature. The discussion unit can also narrow the focus of the discussion by referring to relevant literature. For example, the discussion unit improves the accuracy of its arguments by strengthening the basis of its arguments by referring to relevant literature on the opinions. The discussion unit achieves efficient discussion by adjusting the progress of the discussion based on relevant literature. The discussion unit conducts high-quality discussions by narrowing the focus of the discussion by referring to relevant literature. In this way, the basis of the argument can be strengthened and its accuracy improved by referring to relevant literature. Some or all of the above processing in the discussion unit may be performed using AI, for example, or without using AI. For example, the discussion unit can input relevant literature data on the opinions into a generating AI and have the generating AI adjust the progress of the discussion.

[0088] The decision-making unit estimates the emotions of the members and adjusts the final decision-making method based on the estimated emotions of the members. For example, if a member is relaxed, the decision-making unit will make the decision-making method more flexible. For example, if a member is tense, the decision-making unit will make the decision-making method more rigid. The decision-making unit can also speed up the decision-making method if a member is excited. For example, if a member is relaxed, the decision-making unit will achieve natural decision-making by making the decision-making method flexible. If a member is tense, the decision-making unit will reflect the emotions of the members by making the decision-making method more rigid. If a member is excited, the decision-making unit will reflect the emotions of the members by speeding up the decision-making method. This allows for more appropriate decision-making by adjusting the decision-making method according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input the members' facial expression data into a generating AI, allowing the generating AI to perform emotion estimation.

[0089] The decision-making unit optimizes the current decision by referring to past decision-making data when making a decision. For example, the decision-making unit analyzes past decision-making data and reflects it in the current decision. For example, the decision-making unit optimizes the current decision based on past successful decision-making examples. The decision-making unit can also improve the current decision based on past failures. For example, the decision-making unit achieves efficient decision-making by analyzing past decision-making data and reflecting it in the current decision. The decision-making unit makes high-quality decisions by optimizing the current decision based on past successful decision-making examples. The decision-making unit reduces the burden on members by improving the current decision based on past failures. This allows the current decision to be optimized by referring to past decision-making data. Some or all of the above processes in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input past decision-making data into a generating AI and have the generating AI perform the optimization of the current decision.

[0090] The decision-making unit applies different decision-making methods to each category of opinion when making a decision. For example, the decision-making unit applies a technical decision-making method to technical opinions. For example, the decision-making unit applies a creative decision-making method to creative opinions. The decision-making unit can also apply a business decision-making method to business opinions. For example, the decision-making unit reflects the category of opinion by applying a technical decision-making method to technical opinions. For example, the decision-making unit reflects the category of opinion by applying a creative decision-making method to creative opinions. For example, the decision-making unit reflects the category of opinion by applying a business decision-making method to business opinions. This makes it possible to make decisions appropriate to each category by applying different decision-making methods to each category of opinion. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without using AI. For example, the decision-making unit can input opinion category data into a generating AI and have the generating AI execute the application of the decision-making method.

[0091] The decision-making unit estimates the emotions of the members and adjusts the importance of the decision based on the estimated emotions. For example, if a member is relaxed, the decision-making unit sets the importance of the decision low. For example, if a member is tense, the decision-making unit sets the importance of the decision high. The decision-making unit can also set the importance of the decision to a medium level if a member is excited. For example, if a member is relaxed, the decision-making unit achieves natural decision-making by setting the importance of the decision low. If a member is tense, the decision-making unit reflects the member's emotions by setting the importance of the decision high. If a member is excited, the decision-making unit reflects the member's emotions by setting the importance of the decision to a medium level. This allows for more appropriate decision-making by adjusting the importance of the decision according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input the members' facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0092] The decision-making unit analyzes changes in decision-making based on the timing of opinion submissions. For example, the decision-making unit analyzes changes in decision-making based on the timing of opinion submissions. For example, the decision-making unit makes decisions by prioritizing opinions submitted earlier. Alternatively, the decision-making unit can also postpone decisions based on opinions submitted later. For example, by analyzing changes in decision-making based on the timing of opinion submissions, the decision-making unit can achieve efficient decision-making. By prioritizing opinions submitted earlier, the decision-making unit can make high-quality decisions. By postponing decisions based on opinions submitted later, the decision-making unit can reduce the burden on members. This makes it possible to make more appropriate decisions by analyzing changes in decision-making based on the timing of opinion submissions. Some or all of the above processing in the decision-making unit may be performed using AI, for example, or without AI. For example, the decision-making unit can input opinion submission timing data into a generating AI and have the generating AI perform the analysis of changes in decision-making.

[0093] The decision-making unit analyzes the decision by referring to relevant market data for the opinion during the decision-making process. For example, the decision-making unit strengthens the rationale for the decision by referring to relevant market data for the opinion. For example, the decision-making unit adjusts the progress of the decision-making process based on market data. The decision-making unit can also narrow the focus of the decision by referring to market data. For example, the decision-making unit improves the accuracy of the decision by strengthening the rationale for the decision by referring to relevant market data for the opinion. The decision-making unit achieves efficient decision-making by adjusting the progress of the decision-making process based on market data. The decision-making unit makes high-quality decisions by narrowing the focus of the decision-making process by referring to market data. This allows the rationale for the decision to be strengthened and the accuracy to be improved by referring to relevant market data. Some or all of the above processes in the decision-making unit may be performed using AI, for example, or not using AI. For example, the decision-making unit can input relevant market data for the opinion into a generating AI and have the generating AI perform the analysis of the decision.

[0094] The recording unit estimates the emotions of the members and adjusts the recording method of the discussion based on the estimated emotions of the members. For example, if the members are relaxed, the recording unit will make detailed records. If the members are tense, the recording unit will make concise records. The recording unit can also make summary records if the members are excited. For example, if the recording unit is relaxed, it will achieve a natural recording by making detailed records. If the members are tense, the recording unit will reflect the emotions of the members by making concise records. If the members are excited, the recording unit will reflect the emotions of the members by making summary records. This allows for more appropriate recording by adjusting the recording method of the discussion according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the members' facial expression data into a generating AI, which can then perform emotion estimation.

[0095] The recording unit optimizes its recording algorithm by referring to past discussion data during recording. For example, the recording unit analyzes past discussion data and reflects it in the current recording. For example, the recording unit optimizes the current recording algorithm based on successful past discussions. The recording unit can also improve the current recording algorithm based on unsuccessful past discussions. For example, the recording unit achieves efficient recording by analyzing past discussion data and reflecting it in the current recording. The recording unit produces high-quality recordings by optimizing the current recording algorithm based on successful past discussions. The recording unit reduces the burden on members by improving the current recording algorithm based on unsuccessful past discussions. This allows the recording algorithm to be optimized by referring to past discussion data. Some or all of the above processes in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input past discussion data into a generating AI and have the generating AI perform the optimization of the recording algorithm.

[0096] The recording unit estimates the emotions of the members and adjusts the recording frequency based on the estimated emotions. For example, the recording unit increases the recording frequency when a member is relaxed. For example, the recording unit decreases the recording frequency when a member is tense. The recording unit can also set the recording frequency to a moderate level when a member is excited. For example, the recording unit achieves natural recording by increasing the recording frequency when a member is relaxed. The recording unit reflects the emotions of the members by decreasing the recording frequency when a member is tense. The recording unit reflects the emotions of the members by setting the recording frequency to a moderate level when a member is excited. This allows for more appropriate recording by adjusting the recording frequency according to the emotions of the members. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the members' facial expression data into a generating AI, which can then perform emotion estimation.

[0097] The recording unit weights the recorded data based on when the discussions were submitted. For example, the recording unit may weight discussion data submitted earlier, or lighter discussion data submitted later. The recording unit can also adjust the weighting of the discussion data according to the submission date. For example, by weighting discussion data submitted earlier, the recording unit reflects the importance of the discussion. By lighter discussion data submitted later, the recording unit reflects the importance of the discussion. By adjusting the weighting of the discussion data according to the submission date, the recording unit reflects the importance of the discussion. This allows for more appropriate recording by weighting the recorded data based on when the discussions were submitted. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input the discussion submission date data into a generating AI and have the generating AI perform the weighting of the recorded data.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The data collection unit can analyze members' past statements and assess the consistency of their opinions when gathering them. For example, the unit can compare a member's past opinions with their current opinions and evaluate their consistency. If past and current opinions match, the unit can prioritize collecting those opinions. Furthermore, if past and current opinions contradict each other, the unit can point out the inconsistencies and encourage the member to reconsider. By evaluating the consistency of opinions, the unit can collect more reliable opinions.

[0100] The discussion unit includes a recording unit that records the process of discussions between avatar AI agents. The recording unit can, for example, not only record the audio of the discussion but also summarize its content and extract key points. The recording unit automatically generates a summary of the discussion for later reference. Furthermore, the recording unit can record a video of the discussion, allowing for visual confirmation of its progress. This detailed recording of the discussion process improves the transparency of decision-making and makes it easier to review the discussion content later.

[0101] The data collection unit can estimate the emotions of the members and adjust the method of collecting opinions based on those estimates. For example, if a member is feeling stressed, the data collection unit can provide a relaxing environment for the member and collect opinions. If the member is relaxed, the data collection unit can actively solicit opinions from the member. Furthermore, if the member is focused, the data collection unit can ask specific questions to collect high-quality opinions. By adjusting the method of collecting opinions according to the emotions of the members, it becomes possible to collect more appropriate opinions.

[0102] The collection team analyzes members' past opinion submission history and selects the optimal collection method. For example, the collection team analyzes the content of opinions previously submitted by members and prioritizes collecting related topics. The collection team can also select the most suitable collection method (email, chat, etc.) based on members' past opinion submission history. Furthermore, the collection team can adjust the timing of opinion collection based on members' past opinion submission history. This allows for the selection of the optimal collection method by analyzing past opinion submission history.

[0103] The collection department filters opinions based on members' current projects and areas of interest. For example, it prioritizes collecting opinions related to projects members are currently working on. It can also filter and collect relevant opinions based on members' areas of interest. Furthermore, it can collect the most relevant opinions based on members' current work responsibilities. This allows for the collection of highly relevant opinions by filtering them based on current projects and areas of interest.

[0104] The collection unit estimates the emotions of the members and determines the priority of opinions to collect based on those estimates. For example, if a member is excited, their opinion will be collected first. Conversely, if a member is calm, their opinion can be postponed. Furthermore, if a member is feeling anxious, their opinion can be collected quickly. In this way, by prioritizing opinions according to the emotions of the members, important opinions can be collected first.

[0105] The collection department prioritizes collecting highly relevant opinions by considering the geographical location of the members during the opinion gathering process. For example, if a member is in a specific region, opinions related to that region will be prioritized. Similarly, if a member is on a business trip, opinions related to their destination will be prioritized. Furthermore, if a member is working remotely, opinions related to remote work will be prioritized. This allows for the collection of highly relevant opinions by considering geographical location.

[0106] The collection department analyzes members' social media activity when gathering opinions and collects relevant opinions. For example, the collection department analyzes what members have posted on social media and collects relevant opinions. The collection department can also collect relevant opinions based on the topics members follow on social media. Furthermore, the collection department can analyze members' social media activity history and collect the most relevant opinions. This allows for the collection of relevant opinions by analyzing social media activity.

[0107] The creation team estimates the emotions of the members and adjusts the avatar AI agent's expression based on the estimated emotions. For example, if a member is relaxed, the avatar AI agent's expression will be softened. If a member is tense, the avatar AI agent's expression can be made calmer. Furthermore, if a member is excited, the avatar AI agent's expression can be made more lively. By adjusting the avatar AI agent's expression according to the member's emotions, a more natural expression becomes possible.

[0108] The creation department adjusts the level of detail of avatars based on the importance of the opinions expressed when creating avatar AI agents. For example, avatar AI agents of members with important opinions will have a detailed representation. Conversely, avatar AI agents of members with less important opinions may have a simplified representation. Furthermore, the representation of avatar AI agents can be adjusted in stages according to the importance of the opinions. This allows for detailed representation of avatars of members with important opinions by adjusting the level of detail based on the importance of the opinions.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The collection department gathers opinions from each member. The collection department can collect opinions verbally, in writing, or electronically. For example, opinions can be collected using questionnaires, online forms, or interviews, and the results can be stored in a database. Step 2: The creation unit creates an avatar AI agent that reflects the opinions collected by the collection unit. Based on the collected opinions, the creation unit sets the appearance, behavior, conversational abilities, and personality of the avatar AI agent. Step 3: The discussion section is where the avatar AI agents created by the creation section engage in discussions with each other. The discussion section records the process in which the avatar AI agents exchange opinions, reach consensus, find the optimal solution, and deepen the discussion by creating conflicting opinions. Step 4: The decision-making unit makes a final decision based on the results obtained by the discussion unit. The decision-making unit makes a final decision based on the results of the discussion, using voting, consensus building, and algorithms, and records the process.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] Each of the multiple elements described above, including the collection unit, creation unit, discussion unit, and decision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects the opinions of the members. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates an avatar AI agent based on the collected opinions. The discussion unit is implemented by the control unit 46A of the smart device 14 and conducts discussions among the avatar AI agents. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes a final decision based on the results 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.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] Each of the multiple elements described above, including the collection unit, creation unit, discussion unit, and decision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects the opinions of the members. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates an avatar AI agent based on the collected opinions. The discussion unit is implemented by the control unit 46A of the smart glasses 214 and conducts discussions among the avatar AI agents. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes a final decision based on the results 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.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] Each of the multiple elements described above, including the collection unit, creation unit, discussion unit, and decision unit, is implemented in at least one of the following: the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects the opinions of the members. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates an avatar AI agent based on the collected opinions. The discussion unit is implemented by the control unit 46A of the headset terminal 314 and conducts discussions among the avatar AI agents. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes a final decision based on the results 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 modified in various ways.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] Each of the multiple elements described above, including the collection unit, creation unit, discussion unit, and decision unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects the opinions of the members. The creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates an avatar AI agent based on the collected opinions. The discussion unit is implemented by the control unit 46A of the robot 414 and conducts discussions among the avatar AI agents. The decision unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes a final decision based on the results 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 modified in various ways.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] (Note 1) A collection department that gathers opinions from each member, A creation unit creates an avatar AI agent that reflects the opinions collected by the aforementioned collection unit, A discussion unit where avatar AI agents created by the creation unit engage in discussions with each other, The system comprises a decision unit that makes a final decision based on the results obtained by the discussion unit. A system characterized by the following features. (Note 2) The aforementioned discussion section is, It includes a recording unit that records the process of discussions between avatar AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is We estimate the emotions of the members and adjust the timing of opinion collection based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is Analyze members' past feedback submission history to select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is When collecting opinions, filter them based on the members' current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is Estimate the emotions of the members and determine the priority of the opinions to collect based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is When collecting opinions, we prioritize collecting highly relevant opinions by considering the geographical location of the members. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When collecting opinions, analyze members' social media activity and gather relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned creation unit, It estimates the emotions of the members and adjusts the way the avatar AI agent is represented based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned creation unit, When creating an avatar AI agent, adjust the level of detail of the avatar based on the importance of the opinions expressed. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned creation unit, When creating an avatar AI agent, different creation algorithms are applied depending on the category of the opinion. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned creation unit, It estimates the emotions of the members and adjusts the appearance of the avatar AI agent based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned creation unit, When creating avatar AI agents, the priority of avatars is determined based on when members submit their submissions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned creation unit, When creating an avatar AI agent, adjust the order of avatars based on the relationships between members. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned discussion section is, Estimate the emotions of the members and adjust the discussion criteria based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned discussion section is, When discussing, consider the relationships between opinions to improve the accuracy of the discussion. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned discussion section is, When conducting discussions, take into account the attribute information of the members. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned discussion section is, The system estimates the emotions of the members and adjusts the order in which the discussion results are displayed based on the estimated emotions of the members. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned discussion section is, When conducting a discussion, consider the geographical distribution of opinions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned discussion section is, During discussions, referencing relevant literature can improve the accuracy of the argument. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned determination unit, We estimate the emotions of the team members and adjust the final decision-making process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned determination unit, When making decisions, refer to past decision data to optimize the current decision. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned determination unit, When making decisions, apply different decision-making methods to each category of opinion. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned determination unit, The system estimates the emotions of the team members and adjusts the importance of decision-making based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned determination unit, Analyze how decision-making changes based on when opinions are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned determination unit, When making decisions, we analyze those decisions by referring to relevant market data. The system described in Appendix 1, characterized by the features described herein. (Note 27) The recording unit is, We estimate the emotions of the members and adjust the way we record the discussion based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The recording unit is, During recording, the recording algorithm is optimized by referring to past discussion data. The system described in Appendix 2, characterized by the features described herein. (Note 29) The recording unit is, The system estimates the emotions of the members and adjusts the frequency of recording based on the estimated emotions of the members. The system described in Appendix 2, characterized by the features described herein. (Note 30) The recording unit is, During recording, the recorded data will be weighted based on when the discussion was submitted. The system described in Appendix 2, characterized by the features described herein. [Explanation of Symbols]

[0183] 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. A collection department that gathers opinions from each member, A creation unit creates an avatar AI agent that reflects the opinions collected by the aforementioned collection unit, A discussion unit where avatar AI agents created by the creation unit engage in discussions with each other, The system comprises a decision unit that makes a final decision based on the results obtained by the discussion unit. A system characterized by the following features.

2. The aforementioned discussion section is, It includes a recording unit that records the process of discussions between avatar AI agents. The system according to feature 1.

3. The aforementioned collection unit is We estimate the emotions of the members and adjust the timing of opinion collection based on the estimated emotions of the members. The system according to feature 1.

4. The aforementioned collection unit is Analyze members' past feedback submission history to select the most suitable collection method. The system according to feature 1.

5. The aforementioned collection unit is When collecting opinions, filter them based on the members' current projects and areas of interest. The system according to feature 1.

6. The aforementioned collection unit is Estimate the emotions of the members and determine the priority of the opinions to collect based on the estimated emotions of the members. The system according to feature 1.

7. The aforementioned collection unit is When collecting opinions, we prioritize collecting highly relevant opinions by considering the geographical location of the members. The system according to feature 1.

8. The aforementioned collection unit is When collecting opinions, analyze members' social media activity and gather relevant opinions. The system according to feature 1.

9. The aforementioned creation unit, It estimates the emotions of the members and adjusts the way the avatar AI agent is represented based on the estimated emotions of the members. The system according to feature 1.

Images