system

Abstract

The system according to this embodiment aims to propose solutions to specific problems faced by corporations based on specialized knowledge. [Solution] The system according to the embodiment comprises a database unit, a proposal unit, an answer unit, a customization unit, an update unit, and a learning unit. The database unit databases the knowledge of experts. The proposal unit proposes solutions to the problems of corporations based on the knowledge databased by the database unit. The answer unit answers the user's questions in real time based on the solutions proposed by the proposal unit. The customization unit customizes according to the needs of corporations. The update unit updates periodically. The learning unit allows the AI ​​to learn.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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] [[ID=�5]]In the conventional technology, there is a problem that it is difficult to quickly and accurately provide specialized knowledge for specific problems faced by corporations.

[0005] The system according to the embodiment aims to propose a solution based on specialized knowledge for specific problems faced by corporations.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a database unit, a proposal unit, an answer unit, a customization unit, an update unit, and a learning unit. The database unit databases the knowledge of experts. The proposal unit proposes solutions to the problems of corporations based on the knowledge databased by the database unit. The answer unit answers the user's questions in real time based on the solutions proposed by the proposal unit. The customization unit customizes the system according to the needs of the corporations. The update unit performs periodic updates. The learning unit allows the AI ​​to learn. [Effects of the Invention]

[0007] The system according to this embodiment can propose solutions to specific problems faced by corporations based on specialized knowledge. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The knowledge-sharing agent system according to an embodiment of the present invention is a system that learns from experts and provides that knowledge customized for corporations. This knowledge-sharing agent system proposes solutions to specific problems faced by corporations based on its specialized knowledge. For example, the knowledge-sharing agent system databases the knowledge of experts. The expert knowledge is stored in the database using machine learning and natural language processing. For example, by creating a database of the knowledge of experts in the medical field, it is possible to quickly propose solutions to problems faced by medical institutions. Next, the AI ​​in the knowledge-sharing agent system uses the database to propose solutions to specific problems faced by corporations. For example, if a manufacturing company wants to improve the efficiency of its production line, the AI ​​will propose an optimal production line design based on the expert's knowledge. The knowledge-sharing agent system also answers user questions in real time. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the AI ​​will answer in real time, based on the expert's knowledge, regarding market research methods and points to note. Furthermore, the knowledge-sharing agent system can be customized according to the needs of corporations and can support multiple industries. For example, customization for medical institutions or manufacturing companies is possible. Furthermore, the knowledge-sharing agent system maintains up-to-date knowledge through regular updates. This allows it to always propose solutions based on the latest information. The knowledge-sharing agent system enables corporations to make quick and accurate decisions. For example, by making quick decisions based on solutions proposed by AI, it is expected that costs will be reduced through improved operational efficiency and the speed of decision-making will increase. It is also expected to create opportunities for new businesses. For example, new businesses can be launched based on new business models proposed by AI. In this way, the knowledge-sharing agent system can provide quick and accurate solutions to corporations' problems.

[0029] The knowledge-sharing agent system according to this embodiment comprises a database unit, a proposal unit, an answer unit, a customization unit, an update unit, and a learning unit. The database unit databases the knowledge of experts. The database unit stores the knowledge of experts in the database, for example, using machine learning and natural language processing. For example, by databaseizing the knowledge of experts in the medical field, the database unit can quickly propose solutions to problems faced by medical institutions. The proposal unit proposes solutions to the problems of corporations based on the knowledge databased by the database unit. For example, if a manufacturing company wants to improve the efficiency of its production line, the proposal unit proposes an optimal production line design based on the knowledge of experts. Some or all of the above-described processes in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can propose solutions using an AI model that takes the problems of corporations as input and outputs solutions. The answer unit answers the user's questions in real time based on the solutions proposed by the proposal unit. The response unit, for example, when a company representative asks the AI, "We want to conduct market research on a new product," will provide real-time answers based on expert knowledge regarding market research methods and points to note. Some or all of the above-mentioned processes in the response unit may be performed using AI, or not. For example, the response unit can provide real-time answers using an AI model that takes the user's question as input and outputs an answer. The customization unit customizes according to the needs of the corporation. For example, the customization unit can customize for medical institutions or for the manufacturing industry. Some or all of the above-mentioned processes in the customization unit may be performed using AI, or not. For example, the customization unit can perform customization using an AI model that takes the corporation's needs as input and outputs a customized solution. The update unit periodically updates the database. For example, the update unit periodically adds expert knowledge to the database. Some or all of the above-mentioned processes in the update unit may be performed using AI, or not.For example, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. The learning unit allows the AI ​​to learn expert knowledge. The learning unit learns expert knowledge using a machine learning algorithm, for example. Some or all of the above-described processes in the learning unit may be performed using AI, or not using AI. For example, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results. As a result, the knowledge-sharing agent system according to this embodiment can provide rapid and accurate solutions to corporate problems.

[0030] The Database Division databases expert knowledge. For example, it stores expert knowledge in a database using machine learning and natural language processing. Specifically, it collects information such as documents, reports, papers, and interviews provided by experts, incorporates this information as text data, and analyzes it using natural language processing techniques. The analyzed data is organized by knowledge category and topic and stored in the database in a searchable format. For example, when databaseizing the knowledge of experts in the medical field, it allows for the rapid proposal of solutions to problems faced by healthcare institutions. Medical knowledge includes information on diagnostic methods, treatments, drug use, and patient care. This information is organized so that healthcare institutions can access it quickly when needed. By efficiently collecting, organizing, and storing expert knowledge, the Database Division promotes the sharing and utilization of knowledge. Furthermore, the Database Division performs data validation and cleansing to guarantee the quality of the collected data. This ensures the accuracy and reliability of the information stored in the database. In addition, the Database Division provides an interface for easy data updating and addition, enabling experts to continuously provide new knowledge. This ensures that the database always retains up-to-date information, allowing for quick and accurate solutions to corporate problems.

[0031] The Proposal Department proposes solutions to corporate problems based on knowledge compiled into a database by the Database Department. For example, if a manufacturing company wants to improve the efficiency of its production line, the Proposal Department will propose an optimal production line design based on expert knowledge. Specifically, the Proposal Department can propose solutions using an AI model that takes a corporate problem as input and outputs solutions. The AI ​​model utilizes the expert knowledge accumulated in the database to generate the optimal solution according to the characteristics and conditions of the problem. For example, if a manufacturing company wants to improve the efficiency of its production line, the AI ​​model will identify bottlenecks at each step of the production process and propose improvement measures. The Proposal Department also presents multiple solutions and compares their advantages and disadvantages to help the company make the best choice. By using AI, the Proposal Department can quickly analyze vast amounts of data and propose optimal solutions. Furthermore, the Proposal Department can collect feedback from companies and continuously improve the accuracy and effectiveness of its proposals. As a result, the Proposal Department can provide quick and accurate solutions to corporate problems, supporting business efficiency and problem solving.

[0032] The answering unit responds to user questions in real time based on solutions proposed by the suggestion unit. For example, if a company representative asks the AI, "We want to conduct market research for a new product," the answering unit will provide real-time answers on market research methods and points to note, based on expert knowledge. Specifically, the answering unit can respond in real time using an AI model that takes user questions as input and outputs answers. The AI ​​model utilizes expert knowledge accumulated in a database to generate the optimal answer to the user's question. For example, if a company wants to conduct market research for a new product, the AI ​​model will provide specific advice on market research methods, target market selection, data collection methods, and analysis methods. By using AI, the answering unit can quickly analyze vast amounts of data and provide accurate and rapid answers to user questions. Furthermore, the answering unit can collect user feedback and continuously improve the accuracy and effectiveness of its answers. As a result, the answering unit can provide quick and accurate answers to user questions, supporting business efficiency and problem solving.

[0033] The Customization Department customizes solutions according to the specific needs of each organization. For example, it can customize solutions for healthcare institutions or manufacturing companies. Specifically, the Customization Department uses an AI model that takes the organization's needs as input and outputs customized solutions. The AI ​​model generates optimal solutions based on the organization's specific needs and conditions. For example, customization for healthcare institutions provides diagnostic support systems and treatment planning support systems. Customization for manufacturing companies provides systems for optimizing production lines and supporting quality control. By using AI, the Customization Department can flexibly respond to the specific needs of each organization. Furthermore, the Customization Department can collect feedback from organizations and continuously improve the accuracy and effectiveness of its customizations. This allows the Customization Department to provide optimal solutions tailored to the organization's needs, supporting improved operational efficiency and problem-solving.

[0034] The update unit regularly updates the database. For example, the update unit regularly adds expert knowledge to the database. Specifically, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. The AI ​​model analyzes the new knowledge and integrates it into the existing database. This ensures that the database always holds the latest information and can provide quick and accurate solutions to corporate problems. By using AI, the update unit can quickly analyze vast amounts of data and efficiently update the database. Furthermore, the update unit can collect expert feedback and continuously improve the content and structure of the database. As a result, the update unit can always provide highly accurate solutions based on the latest information and support corporate problem-solving.

[0035] The learning unit allows AI to learn expert knowledge. For example, the learning unit learns expert knowledge using machine learning algorithms. Specifically, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results. The AI ​​model analyzes the expert knowledge and extracts patterns and trends. This allows the AI ​​to efficiently learn expert knowledge and accumulate knowledge useful for problem solving. By using AI, the learning unit can quickly analyze vast amounts of data and perform learning efficiently. Furthermore, the learning unit can collect feedback from experts and continuously improve the accuracy and effectiveness of its learning content. This enables the learning unit to always provide highly accurate solutions based on the latest knowledge, supporting problem solving for corporations.

[0036] The database creation unit can store expert knowledge in a database using machine learning and natural language processing. For example, the database creation unit can store expert knowledge in a database using machine learning algorithms. For example, the database creation unit can store expert knowledge in a database using supervised learning. The database creation unit can also store expert knowledge in a database using unsupervised learning. Furthermore, the database creation unit can store expert knowledge in a database using reinforcement learning. For example, the database creation unit can store expert knowledge in a database using natural language processing techniques. For example, the database creation unit can store expert knowledge in a database using morphological analysis. Furthermore, the database creation unit can store expert knowledge in a database using grammatical analysis. Furthermore, the database creation unit can store expert knowledge in a database using semantic analysis. This allows for the efficient database creation of expert knowledge. Some or all of the above-described processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can perform database creation using an AI model that takes expert knowledge as input and outputs a database.

[0037] The proposal department can propose solutions to specific problems faced by corporations based on its database of knowledge. For example, it can propose solutions to technical problems faced by corporations based on its database of knowledge. For instance, if a manufacturing company wants to improve the efficiency of its production line, the proposal department can propose an optimal production line design based on its expert knowledge. The proposal department can also propose solutions to management problems faced by corporations based on its database of knowledge. For example, it can propose an optimal management strategy based on its expert knowledge regarding issues related to a company's management strategy. Furthermore, the proposal department can propose solutions to legal problems faced by corporations based on its database of knowledge. For example, it can propose an optimal legal strategy based on its expert knowledge regarding issues related to a company's legal affairs. This allows the proposal department to propose appropriate solutions to the problems of corporations. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can propose solutions using an AI model that takes a corporation's problem as input and outputs a solution.

[0038] The answering unit can respond to user questions in real time. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit will respond in real time, based on expert knowledge, with information on market research methods and points to note. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. Furthermore, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. Furthermore, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. This allows for a rapid response to user questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can respond in real time using an AI model that takes user questions as input and outputs answers.

[0039] The customization department can be customized according to the needs of the corporation. For example, the customization department can customize for healthcare institutions or for the manufacturing industry. For example, the customization department can customize for healthcare institutions with enhanced medical-related expertise. For the manufacturing industry, the customization department can customize specifically for improving the efficiency of production lines. Furthermore, the customization department can customize for the financial industry with a focus on risk management. This allows the department to address the specific needs of the corporation. Some or all of the processes described above in the customization department may be performed using AI, for example, or not. For example, the customization department can perform customization using an AI model that takes the corporation's needs as input and outputs a customized solution.

[0040] The update unit can periodically update the database. For example, the update unit can periodically add expert knowledge to the database. For example, the update unit can add new expert knowledge to the database every month. It can also add new expert knowledge to the database every week. Furthermore, it can add new expert knowledge to the database every day. This ensures that the latest information is always provided. Some or all of the above processes in the update unit may be performed using AI, for example, or without AI. For example, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database.

[0041] The learning unit allows the AI ​​to learn expert knowledge. For example, the learning unit learns expert knowledge using machine learning algorithms. For example, the learning unit can learn expert knowledge using supervised learning. The learning unit can also learn expert knowledge using unsupervised learning. Furthermore, the learning unit can learn expert knowledge using reinforcement learning. This allows the AI ​​to continuously learn expert knowledge. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results.

[0042] The database creation unit can evaluate the reliability of expert knowledge when creating a database, and prioritize the creation of highly reliable information. For example, the database creation unit can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the accuracy of expert knowledge and prioritize the creation of accurate information. Furthermore, the database creation unit can evaluate the consistency of expert knowledge and prioritize the creation of consistent information. This ensures that highly reliable information is prioritized in the database. Some or all of the above processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates reliability to create a database of highly reliable information.

[0043] The database creation unit can evaluate the relevance of expert knowledge when creating a database, and prioritize the creation of highly relevant information. For example, the database creation unit can evaluate the relevance of expert knowledge and prioritize the creation of highly relevant information. For example, the database creation unit can evaluate the scope of application of expert knowledge and prioritize the creation of information that can be widely applied. Furthermore, the database creation unit can evaluate the practicality of expert knowledge and prioritize the creation of practical information. This allows for the prioritization of highly relevant information in the database. Some or all of the above-described processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates relevance to create a database of highly relevant information.

[0044] The database creation unit can evaluate the frequency of knowledge updates when creating a database of expert knowledge, and prioritize the creation of information that is frequently updated. For example, the database creation unit can evaluate the frequency of updates of expert knowledge and prioritize the creation of information that is frequently updated. For example, the database creation unit can evaluate the timeliness of expert knowledge and prioritize the creation of the latest information. Furthermore, the database creation unit can evaluate the variability of expert knowledge and prioritize the creation of information that does not variage. This allows for the prioritization of information that is frequently updated. Some or all of the above processing in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates the frequency of updates to create a database of information that is frequently updated.

[0045] The database creation unit, when creating a database of expert knowledge, can evaluate the source of the knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the accuracy of the source of expert knowledge and prioritize the creation of information from accurate sources. Furthermore, the database creation unit can evaluate the consistency of the source of expert knowledge and prioritize the creation of information from consistent sources. This ensures that information from reliable sources is prioritized for database creation. Some or all of the above processing in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates the reliability of the source to create a database of information from reliable sources.

[0046] The proposal department can assess the urgency of a corporation's problems and propose solutions preferentially to those with high urgency. For example, the proposal department can assess the scope of impact of a corporation's problems and propose solutions preferentially to those with a wide scope of impact. The proposal department can also assess the frequency of occurrence of a corporation's problems and propose solutions preferentially to those that occur frequently. This allows for the rapid proposal of solutions to high-urgency problems. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can take a corporation's problems as input and use an AI model to assess urgency and propose solutions preferentially to those with high urgency.

[0047] The proposal unit can assess the complexity of a corporation's problems and propose detailed solutions to complex problems. For example, the proposal unit can assess the scope of impact of a corporation's problems and propose detailed solutions to problems with a wide scope of impact. The proposal unit can also assess the frequency of occurrence of a corporation's problems and propose detailed solutions to problems that occur frequently. In this way, it can propose detailed solutions to complex problems. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can take a corporation's problems as input and use an AI model to assess complexity to propose detailed solutions to complex problems.

[0048] The proposal department can evaluate the scope of impact of a corporation's problems and propose solutions preferentially to problems with a wide scope of impact. For example, the proposal department can evaluate the scope of impact of a corporation's problems and propose solutions preferentially to problems with a wide scope of impact. For example, the proposal department can evaluate the urgency of a corporation's problems and propose solutions preferentially to problems with high urgency. The proposal department can also evaluate the frequency of occurrence of a corporation's problems and propose solutions preferentially to problems that occur frequently. This allows for the rapid proposal of solutions to problems with a wide scope of impact. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can take a corporation's problems as input and use an AI model to evaluate the scope of impact to propose solutions preferentially to problems with a wide scope of impact.

[0049] The proposal department can evaluate the frequency of problems occurring within a corporation and propose solutions preferentially to those that occur frequently. For example, the proposal department can evaluate the scope of impact of problems within a corporation and propose solutions preferentially to those that occur frequently. Furthermore, the proposal department can evaluate the urgency of problems within a corporation and propose solutions preferentially to those that are highly urgent. This allows for the rapid proposal of solutions to frequently occurring problems. Some or all of the above-described processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can take problems within a corporation as input and use an AI model to evaluate their frequency of occurrence to propose solutions preferentially to those that occur frequently.

[0050] The answering unit can evaluate the importance of user questions and prioritize answering questions of higher importance. For example, the answering unit can evaluate the importance of user questions and prioritize answering questions of higher importance. For example, the answering unit can evaluate the urgency of user questions and prioritize answering questions of higher urgency. The answering unit can also evaluate the scope of impact of user questions and prioritize answering questions with a wide scope of impact. This allows for quick answers to questions of higher importance. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate importance and prioritize answering questions of higher importance.

[0051] The answering unit can evaluate the complexity of the user's question and provide detailed answers to complex questions. For example, the answering unit can evaluate the scope of the user's question and provide detailed answers to questions with a wide scope of impact. The answering unit can also evaluate the urgency of the user's question and provide detailed answers to questions with high urgency. In this way, detailed answers can be provided to complex questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take the user's question as input and use an AI model to evaluate complexity to provide detailed answers to complex questions.

[0052] The answering unit can evaluate the frequency of user questions and prioritize answers to frequently asked questions. For example, the answering unit can evaluate the frequency of user questions and prioritize answers to frequently asked questions. For example, the answering unit can evaluate the importance of user questions and prioritize answers to high-importance questions. The answering unit can also evaluate the urgency of user questions and prioritize answers to high-urgency questions. This allows for quick answers to frequently asked questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate frequency and prioritize answers to frequently asked questions.

[0053] The answering unit can evaluate the relevance of user questions and prioritize answering questions that are highly relevant. For example, the answering unit can evaluate the relevance of user questions and prioritize answering questions that are highly relevant. For example, the answering unit can evaluate the importance of user questions and prioritize answering questions that are of high importance. The answering unit can also evaluate the urgency of user questions and prioritize answering questions that are of high urgency. This allows for quick answers to highly relevant questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate relevance and prioritize answering questions that are highly relevant.

[0054] The customization department can evaluate the industry characteristics of a corporation and perform customizations tailored to those characteristics. For example, the customization department can perform customizations for the medical industry that enhance medical-related expertise. For example, the customization department can perform customizations for the manufacturing industry that focus on improving the efficiency of production lines. Furthermore, the customization department can perform customizations for the financial industry that focus on risk management. This allows for customizations tailored to industry characteristics. Some or all of the above-mentioned processes in the customization department may be performed using AI, for example, or not. For example, the customization department can use an AI model that takes the industry characteristics of a corporation as input and performs customizations tailored to those characteristics.

[0055] The customization department can evaluate the size of a corporation and perform customizations appropriate to that size. For example, the customization department can perform customizations for large corporations to handle large-scale data processing. For example, the customization department can perform cost-effective customizations for small and medium-sized enterprises. Furthermore, the customization department can perform highly flexible customizations for startups. This allows for customizations tailored to the size of the corporation. Some or all of the above-mentioned processes in the customization department may be performed using AI, for example, or not. For example, the customization department can perform customizations using an AI model that takes the size of the corporation as input and performs customizations appropriate to that size.

[0056] The update unit can evaluate the update frequency of the database and prioritize updating information that is frequently updated. For example, the update unit can evaluate the up-to-dateness of the database and prioritize updating the latest information. The update unit can also evaluate the variability of the database and prioritize updating information that does not vari. This allows for the priority updating of information that is frequently updated. Some or all of the above processing in the update unit may be performed using AI, for example, or without AI. For example, the update unit can take the database update frequency as input and use an AI model to evaluate the update frequency to update information that is frequently updated.

[0057] The update unit can evaluate the reliability of the database and prioritize updating highly reliable information. For example, the update unit can evaluate the reliability of the database and prioritize updating highly reliable information. For example, the update unit can evaluate the accuracy of the database and prioritize updating accurate information. The update unit can also evaluate the consistency of the database and prioritize updating consistent information. This ensures that highly reliable information is updated preferentially. Some or all of the above processing in the update unit may be performed using AI, for example, or without AI. For example, the update unit can take the reliability of the database as input and use an AI model to evaluate reliability to update highly reliable information.

[0058] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit can optimize the learning algorithm by analyzing past learning results. The learning unit can also optimize the learning algorithm by evaluating trends in past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can perform learning using an AI model that takes past learning data as input and optimizes the learning algorithm.

[0059] The learning unit can weight the training data based on the database update timing during training. For example, the learning unit can weight the most recent data based on the database update timing. For example, the learning unit can weight frequently updated data based on the database update frequency. The learning unit can also weight highly reliable data based on the database reliability. This allows the training data to be weighted based on the database update timing. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can perform training using an AI model that takes the database update timing as input and weights the training data.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The database creation unit can evaluate the reliability of expert knowledge when creating a database, and prioritize the creation of highly reliable information. For example, it can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. It can also evaluate the accuracy of expert knowledge and prioritize the creation of accurate information. Furthermore, it can evaluate the consistency of expert knowledge and prioritize the creation of consistent information. In this way, highly reliable information can be prioritized in the database.

[0062] The proposal department can assess the urgency of a company's problems and prioritize solutions for those with high urgency. For example, it can assess the scope of impact of a company's problems and prioritize solutions for those with a wide impact. It can also assess the frequency of occurrence of a company's problems and prioritize solutions for those that occur frequently. This allows for the rapid proposal of solutions to high-urgency problems.

[0063] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can optimize the learning algorithm by referring to past learning data. It can also optimize the learning algorithm by analyzing past learning results. Furthermore, it can optimize the learning algorithm by evaluating trends in past learning data. This allows for the optimization of the learning algorithm by referring to past learning data.

[0064] The proposal department can assess the complexity of a corporation's problems and propose detailed solutions to those problems. For example, it can assess the scope of impact of a corporation's problems and propose detailed solutions to problems with a wide impact. It can also assess the frequency of occurrence of a corporation's problems and propose detailed solutions to problems that occur frequently. In this way, it can propose detailed solutions to complex problems.

[0065] The answering function can evaluate the importance of user questions and prioritize answering high-priority questions. For example, it can evaluate the urgency of user questions and prioritize answering high-priority questions. It can also evaluate the scope of impact of user questions and prioritize answering questions with a wide scope of impact. This allows for quick answers to high-priority questions.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The database creation unit creates a database of expert knowledge. For example, machine learning and natural language processing are used to store expert knowledge in the database. This allows for the creation of a database of expert knowledge in the medical field, enabling the rapid proposal of solutions to problems faced by healthcare institutions. Step 2: The proposal department proposes solutions to the company's problems based on the knowledge compiled in the database by the database department. For example, if a manufacturing company wants to improve the efficiency of its production line, the proposal department will propose an optimal production line design based on expert knowledge. The proposal department can propose solutions using an AI model that takes the company's problems as input and outputs solutions. Step 3: The answering unit responds to user questions in real time based on the solutions proposed by the suggestion unit. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the AI ​​will respond in real time with market research methods and points to note based on expert knowledge. The answering unit can respond in real time using an AI model that takes user questions as input and outputs answers. Step 4: The customization section customizes the system according to the needs of the organization. For example, customization is possible for healthcare institutions or manufacturing companies. The customization section can perform customization using an AI model that takes the organization's needs as input and outputs a customized solution. Step 5: The update unit periodically updates the database. For example, it regularly adds expert knowledge to the database. The update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. Step 6: The learning unit allows the AI ​​to learn expert knowledge. For example, it can learn expert knowledge using machine learning algorithms. The learning unit can perform learning using an AI model that takes expert knowledge as input and outputs the learning results.

[0068] (Example of form 2) The knowledge-sharing agent system according to an embodiment of the present invention is a system that learns from experts and provides that knowledge customized for corporations. This knowledge-sharing agent system proposes solutions to specific problems faced by corporations based on its specialized knowledge. For example, the knowledge-sharing agent system databases the knowledge of experts. The expert knowledge is stored in the database using machine learning and natural language processing. For example, by creating a database of the knowledge of experts in the medical field, it is possible to quickly propose solutions to problems faced by medical institutions. Next, the AI ​​in the knowledge-sharing agent system uses the database to propose solutions to specific problems faced by corporations. For example, if a manufacturing company wants to improve the efficiency of its production line, the AI ​​will propose an optimal production line design based on the expert's knowledge. The knowledge-sharing agent system also answers user questions in real time. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the AI ​​will answer in real time, based on the expert's knowledge, regarding market research methods and points to note. Furthermore, the knowledge-sharing agent system can be customized according to the needs of corporations and can support multiple industries. For example, customization for medical institutions or manufacturing companies is possible. Furthermore, the knowledge-sharing agent system maintains up-to-date knowledge through regular updates. This allows it to always propose solutions based on the latest information. The knowledge-sharing agent system enables corporations to make quick and accurate decisions. For example, by making quick decisions based on solutions proposed by AI, it is expected that costs will be reduced through improved operational efficiency and the speed of decision-making will increase. It is also expected to create opportunities for new businesses. For example, new businesses can be launched based on new business models proposed by AI. In this way, the knowledge-sharing agent system can provide quick and accurate solutions to corporations' problems.

[0069] The knowledge-sharing agent system according to this embodiment comprises a database unit, a proposal unit, an answer unit, a customization unit, an update unit, and a learning unit. The database unit databases the knowledge of experts. The database unit stores the knowledge of experts in the database, for example, using machine learning and natural language processing. For example, by databaseizing the knowledge of experts in the medical field, the database unit can quickly propose solutions to problems faced by medical institutions. The proposal unit proposes solutions to the problems of corporations based on the knowledge databased by the database unit. For example, if a manufacturing company wants to improve the efficiency of its production line, the proposal unit proposes an optimal production line design based on the knowledge of experts. Some or all of the above-described processes in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can propose solutions using an AI model that takes the problems of corporations as input and outputs solutions. The answer unit answers the user's questions in real time based on the solutions proposed by the proposal unit. The response unit, for example, when a company representative asks the AI, "We want to conduct market research on a new product," will provide real-time answers based on expert knowledge regarding market research methods and points to note. Some or all of the above-mentioned processes in the response unit may be performed using AI, or not. For example, the response unit can provide real-time answers using an AI model that takes the user's question as input and outputs an answer. The customization unit customizes according to the needs of the corporation. For example, the customization unit can customize for medical institutions or for the manufacturing industry. Some or all of the above-mentioned processes in the customization unit may be performed using AI, or not. For example, the customization unit can perform customization using an AI model that takes the corporation's needs as input and outputs a customized solution. The update unit periodically updates the database. For example, the update unit periodically adds expert knowledge to the database. Some or all of the above-mentioned processes in the update unit may be performed using AI, or not.For example, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. The learning unit allows the AI ​​to learn expert knowledge. The learning unit learns expert knowledge using a machine learning algorithm, for example. Some or all of the above-described processes in the learning unit may be performed using AI, or not using AI. For example, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results. As a result, the knowledge-sharing agent system according to this embodiment can provide rapid and accurate solutions to corporate problems.

[0070] The Database Division databases expert knowledge. For example, it stores expert knowledge in a database using machine learning and natural language processing. Specifically, it collects information such as documents, reports, papers, and interviews provided by experts, incorporates this information as text data, and analyzes it using natural language processing techniques. The analyzed data is organized by knowledge category and topic and stored in the database in a searchable format. For example, when databaseizing the knowledge of experts in the medical field, it allows for the rapid proposal of solutions to problems faced by healthcare institutions. Medical knowledge includes information on diagnostic methods, treatments, drug use, and patient care. This information is organized so that healthcare institutions can access it quickly when needed. By efficiently collecting, organizing, and storing expert knowledge, the Database Division promotes the sharing and utilization of knowledge. Furthermore, the Database Division performs data validation and cleansing to guarantee the quality of the collected data. This ensures the accuracy and reliability of the information stored in the database. In addition, the Database Division provides an interface for easy data updating and addition, enabling experts to continuously provide new knowledge. This ensures that the database always retains up-to-date information, allowing for quick and accurate solutions to corporate problems.

[0071] The Proposal Department proposes solutions to corporate problems based on knowledge compiled into a database by the Database Department. For example, if a manufacturing company wants to improve the efficiency of its production line, the Proposal Department will propose an optimal production line design based on expert knowledge. Specifically, the Proposal Department can propose solutions using an AI model that takes a corporate problem as input and outputs solutions. The AI ​​model utilizes the expert knowledge accumulated in the database to generate the optimal solution according to the characteristics and conditions of the problem. For example, if a manufacturing company wants to improve the efficiency of its production line, the AI ​​model will identify bottlenecks at each step of the production process and propose improvement measures. The Proposal Department also presents multiple solutions and compares their advantages and disadvantages to help the company make the best choice. By using AI, the Proposal Department can quickly analyze vast amounts of data and propose optimal solutions. Furthermore, the Proposal Department can collect feedback from companies and continuously improve the accuracy and effectiveness of its proposals. As a result, the Proposal Department can provide quick and accurate solutions to corporate problems, supporting business efficiency and problem solving.

[0072] The answering unit responds to user questions in real time based on solutions proposed by the suggestion unit. For example, if a company representative asks the AI, "We want to conduct market research for a new product," the answering unit will provide real-time answers on market research methods and points to note, based on expert knowledge. Specifically, the answering unit can respond in real time using an AI model that takes user questions as input and outputs answers. The AI ​​model utilizes expert knowledge accumulated in a database to generate the optimal answer to the user's question. For example, if a company wants to conduct market research for a new product, the AI ​​model will provide specific advice on market research methods, target market selection, data collection methods, and analysis methods. By using AI, the answering unit can quickly analyze vast amounts of data and provide accurate and rapid answers to user questions. Furthermore, the answering unit can collect user feedback and continuously improve the accuracy and effectiveness of its answers. As a result, the answering unit can provide quick and accurate answers to user questions, supporting business efficiency and problem solving.

[0073] The Customization Department customizes solutions according to the specific needs of each organization. For example, it can customize solutions for healthcare institutions or manufacturing companies. Specifically, the Customization Department uses an AI model that takes the organization's needs as input and outputs customized solutions. The AI ​​model generates optimal solutions based on the organization's specific needs and conditions. For example, customization for healthcare institutions provides diagnostic support systems and treatment planning support systems. Customization for manufacturing companies provides systems for optimizing production lines and supporting quality control. By using AI, the Customization Department can flexibly respond to the specific needs of each organization. Furthermore, the Customization Department can collect feedback from organizations and continuously improve the accuracy and effectiveness of its customizations. This allows the Customization Department to provide optimal solutions tailored to the organization's needs, supporting improved operational efficiency and problem-solving.

[0074] The update unit regularly updates the database. For example, the update unit regularly adds expert knowledge to the database. Specifically, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. The AI ​​model analyzes the new knowledge and integrates it into the existing database. This ensures that the database always holds the latest information and can provide quick and accurate solutions to corporate problems. By using AI, the update unit can quickly analyze vast amounts of data and efficiently update the database. Furthermore, the update unit can collect expert feedback and continuously improve the content and structure of the database. As a result, the update unit can always provide highly accurate solutions based on the latest information and support corporate problem-solving.

[0075] The learning unit allows AI to learn expert knowledge. For example, the learning unit learns expert knowledge using machine learning algorithms. Specifically, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results. The AI ​​model analyzes the expert knowledge and extracts patterns and trends. This allows the AI ​​to efficiently learn expert knowledge and accumulate knowledge useful for problem solving. By using AI, the learning unit can quickly analyze vast amounts of data and perform learning efficiently. Furthermore, the learning unit can collect feedback from experts and continuously improve the accuracy and effectiveness of its learning content. This enables the learning unit to always provide highly accurate solutions based on the latest knowledge, supporting problem solving for corporations.

[0076] The database creation unit can store expert knowledge in a database using machine learning and natural language processing. For example, the database creation unit can store expert knowledge in a database using machine learning algorithms. For example, the database creation unit can store expert knowledge in a database using supervised learning. The database creation unit can also store expert knowledge in a database using unsupervised learning. Furthermore, the database creation unit can store expert knowledge in a database using reinforcement learning. For example, the database creation unit can store expert knowledge in a database using natural language processing techniques. For example, the database creation unit can store expert knowledge in a database using morphological analysis. Furthermore, the database creation unit can store expert knowledge in a database using grammatical analysis. Furthermore, the database creation unit can store expert knowledge in a database using semantic analysis. This allows for the efficient database creation of expert knowledge. Some or all of the above-described processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can perform database creation using an AI model that takes expert knowledge as input and outputs a database.

[0077] The proposal department can propose solutions to specific problems faced by corporations based on its database of knowledge. For example, it can propose solutions to technical problems faced by corporations based on its database of knowledge. For instance, if a manufacturing company wants to improve the efficiency of its production line, the proposal department can propose an optimal production line design based on its expert knowledge. The proposal department can also propose solutions to management problems faced by corporations based on its database of knowledge. For example, it can propose an optimal management strategy based on its expert knowledge regarding issues related to a company's management strategy. Furthermore, the proposal department can propose solutions to legal problems faced by corporations based on its database of knowledge. For example, it can propose an optimal legal strategy based on its expert knowledge regarding issues related to a company's legal affairs. This allows the proposal department to propose appropriate solutions to the problems of corporations. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can propose solutions using an AI model that takes a corporation's problem as input and outputs a solution.

[0078] The answering unit can respond to user questions in real time. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit will respond in real time, based on expert knowledge, with information on market research methods and points to note. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. Furthermore, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. Furthermore, if a company representative asks the AI, "We want to conduct market research on a new product," the answering unit can respond in real time, based on expert knowledge, with information on market research methods and points to note. This allows for a rapid response to user questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can respond in real time using an AI model that takes user questions as input and outputs answers.

[0079] The customization department can be customized according to the needs of the corporation. For example, the customization department can customize for healthcare institutions or for the manufacturing industry. For example, the customization department can customize for healthcare institutions with enhanced medical-related expertise. For the manufacturing industry, the customization department can customize specifically for improving the efficiency of production lines. Furthermore, the customization department can customize for the financial industry with a focus on risk management. This allows the department to address the specific needs of the corporation. Some or all of the processes described above in the customization department may be performed using AI, for example, or not. For example, the customization department can perform customization using an AI model that takes the corporation's needs as input and outputs a customized solution.

[0080] The update unit can periodically update the database. For example, the update unit can periodically add expert knowledge to the database. For example, the update unit can add new expert knowledge to the database every month. It can also add new expert knowledge to the database every week. Furthermore, it can add new expert knowledge to the database every day. This ensures that the latest information is always provided. Some or all of the above processes in the update unit may be performed using AI, for example, or without AI. For example, the update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database.

[0081] The learning unit allows the AI ​​to learn expert knowledge. For example, the learning unit learns expert knowledge using machine learning algorithms. For example, the learning unit can learn expert knowledge using supervised learning. The learning unit can also learn expert knowledge using unsupervised learning. Furthermore, the learning unit can learn expert knowledge using reinforcement learning. This allows the AI ​​to continuously learn expert knowledge. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can perform learning using an AI model that takes expert knowledge as input and outputs learning results.

[0082] The database creation unit can estimate the sentiments of experts, evaluate the importance of knowledge based on the estimated expert sentiments, and determine the priority of database creation. For example, the database creation unit can prioritize the creation of knowledge that experts have shown strong interest in. For example, the database creation unit can prioritize the creation of knowledge that experts have deemed important. The database creation unit can also prioritize the creation of knowledge that experts frequently refer to. This allows the importance of knowledge to be evaluated and priority determined based on the expert sentiments. Sentiment estimation is achieved using sentiment estimation functions, such as sentiment engines 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 processing in the database creation unit may be performed using AI, or not. For example, the database creation unit can determine the priority of database creation using an AI model that takes expert sentiment data as input and evaluates the importance of knowledge.

[0083] The database creation unit can evaluate the reliability of expert knowledge when creating a database, and prioritize the creation of highly reliable information. For example, the database creation unit can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the accuracy of expert knowledge and prioritize the creation of accurate information. Furthermore, the database creation unit can evaluate the consistency of expert knowledge and prioritize the creation of consistent information. This ensures that highly reliable information is prioritized in the database. Some or all of the above processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates reliability to create a database of highly reliable information.

[0084] The database creation unit can evaluate the relevance of expert knowledge when creating a database, and prioritize the creation of highly relevant information. For example, the database creation unit can evaluate the relevance of expert knowledge and prioritize the creation of highly relevant information. For example, the database creation unit can evaluate the scope of application of expert knowledge and prioritize the creation of information that can be widely applied. Furthermore, the database creation unit can evaluate the practicality of expert knowledge and prioritize the creation of practical information. This allows for the prioritization of highly relevant information in the database. Some or all of the above-described processes in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates relevance to create a database of highly relevant information.

[0085] The database creation unit can estimate the emotions of experts, classify knowledge categories based on the estimated emotions, and create a database. For example, the database creation unit can prioritize the creation of categories that experts have shown strong interest in. For example, the database creation unit can prioritize the creation of categories that experts have deemed important. The database creation unit can also prioritize the creation of categories that experts frequently refer to. This allows for the classification and database creation of knowledge categories based on the emotions of experts. 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 database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can take expert emotion data as input and perform database creation using an AI model that classifies knowledge categories.

[0086] The database creation unit can evaluate the frequency of knowledge updates when creating a database of expert knowledge, and prioritize the creation of information that is frequently updated. For example, the database creation unit can evaluate the frequency of updates of expert knowledge and prioritize the creation of information that is frequently updated. For example, the database creation unit can evaluate the timeliness of expert knowledge and prioritize the creation of the latest information. Furthermore, the database creation unit can evaluate the variability of expert knowledge and prioritize the creation of information that does not variage. This allows for the prioritization of information that is frequently updated. Some or all of the above processing in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates the frequency of updates to create a database of information that is frequently updated.

[0087] The database creation unit, when creating a database of expert knowledge, can evaluate the source of the knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. For example, the database creation unit can evaluate the accuracy of the source of expert knowledge and prioritize the creation of information from accurate sources. Furthermore, the database creation unit can evaluate the consistency of the source of expert knowledge and prioritize the creation of information from consistent sources. This ensures that information from reliable sources is prioritized for database creation. Some or all of the above processing in the database creation unit may be performed using AI, for example, or without AI. For example, the database creation unit can use an AI model that takes expert knowledge as input and evaluates the reliability of the source to create a database of information from reliable sources.

[0088] The proposal unit can estimate the emotions of the company's representative and adjust the expression of the proposal based on the estimated emotions. For example, if the company's representative is stressed, the proposal unit can suggest a simple expression. For example, if the company's representative is relaxed, the proposal unit can suggest a detailed expression. Furthermore, if the company's representative is in a hurry, the proposal unit can suggest a quick expression. This allows the proposal to be expressed in a way that suits the emotions of the company's representative. 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 proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can take the company's representative's emotion data as input and make a proposal using an AI model that adjusts the expression of the proposal.

[0089] The proposal department can assess the urgency of a corporation's problems and propose solutions preferentially to those with high urgency. For example, the proposal department can assess the scope of impact of a corporation's problems and propose solutions preferentially to those with a wide scope of impact. The proposal department can also assess the frequency of occurrence of a corporation's problems and propose solutions preferentially to those that occur frequently. This allows for the rapid proposal of solutions to high-urgency problems. Some or all of the above processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can take a corporation's problems as input and use an AI model to assess urgency and propose solutions preferentially to those with high urgency.

[0090] The proposal unit can assess the complexity of a corporation's problems and propose detailed solutions to complex problems. For example, the proposal unit can assess the scope of impact of a corporation's problems and propose detailed solutions to problems with a wide scope of impact. The proposal unit can also assess the frequency of occurrence of a corporation's problems and propose detailed solutions to problems that occur frequently. In this way, it can propose detailed solutions to complex problems. Some or all of the above processing in the proposal unit may be performed using AI, for example, or without AI. For example, the proposal unit can take a corporation's problems as input and use an AI model to assess complexity to propose detailed solutions to complex problems.

[0091] The proposal unit can estimate the emotions of the company's representative and adjust the timing of the proposal based on the estimated emotions. For example, if the company's representative is stressed, the proposal unit can delay the timing of the proposal. For example, if the company's representative is relaxed, the proposal unit can advance the timing of the proposal. Also, if the company's representative is in a hurry, the proposal unit can make the proposal quickly. This allows proposals to be made at a timing appropriate to the emotions of the company's representative. 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 proposal unit may be performed using AI, for example, or not using AI. For example, the proposal unit can take the company's representative's emotion data as input and make a proposal using an AI model that adjusts the timing of the proposal.

[0092] The proposal department can evaluate the scope of impact of a corporation's problems and propose solutions preferentially to problems with a wide scope of impact. For example, the proposal department can evaluate the scope of impact of a corporation's problems and propose solutions preferentially to problems with a wide scope of impact. For example, the proposal department can evaluate the urgency of a corporation's problems and propose solutions preferentially to problems with high urgency. The proposal department can also evaluate the frequency of occurrence of a corporation's problems and propose solutions preferentially to problems that occur frequently. This allows for the rapid proposal of solutions to problems with a wide scope of impact. Some or all of the above processes in the proposal department may be performed using AI, for example, or not using AI. For example, the proposal department can take a corporation's problems as input and use an AI model to evaluate the scope of impact to propose solutions preferentially to problems with a wide scope of impact.

[0093] The proposal department can evaluate the frequency of problems occurring within a corporation and propose solutions preferentially to those that occur frequently. For example, the proposal department can evaluate the scope of impact of problems within a corporation and propose solutions preferentially to those that occur frequently. Furthermore, the proposal department can evaluate the urgency of problems within a corporation and propose solutions preferentially to those that are highly urgent. This allows for the rapid proposal of solutions to frequently occurring problems. Some or all of the above-described processes in the proposal department may be performed using AI, for example, or not. For example, the proposal department can take problems within a corporation as input and use an AI model to evaluate their frequency of occurrence to propose solutions preferentially to those that occur frequently.

[0094] The response unit can estimate the user's emotions and adjust the way it expresses its response based on the estimated emotions. For example, if the user is stressed, the response unit will respond in a simple way. For example, if the user is relaxed, the response unit can respond in a detailed way. Also, if the user is in a hurry, the response unit can respond in a rapid way. This allows the response to be expressed in a way that suits the user's emotions. 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 response unit may be performed using AI, for example, or not using AI. For example, the response unit can take user emotion data as input and use an AI model to adjust the way it expresses its response to provide an answer.

[0095] The answering unit can evaluate the importance of user questions and prioritize answering questions of higher importance. For example, the answering unit can evaluate the importance of user questions and prioritize answering questions of higher importance. For example, the answering unit can evaluate the urgency of user questions and prioritize answering questions of higher urgency. The answering unit can also evaluate the scope of impact of user questions and prioritize answering questions with a wide scope of impact. This allows for quick answers to questions of higher importance. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate importance and prioritize answering questions of higher importance.

[0096] The answering unit can evaluate the complexity of the user's question and provide detailed answers to complex questions. For example, the answering unit can evaluate the scope of the user's question and provide detailed answers to questions with a wide scope of impact. The answering unit can also evaluate the urgency of the user's question and provide detailed answers to questions with high urgency. In this way, detailed answers can be provided to complex questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take the user's question as input and use an AI model to evaluate complexity to provide detailed answers to complex questions.

[0097] The response unit can estimate the user's emotions and adjust the timing of its response based on the estimated emotions. For example, if the user is stressed, the response unit may delay its response. For example, if the user is relaxed, the response unit may speed up its response. The response unit can also respond quickly if the user is in a hurry. This allows the response to be given at a time appropriate to the user's emotions. 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 response unit may be performed using AI, for example, or without AI. For example, the response unit can take user emotion data as input and provide a response using an AI model that adjusts the timing of the response.

[0098] The answering unit can evaluate the frequency of user questions and prioritize answers to frequently asked questions. For example, the answering unit can evaluate the frequency of user questions and prioritize answers to frequently asked questions. For example, the answering unit can evaluate the importance of user questions and prioritize answers to high-importance questions. The answering unit can also evaluate the urgency of user questions and prioritize answers to high-urgency questions. This allows for quick answers to frequently asked questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate frequency and prioritize answers to frequently asked questions.

[0099] The answering unit can evaluate the relevance of user questions and prioritize answering questions that are highly relevant. For example, the answering unit can evaluate the relevance of user questions and prioritize answering questions that are highly relevant. For example, the answering unit can evaluate the importance of user questions and prioritize answering questions that are of high importance. The answering unit can also evaluate the urgency of user questions and prioritize answering questions that are of high urgency. This allows for quick answers to highly relevant questions. Some or all of the above processing in the answering unit may be performed using AI, for example, or without AI. For example, the answering unit can take user questions as input and use an AI model to evaluate relevance and prioritize answering questions that are highly relevant.

[0100] The customization unit can estimate the emotions of the company's representative and adjust the customization content based on the estimated emotions. For example, if the company's representative is stressed, the customization unit can suggest simple customization content. For example, if the company's representative is relaxed, the customization unit can suggest detailed customization content. Furthermore, if the company's representative is in a hurry, the customization unit can suggest quick customization content. This allows customization to be performed in accordance with the emotions of the company's representative. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the customization unit may be performed using AI, or not using AI. For example, the customization unit can perform customization using an AI model that takes the company's representative's emotion data as input and adjusts the customization content.

[0101] The customization department can evaluate the industry characteristics of a corporation and perform customizations tailored to those characteristics. For example, the customization department can perform customizations for the medical industry that enhance medical-related expertise. For example, the customization department can perform customizations for the manufacturing industry that focus on improving the efficiency of production lines. Furthermore, the customization department can perform customizations for the financial industry that focus on risk management. This allows for customizations tailored to industry characteristics. Some or all of the above-mentioned processes in the customization department may be performed using AI, for example, or not. For example, the customization department can use an AI model that takes the industry characteristics of a corporation as input and performs customizations tailored to those characteristics.

[0102] The customization unit can estimate the emotions of the company's representative and determine the priority of customization based on the estimated emotions. For example, if the company's representative is stressed, the customization unit can suggest high-priority customizations. For example, if the company's representative is relaxed, the customization unit can suggest low-priority customizations. The customization unit can also perform customizations quickly if the company's representative is in a hurry. This allows customizations to be performed with priorities that correspond to the emotions of the company's representative. 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 customization unit may be performed using AI, for example, or without AI. For example, the customization unit can take the emotions of the company's representative as input and perform customizations using an AI model that determines the priority of customizations.

[0103] The customization department can evaluate the size of a corporation and perform customizations appropriate to that size. For example, the customization department can perform customizations for large corporations to handle large-scale data processing. For example, the customization department can perform cost-effective customizations for small and medium-sized enterprises. Furthermore, the customization department can perform highly flexible customizations for startups. This allows for customizations tailored to the size of the corporation. Some or all of the above-mentioned processes in the customization department may be performed using AI, for example, or not. For example, the customization department can perform customizations using an AI model that takes the size of the corporation as input and performs customizations appropriate to that size.

[0104] The update unit can estimate the emotions of experts and adjust the content of the update based on the estimated emotions. For example, the update unit can prioritize updating information that experts deem important. For example, the update unit can prioritize updating information that experts frequently refer to. It can also prioritize updating information that experts have shown strong interest in. This allows updates to be made in accordance with the emotions of experts. 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 update unit may be performed using AI, for example, or without AI. For example, the update unit can take expert emotion data as input and perform updates using an AI model that adjusts the content of the update.

[0105] The update unit can evaluate the update frequency of the database and prioritize updating information that is frequently updated. For example, the update unit can evaluate the up-to-dateness of the database and prioritize updating the latest information. The update unit can also evaluate the variability of the database and prioritize updating information that does not vari. This allows for the priority updating of information that is frequently updated. Some or all of the above processing in the update unit may be performed using AI, for example, or without AI. For example, the update unit can take the database update frequency as input and use an AI model to evaluate the update frequency to update information that is frequently updated.

[0106] The update unit can estimate the expert's emotions and adjust the timing of updates based on the estimated emotions. For example, if the expert is stressed, the update unit can delay the timing of the update. For example, if the expert is relaxed, the update unit can speed up the timing of the update. Also, if the expert is in a hurry, the update unit can perform the update quickly. This allows updates to be performed at a timing appropriate to the expert's emotions. 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 update unit may be performed using AI, for example, or without AI. For example, the update unit can take expert emotion data as input and perform updates using an AI model that adjusts the timing of updates.

[0107] The update unit can evaluate the reliability of the database and prioritize updating highly reliable information. For example, the update unit can evaluate the reliability of the database and prioritize updating highly reliable information. For example, the update unit can evaluate the accuracy of the database and prioritize updating accurate information. The update unit can also evaluate the consistency of the database and prioritize updating consistent information. This ensures that highly reliable information is updated preferentially. Some or all of the above processing in the update unit may be performed using AI, for example, or without AI. For example, the update unit can take the reliability of the database as input and use an AI model to evaluate reliability to update highly reliable information.

[0108] The learning unit can estimate the emotions of experts and select training data based on the estimated emotions. For example, the learning unit can prioritize learning data that experts deem important. For example, the learning unit can prioritize learning data that experts frequently mention. It can also prioritize learning data that experts have shown strong interest in. This allows for the selection of training data based on the emotions of experts. 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 learning unit may be performed using AI, for example, or without AI. For example, the learning unit can perform training using an AI model that takes expert emotion data as input and selects training data.

[0109] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit can optimize the learning algorithm by analyzing past learning results. The learning unit can also optimize the learning algorithm by evaluating trends in past learning data. This allows the learning algorithm to be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can perform learning using an AI model that takes past learning data as input and optimizes the learning algorithm.

[0110] The learning unit can estimate the emotions of experts and adjust the learning frequency based on the estimated emotions. For example, if the expert is stressed, the learning unit can reduce the learning frequency. For example, if the expert is relaxed, the learning unit can increase the learning frequency. The learning unit can also perform learning quickly if the expert is in a hurry. This allows learning to be performed at a frequency appropriate to the expert's emotions. 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 learning unit may be performed using AI, for example, or without AI. For example, the learning unit can take expert emotion data as input and perform learning using an AI model that adjusts the learning frequency.

[0111] The learning unit can weight the training data based on the database update timing during training. For example, the learning unit can weight the most recent data based on the database update timing. For example, the learning unit can weight frequently updated data based on the database update frequency. The learning unit can also weight highly reliable data based on the database reliability. This allows the training data to be weighted based on the database update timing. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can perform training using an AI model that takes the database update timing as input and weights the training data.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The proposal team can estimate the emotions of the company's representative and adjust the way the proposal is presented based on that estimation. For example, if the representative is stressed, a simpler approach can be suggested. If the representative is relaxed, a more detailed approach can be suggested. Furthermore, if the representative is in a hurry, a more concise approach can be suggested. This allows proposals to be presented in a way that is appropriate to the emotions of the company's representative.

[0114] The database creation unit can evaluate the reliability of expert knowledge when creating a database, and prioritize the creation of highly reliable information. For example, it can evaluate the source of expert knowledge and prioritize the creation of information from reliable sources. It can also evaluate the accuracy of expert knowledge and prioritize the creation of accurate information. Furthermore, it can evaluate the consistency of expert knowledge and prioritize the creation of consistent information. In this way, highly reliable information can be prioritized in the database.

[0115] The proposal department can assess the urgency of a company's problems and prioritize solutions for those with high urgency. For example, it can assess the scope of impact of a company's problems and prioritize solutions for those with a wide impact. It can also assess the frequency of occurrence of a company's problems and prioritize solutions for those that occur frequently. This allows for the rapid proposal of solutions to high-urgency problems.

[0116] The response unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is stressed, it can respond using simple language. If the user is relaxed, it can respond using detailed language. Furthermore, if the user is in a hurry, it can respond using rapid language. This allows the system to respond in a way that is appropriate to the user's emotions.

[0117] The customization unit can estimate the emotions of the company's representative and adjust the customization content based on those estimates. For example, if the company's representative is stressed, it can suggest a simple customization plan. If the representative is relaxed, it can suggest a more detailed customization plan. Furthermore, if the representative is in a hurry, it can suggest a quick customization plan. This allows for customization tailored to the emotions of the company's representative.

[0118] The update unit can estimate the sentiment of experts and adjust the content of updates based on that estimated sentiment. For example, it can prioritize updating information that experts deem important. It can also prioritize updating information that experts frequently mention. Furthermore, it can prioritize updating information that experts have shown strong interest in. This allows updates to be tailored to the sentiments of experts.

[0119] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, it can optimize the learning algorithm by referring to past learning data. It can also optimize the learning algorithm by analyzing past learning results. Furthermore, it can optimize the learning algorithm by evaluating trends in past learning data. This allows for the optimization of the learning algorithm by referring to past learning data.

[0120] The proposal department can assess the complexity of a corporation's problems and propose detailed solutions to those problems. For example, it can assess the scope of impact of a corporation's problems and propose detailed solutions to problems with a wide impact. It can also assess the frequency of occurrence of a corporation's problems and propose detailed solutions to problems that occur frequently. In this way, it can propose detailed solutions to complex problems.

[0121] The answering function can evaluate the importance of user questions and prioritize answering high-priority questions. For example, it can evaluate the urgency of user questions and prioritize answering high-priority questions. It can also evaluate the scope of impact of user questions and prioritize answering questions with a wide scope of impact. This allows for quick answers to high-priority questions.

[0122] The learning unit can estimate the sentiments of experts and select training data based on those estimated sentiments. For example, it can prioritize training on data that experts deem important. It can also prioritize training on data that experts frequently mention. Furthermore, it can prioritize training on data that experts have shown strong interest in. This allows for the selection of training data based on the sentiments of experts.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The database creation unit creates a database of expert knowledge. For example, machine learning and natural language processing are used to store expert knowledge in the database. This allows for the creation of a database of expert knowledge in the medical field, enabling the rapid proposal of solutions to problems faced by healthcare institutions. Step 2: The proposal department proposes solutions to the company's problems based on the knowledge compiled in the database by the database department. For example, if a manufacturing company wants to improve the efficiency of its production line, the proposal department will propose an optimal production line design based on expert knowledge. The proposal department can propose solutions using an AI model that takes the company's problems as input and outputs solutions. Step 3: The answering unit responds to user questions in real time based on the solutions proposed by the suggestion unit. For example, if a company representative asks the AI, "We want to conduct market research on a new product," the AI ​​will respond in real time with market research methods and points to note based on expert knowledge. The answering unit can respond in real time using an AI model that takes user questions as input and outputs answers. Step 4: The customization section customizes the system according to the needs of the organization. For example, customization is possible for healthcare institutions or manufacturing companies. The customization section can perform customization using an AI model that takes the organization's needs as input and outputs a customized solution. Step 5: The update unit periodically updates the database. For example, it regularly adds expert knowledge to the database. The update unit can perform updates using an AI model that takes new expert knowledge as input and updates the database. Step 6: The learning unit allows the AI ​​to learn expert knowledge. For example, it can learn expert knowledge using machine learning algorithms. The learning unit can perform learning using an AI model that takes expert knowledge as input and outputs the learning results.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the database unit, proposal unit, response unit, customization unit, update unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the database unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes solutions to the corporation's problems. The response unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12 and answers the user's questions in real time. The customization unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12 and performs customization according to the corporation's needs. The update unit is implemented by the specific processing unit 290 of the data processing unit 12 and periodically updates the database. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns expert knowledge. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the database unit, proposal unit, response unit, customization unit, update unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the database unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes solutions to the company's problems. The response unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12 and answers the user's questions in real time. The customization unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12 and performs customization according to the company's needs. The update unit is implemented by the specific processing unit 290 of the data processing unit 12 and periodically updates the database. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns expert knowledge. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the database unit, proposal unit, response unit, customization unit, update unit, and learning unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the database unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to the corporation's problems. The response unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12 and answers the user's questions in real time. The customization unit is implemented by, for example, the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12 and performs customization according to the corporation's needs. The update unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and periodically updates the database. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns expert knowledge. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements described above, including the database unit, proposal unit, answer unit, customization unit, update unit, and learning unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the database unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to the corporation's problems. The answer unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12 and answers the user's questions in real time. The customization unit is implemented by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12 and performs customization according to the corporation's needs. The update unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and periodically updates the database. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns expert knowledge. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) A database department that digitizes expert knowledge, A proposal unit that proposes solutions to corporate problems based on the knowledge compiled in the database by the aforementioned database unit, A response unit that answers user questions in real time based on the solution proposed by the aforementioned proposal unit, A customization department that customizes products according to the needs of corporations, The update section, which is updated regularly, It includes a learning unit in which the AI ​​learns. A system characterized by the following features. (Note 2) The aforementioned database unit, Accumulate expert knowledge in a database using machine learning and natural language processing. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned proposal section is, We propose solutions to specific problems faced by corporations based on database-driven knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned response section is, Answer user questions in real time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned customization unit is Customized to meet the needs of the corporation. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned update section is, Update the database regularly. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, AI learns expert knowledge. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned database unit, The system estimates the sentiments of experts, evaluates the importance of knowledge based on those estimated sentiments, and determines the priority for database inclusion. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned database unit, When creating a database of expert knowledge, the reliability of that knowledge is evaluated, and the most reliable information is prioritized for inclusion in the database. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned database unit, When creating a database of expert knowledge, the relevance of the knowledge is evaluated, and highly relevant information is prioritized for inclusion in the database. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned database unit, We estimate the sentiments of experts, classify knowledge categories based on those estimated sentiments, and create a database. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned database unit, When creating a database of expert knowledge, the frequency of knowledge updates is evaluated, and information that is frequently updated is prioritized for inclusion in the database. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned database unit, When creating a database of expert knowledge, the source of the knowledge is evaluated, and information from reliable sources is prioritized for inclusion in the database. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, We estimate the emotions of the company's representative and adjust the way the proposal is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, We assess the urgency of corporate issues and prioritize solutions for the most urgent problems. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, We assess the complexity of corporate problems and propose detailed solutions for those complex issues. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, We estimate the emotions of the company's representative and adjust the timing of the proposal based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned proposal section is, We assess the scope of the impact of corporate issues and prioritize solutions for those with a wide impact. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, We evaluate the frequency of problems occurring within the organization and propose solutions that prioritize those that occur frequently. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned response section is, It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned response section is, The system evaluates the importance of user questions and prioritizes answering questions of higher importance. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned response section is, Evaluate the complexity of user questions and provide detailed answers to complex questions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned response section is, It estimates the user's emotions and adjusts the timing of responses based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned response section is, Evaluate the frequency of user questions and prioritize answering frequently asked questions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned response section is, The system evaluates the relevance of user questions and prioritizes answering those that are most relevant. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned customization unit is The system estimates the emotions of the company's representative and adjusts the customization based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned customization unit is We evaluate the industry characteristics of each company and customize the service to suit those characteristics. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned customization unit is It estimates the emotions of the company's representative and determines the priority of customization based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned customization unit is We evaluate the size of the company and customize the service accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned update section is, We estimate the sentiment of experts and adjust the content of updates based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned update section is, Evaluate the update frequency of the database and prioritize updating information that is frequently updated. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned update section is, We estimate the sentiment of experts and adjust the timing of updates based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned update section is, Evaluate the reliability of the database and prioritize updating with the most reliable information. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned learning unit, The system estimates the sentiments of experts and selects training data based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned learning unit, It estimates the sentiment of experts and adjusts the frequency of learning based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned learning unit, During training, the training data is weighted based on when the database was updated. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 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 database department that digitizes expert knowledge, A proposal unit that proposes solutions to corporate problems based on the knowledge compiled in the database by the aforementioned database unit, A response unit that answers user questions in real time based on the solution proposed by the aforementioned proposal unit, A customization department that customizes products according to the needs of corporations, The update section, which is updated regularly, It includes a learning unit in which the AI ​​learns, A system characterized by the following features.

2. The aforementioned database unit, Accumulate expert knowledge in a database using machine learning and natural language processing. The system according to feature 1.

3. The aforementioned proposal section is, We propose solutions to specific problems faced by corporations based on database-driven knowledge. The system according to feature 1.

4. The aforementioned response section is, Answer user questions in real time. The system according to feature 1.

5. The aforementioned customization unit is Customized to meet the needs of the corporation. The system according to feature 1.

6. The aforementioned update section is, Update the database regularly. The system according to feature 1.

7. The aforementioned learning unit, AI learns the knowledge of experts. The system according to feature 1.

8. The aforementioned database unit, The system estimates the sentiments of experts, evaluates the importance of knowledge based on those estimated sentiments, and determines the priority for database inclusion. The system according to feature 1.

Images