System

Abstract

An object of the system according to the embodiment is to improve the efficiency of business by obtaining expert knowledge even in a company with budget constraints.SOLUTION: A system according to an embodiment includes an expert knowledge providing unit, a work efficiency improvement proposal unit, and a problem solution support unit. The expert knowledge providing unit provides expert knowledge for a question or a problem of a company. The business efficiency improvement proposal part analyzes the business process on the basis of the expert knowledge provided by the expert knowledge provision part, and proposes efficiency improvement. The problem solution support unit proposes a solution to a specific problem based on the efficiency promotion plan proposed by the work efficiency promotion proposal unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has the drawback that it is difficult for companies that cannot hire experts due to budget constraints to obtain specialized knowledge.

[0005] The system according to the embodiment aims to enable even companies with budgetary constraints to acquire specialized knowledge and improve business efficiency. [Means for solving the problem]

[0006] The system according to the embodiment includes a specialized knowledge providing unit, a business efficiency improvement proposal unit, and a problem-solving support unit. The specialized knowledge providing unit provides specialized knowledge in response to questions and issues from companies. The business efficiency improvement proposal unit analyzes business processes based on the specialized knowledge provided by the specialized knowledge providing unit and makes proposals for efficiency improvements. The problem-solving support unit proposes solutions to specific problems based on the efficiency proposals proposed by the business efficiency improvement proposal unit. [Effects of the Invention]

[0007] The system according to the embodiment allows even companies with budgetary constraints to acquire specialized knowledge and improve the efficiency of their operations. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The AI-based specialized skill provision system according to an embodiment of the present invention is a system that provides specialized knowledge and skills that companies need, and supports improving business efficiency and problem solving. As a result, the AI-based specialized skill provision system enables companies that cannot hire experts due to budget constraints to utilize advanced specialized knowledge and skills to improve business efficiency and solve problems.

[0029] An AI-based specialized skill provision system according to an embodiment includes a specialized knowledge provision unit, a business efficiency improvement proposal unit, and a problem-solving support unit. The specialized knowledge provision unit provides specialized knowledge in response to a company's questions and challenges. For example, when a company inputs a marketing question, the specialized knowledge provision unit has a generation AI analyze the question and propose an appropriate marketing strategy. Furthermore, when a company submits a financial challenge, the specialized knowledge provision unit has a generation AI analyze the challenge and provide advice on financial analysis and budget management. Furthermore, when a company inputs a legal question, the specialized knowledge provision unit has a generation AI analyze the question and provide appropriate legal advice. The business efficiency improvement proposal unit analyzes business processes based on the specialized knowledge provided by the specialized knowledge provision unit and proposes efficiency improvements. For example, the business efficiency proposal unit analyzes a company's business flow, and the generation AI proposes workflow optimization. Furthermore, the business efficiency proposal unit can analyze a company's resource allocation, and the generation AI proposes optimal resource allocation. Furthermore, the business efficiency proposal unit can analyze a company's project management, and the generation AI proposes improvements to the project management. The problem-solving support unit proposes solutions to specific problems based on the efficiency proposals proposed by the business efficiency proposal unit. For example, if a company needs technical troubleshooting, the problem-solving support unit uses the generation AI to analyze the problem and propose a specific solution. If a company needs market analysis, the problem-solving support unit uses the generation AI to analyze market data and provide a competitive analysis and market trend forecast. When a company presents a challenge it faces in a specific project, the problem-solving support unit uses the generation AI to analyze the challenge and propose an optimal solution. In this way, the AI-based specialized skill provision system according to the embodiment can provide specialized knowledge for a company's questions and challenges, helping to streamline business processes and solve specific problems. For example, a company can receive quick and accurate advice through the AI ​​agent, thereby improving business efficiency and solving problems. Furthermore, a company can utilize specialized knowledge through the AI ​​agent to support business improvement and growth.

[0030] The expertise providing unit can generate personalized answers based on the user's past question history. In this case, for example, an AI agent analyzes the user's past question history and generates personalized answers based on the user's interests and needs. For example, a user who has asked many marketing-related questions in the past can be provided with answers specialized in marketing. In addition, the expertise providing unit identifies the user's knowledge level and field of expertise based on the user's past question history and provides appropriate expertise. For example, basic knowledge is provided for questions aimed at beginners, and advanced knowledge is provided for questions aimed at experts. In addition, the expertise providing unit allows the AI ​​agent to learn the user's past question history and generate answers to new questions based on answers the user previously received. For example, the AI ​​agent can provide more specific and detailed answers by referring to past answers. This makes it possible to provide more appropriate expertise by providing personalized answers based on the user's past question history.

[0031] The expert knowledge provision unit automatically incorporates the latest research papers and patent information, allowing it to always provide the latest information. For example, the expert knowledge provision unit uses an AI agent to regularly collect the latest research papers and patent information and update its expert knowledge based on that information. For example, it provides answers that incorporate the latest technological trends and research results. The expert knowledge provision unit also uses an AI agent to automatically analyze the latest research papers and patent information in a specific field, summarize the content, and provide it to the user. For example, it provides concise information on new technologies and methodologies. The expert knowledge provision unit also uses an AI agent to generate answers to user questions based on the latest research papers and patent information. For example, it provides specific solutions and suggestions while citing the latest research results. This allows the system to always provide the latest expert knowledge by incorporating the latest research papers and patent information.

[0032] The expertise providing unit can make the expertise available through at least one different interface of a voice assistant or a chatbot. The expertise providing unit, for example, makes the expertise provided by an AI agent available through a voice assistant. For example, a user can input a question by voice and receive an answer by voice. The expertise providing unit also makes the expertise provided by the AI ​​agent available through a chatbot. For example, a user can input a question in chat format and receive an answer in real time. The expertise providing unit also builds an integrated system for making the expertise provided by the AI ​​agent available through different interfaces. For example, consistent answers are provided across multiple platforms, such as a voice assistant, a chatbot, and a web interface. This improves user convenience by providing expertise through different interfaces, such as a voice assistant or a chatbot.

[0033] The expertise provision unit can integrate expertise from different industries and provide cross-domain knowledge. For example, an AI agent can integrate expertise from different industries to provide cross-domain knowledge. For example, it can combine knowledge from the medical and technical fields to make suggestions for new medical technologies. The expertise provision unit can also build a database for integrating expertise from different industries, and the AI ​​agent can provide cross-domain knowledge based on that database. For example, it can combine knowledge from marketing and finance to propose effective marketing strategies. The expertise provision unit can also collect feedback from experts in different industries and provide cross-domain knowledge based on that information. For example, it can combine knowledge from technology development and legal affairs to make suggestions for solving technical and legal problems simultaneously. This makes it possible to provide a wider range of knowledge by integrating expertise from different industries.

[0034] The business efficiency proposal unit can build a predictive model based on past business data and propose future business efficiency improvements. For example, the business efficiency proposal unit proposes future business efficiency improvements by having an AI agent analyze past business data and build a predictive model. For example, it identifies bottlenecks in business flows based on past data and proposes improvement measures. The business efficiency proposal unit also has an AI agent run a simulation for future business efficiency improvements based on past business data and propose an optimal business flow. For example, it makes proposals to optimize resource allocation and task priorities. The business efficiency proposal unit also has an AI agent learn from past business data and build a predictive model for future business efficiency improvements. For example, it proposes business process automation and optimal resource allocation. In this way, by building a predictive model based on past business data, it is possible to propose future business efficiency improvements.

[0035] The business efficiency proposal unit can perform simulations of efficiency improvement plans and select the optimal business flow. The business efficiency proposal unit, for example, builds a system that performs simulations of efficiency improvement plans proposed by an AI agent and selects the optimal business flow. For example, it simulates multiple efficiency improvement plans and selects the most effective plan. The business efficiency proposal unit also evaluates the feasibility of the efficiency improvement plans proposed by the AI ​​agent through simulation and selects the optimal business flow. For example, it simulates resource allocation and task scheduling. The business efficiency proposal unit also performs simulations of the efficiency improvement plans proposed by the AI ​​agent and identifies areas for improvement in the business flow. For example, it identifies bottlenecks in the business process through simulation and proposes improvement measures. In this way, the optimal business flow can be selected by performing simulations of the efficiency improvement plans.

[0036] The Business Efficiency Proposal Department can apply the efficiency improvement proposals to different departments and projects, thereby achieving company-wide efficiency. For example, the Business Efficiency Proposal Department builds a system that applies the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide efficiency. For example, it integrates business flows between departments, thereby achieving company-wide efficiency. The Business Efficiency Proposal Department also applies the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide business efficiency. For example, it makes proposals to optimize resource allocation for each department. The Business Efficiency Proposal Department also builds an integrated system to apply the efficiency improvement proposals proposed by the AI ​​agent across the company. For example, it integrates project management tools, thereby achieving company-wide business efficiency. In this way, company-wide efficiency can be achieved by applying the efficiency proposals to different departments and projects.

[0037] The business efficiency proposal department can compare business efficiency proposals with best practices from other companies and industries and make optimal proposals. For example, the business efficiency proposal department builds a system that compares business efficiency proposals proposed by an AI agent with best practices from other companies and industries and makes optimal proposals. For example, it makes proposals that incorporate industry-standard efficiency methods. The business efficiency proposal department also evaluates business efficiency proposals proposed by the AI ​​agent based on best practices from other companies and industries and makes optimal proposals. For example, it makes proposals that refer to successful cases from competitors. The business efficiency proposal department also uses the AI ​​agent to collect best practices from other companies and industries and makes business efficiency proposals based on that information. For example, it proposes efficiency proposals that incorporate the latest industry trends. This makes it possible to make optimal business efficiency proposals by comparing with best practices from other companies and industries.

[0038] The problem-solving support unit can propose optimal solutions based on past solutions and their results. For example, the problem-solving support unit uses an AI agent to analyze past problem-solving solutions and their results and propose optimal solutions. For example, it proposes solutions to similar problems based on solutions that have been successful in the past. The problem-solving support unit also builds a system in which the AI ​​agent proposes optimal solutions based on past problem-solving data. For example, it learns from past data and proposes the most effective solution. The problem-solving support unit also uses an AI agent to analyze past solutions and their results and propose optimal solutions with low risk. For example, it proposes solutions to avoid past failures. In this way, the accuracy of problem-solving is improved by proposing optimal solutions based on past solutions and their results.

[0039] The problem-solving support unit can perform risk assessments on solutions and prioritize low-risk solutions. The problem-solving support unit, for example, performs risk assessments on solutions proposed by an AI agent and builds a system that prioritizes low-risk solutions. For example, it quantifies the risk of solutions using a risk assessment model. The problem-solving support unit also determines the priority of solutions proposed by the AI ​​agent based on the risk assessment. For example, it prioritizes solutions with low risk. The problem-solving support unit also performs risk assessments on solutions proposed by the AI ​​agent and selects low-risk solutions. For example, it sets solution selection criteria based on the risk assessment results. In this way, risk assessments are performed and low-risk solutions are prioritized, thereby improving the safety of problem solving.

[0040] The problem-solving support unit can apply a solution to different problems and challenges and provide a general-purpose solution. For example, the problem-solving support unit builds a system that applies a solution proposed by an AI agent to different problems and challenges and provides a general-purpose solution. For example, it applies a solution to a technical problem to other business processes. The problem-solving support unit also applies a solution proposed by an AI agent to different problems and challenges and provides a general-purpose solution. For example, it applies a solution to a marketing problem to a financial problem. The problem-solving support unit also builds an integrated system that applies the solution proposed by the AI ​​agent to different problems and challenges. For example, it provides a common solution for different business processes. In this way, a general-purpose solution can be provided by applying the proposed solution to different problems and challenges.

[0041] The problem-solving support unit can compare problem-solving proposals with success stories from other companies and industries to provide optimal solutions. For example, the problem-solving support unit compares problem-solving proposals made by an AI agent with success stories from other companies and industries to build a system that provides optimal solutions. For example, it makes proposals that incorporate industry-standard solutions. The problem-solving support unit also evaluates problem-solving proposals made by an AI agent based on success stories from other companies and industries to provide optimal solutions. For example, it makes proposals that refer to success stories from competitors. The problem-solving support unit also collects success stories from other companies and industries and makes problem-solving proposals based on that information. For example, it proposes solutions that incorporate the latest trends in the industry. This makes it possible to provide optimal solutions by comparing with success stories from other companies and industries.

[0042] The system can collect feedback on the services it provides in real time and learn and improve instantly. For example, the system collects feedback on the services it provides from an AI agent in real time, and builds a system that learns and improves instantly based on that data. For example, the quality of the service is improved based on user feedback. The system also identifies areas for improvement in the services it provides from the AI ​​agent based on the feedback collected in real time, and learns and improves instantly. For example, it improves the service by reflecting user opinions. The system also analyzes feedback on the services it provides from the AI ​​agent in real time, and develops a system that learns and improves instantly. For example, it improves the quality of the service based on the feedback. In this way, the quality of the service is improved by collecting feedback in real time and learning and improving instantly.

[0043] The system can quantitatively evaluate the effectiveness of proposals and solutions provided and learn based on the results. For example, the system quantitatively evaluates the effectiveness of proposals and solutions provided by an AI agent and builds a system that learns based on the results. For example, the results after the proposal is implemented are evaluated numerically and used as learning data. The system also develops an evaluation model for quantitatively evaluating the effectiveness of proposals and solutions, and the AI ​​agent learns based on the results. For example, it evaluates the business efficiency and results after the proposal is implemented. The system also develops a system that quantitatively evaluates the effectiveness of proposals and solutions provided by an AI agent and learns based on that data. For example, it evaluates the results after the proposal is implemented numerically and reflects them in future proposals. In this way, the effectiveness of proposals and solutions can be quantitatively evaluated and learning based on the results can improve the accuracy of future proposals and solutions.

[0044] The system can collect learning data from different industries and fields, and improve services based on a wide range of knowledge. For example, the system can collect data for an AI agent to learn from different industries and fields, and build a system to improve services based on a wide range of knowledge. For example, data from different industries can be integrated to improve service quality. The system can also collect data from different industries and fields, and the AI ​​agent can learn from that data to improve services. For example, services can be improved by incorporating best practices from different industries. The system can also develop a system in which an AI agent collects data from different industries and fields, and improves services based on that information. For example, services can be improved by incorporating trends from different industries. In this way, by collecting data from different industries and fields, services can be improved based on a wide range of knowledge.

[0045] The system can share the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, the system builds a system for sharing the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, by sharing learning data, multiple AI agents simultaneously improve the quality of service. The system also develops an integrated system for sharing learning data with other AI agents to improve the overall quality of service. For example, different AI agents share learning data and improve services. The system also builds a platform for sharing the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, by sharing learning data, multiple AI agents simultaneously improve the quality of service. In this way, by sharing the results of continuous learning and improvement with other AI agents, the overall quality of service is improved.

[0046] The system can customize the specialized skills provided to specialize them for specific projects and challenges of a company. For example, the system builds a system that customizes the specialized skills provided by an AI agent to specialize them for specific projects and challenges of a company. For example, it provides a skill set required for a specific project. The system also customizes the specialized skills provided by the AI ​​agent for a specific challenge of a company and provides an optimal solution. For example, it provides expertise on a specific technical problem. The system also develops a customization system that enables the AI ​​agent to provide specialized skills specialized for specific projects and challenges of a company. For example, it adjusts the skill set according to the progress of the project. In this way, more effective support can be provided by customizing specialized skills to specialize them for specific projects and challenges of a company.

[0047] The system can dynamically change the skill sets it provides depending on the growth stage of a company and the market environment. For example, the system builds a system that dynamically changes the skill sets provided by an AI agent depending on the growth stage of a company and the market environment. For example, it provides skill sets that are necessary as a company grows. The system also dynamically changes the skill sets provided by the AI ​​agent depending on the company's market environment to provide optimal skills. For example, it provides skill sets that respond to market changes. The system also develops a customization system that enables the AI ​​agent to dynamically change the skill sets depending on the growth stage of a company and the market environment. For example, it adjusts the skill sets as the company grows. This makes it possible to provide optimal support to meet the needs of a company by dynamically changing the skill sets depending on the growth stage of a company and the market environment.

[0048] The system can apply the specialized skills it provides to different industries and applications, providing a generic skill set. For example, the system builds a system that applies specialized skills provided by an AI agent to different industries and applications, providing a generic skill set. For example, it can provide a skill set that combines the technical field with the consumer market. The system also applies specialized skills provided by an AI agent to different industries and applications, providing a generic skill set. For example, it can provide a skill set that applies medical field technology to everyday life. The system also builds an integrated system that applies specialized skills provided by an AI agent to different industries and applications. For example, it can provide a skill set that combines the needs of different industries. This makes it possible to provide a generic skill set by applying specialized skills to different industries and applications.

[0049] The system can apply customized specialized skills to other companies and projects to help solve common problems. For example, the system builds a system that applies customized specialized skills to other companies and projects to help solve common problems. For example, it provides a skill set for common problems in a specific industry. The system also applies customized specialized skills to other companies and projects to help solve common problems. For example, it provides a skill set for common problems in different companies. The system also builds an integrated system for applying customized specialized skills to other companies and projects. For example, it provides a skill set for common problems in different projects. In this way, the customized specialized skills can be applied to other companies and projects to help solve common problems.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The expertise providing unit can generate personalized answers based on the user's past question history. For example, an AI agent analyzes the user's past question history and generates personalized answers based on the user's interests and needs. For example, a user who has asked many marketing-related questions in the past can be provided with answers specialized in marketing. The expertise providing unit also identifies the user's knowledge level and field of expertise based on the user's past question history and provides appropriate expertise. For example, it provides basic knowledge for questions aimed at beginners and advanced knowledge for questions aimed at experts. The expertise providing unit also allows the AI ​​agent to learn the user's past question history and generate answers to new questions based on answers the user previously received. For example, it can provide more specific and detailed answers by referring to past answers. This makes it possible to provide more appropriate expertise by providing personalized answers based on the user's past question history.

[0052] The expert knowledge provision unit automatically incorporates the latest research papers and patent information, enabling it to always provide the latest information. For example, an AI agent regularly collects the latest research papers and patent information and updates its expert knowledge based on that information. For example, it provides answers that incorporate the latest technological trends and research results. The expert knowledge provision unit also allows the AI ​​agent to automatically analyze the latest research papers and patent information in a specific field, summarize the content, and provide it to the user. For example, it provides concise information on new technologies and methodologies. The expert knowledge provision unit also allows the AI ​​agent to generate answers to user questions based on the latest research papers and patent information. For example, it provides specific solutions and suggestions while citing the latest research results. This allows the AI ​​agent to always provide the latest expert knowledge by incorporating the latest research papers and patent information.

[0053] The expertise providing unit can make the expertise available through at least one different interface of a voice assistant or a chatbot. For example, the expertise provided by an AI agent can be made available through a voice assistant. For example, a user can input a question by voice and receive a response by voice. The expertise providing unit can also make the expertise provided by the AI ​​agent available through a chatbot. For example, a user can input a question in chat format and receive a response in real time. The expertise providing unit also builds an integrated system for making the expertise provided by the AI ​​agent available through different interfaces. For example, consistent responses are provided across multiple platforms, such as a voice assistant, a chatbot, and a web interface. This improves user convenience by providing expertise through different interfaces, such as a voice assistant or a chatbot.

[0054] The expertise provision unit can integrate expertise from different industries and provide cross-domain knowledge. For example, an AI agent can integrate expertise from different industries to provide cross-domain knowledge. For example, it can combine knowledge from the medical and technical fields to make suggestions for new medical technologies. The expertise provision unit can also build a database to integrate expertise from different industries, and the AI ​​agent can provide cross-domain knowledge based on that database. For example, it can combine knowledge from marketing and finance to propose effective marketing strategies. The expertise provision unit can also collect feedback from experts in different industries and provide cross-domain knowledge based on that information. For example, it can combine knowledge from technology development and legal affairs to make suggestions for solving technical and legal problems simultaneously. This makes it possible to provide a wider range of knowledge by integrating expertise from different industries.

[0055] The business efficiency proposal unit can build a predictive model based on past business data and propose future business efficiency improvements. For example, an AI agent analyzes past business data and builds a predictive model to propose future business efficiency improvements. For example, it identifies bottlenecks in business flows based on past data and proposes improvement measures. The business efficiency proposal unit also uses an AI agent to perform simulations for future business efficiency improvements based on past business data and proposes optimal business flows. For example, it makes proposals to optimize resource allocation and task priorities. The business efficiency proposal unit also uses an AI agent to learn from past business data and build a predictive model for future business efficiency improvements. For example, it proposes business process automation and optimal resource allocation. In this way, by building a predictive model based on past business data, it is possible to propose future business efficiency improvements.

[0056] The business efficiency proposal unit can run simulations of efficiency improvement plans to select the optimal business flow. For example, a system can be built that runs simulations of efficiency improvement plans proposed by an AI agent to select the optimal business flow. For example, multiple efficiency improvement plans can be simulated and the most effective plan selected. The business efficiency proposal unit can also use simulations to evaluate the feasibility of the efficiency improvement plans proposed by the AI ​​agent and select the optimal business flow. For example, it can simulate resource allocation and task scheduling. The business efficiency proposal unit can also run simulations of the efficiency improvement plans proposed by the AI ​​agent to identify areas for improvement in the business flow. For example, it can identify bottlenecks in the business process through simulation and propose improvement measures. In this way, the optimal business flow can be selected by running simulations of the efficiency improvement plans.

[0057] The Business Efficiency Proposal Department can apply the efficiency improvement proposals to different departments and projects, thereby achieving company-wide efficiency. For example, a system can be built to apply the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide efficiency. For example, work flows between departments can be integrated to achieve company-wide efficiency. The Business Efficiency Proposal Department can also apply the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide business efficiency. For example, it can make proposals to optimize resource allocation for each department. The Business Efficiency Proposal Department can also build an integrated system to apply the efficiency improvement proposals proposed by the AI ​​agent across the company. For example, it can integrate project management tools to achieve company-wide business efficiency. In this way, company-wide efficiency can be achieved by applying the efficiency improvement proposals to different departments and projects.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The Expertise Provider provides expertise in response to a company's questions and challenges. For example, if a company inputs a marketing question, the Generative AI analyzes the question and suggests an appropriate marketing strategy. Alternatively, if a company presents a financial challenge, the Generative AI can analyze the challenge and provide advice on financial analysis and budget management. Furthermore, if a company inputs a legal question, the Generative AI can analyze the question and provide appropriate legal advice. Step 2: The Business Efficiency Proposal Department analyzes business processes based on the expertise provided by the Expert Knowledge Providing Department and makes proposals for improving efficiency, such as optimizing business flow, optimizing resource allocation, and improving project management. Step 3: The Problem-Solving Support Department proposes solutions to specific problems based on the efficiency improvement proposals proposed by the Business Efficiency Proposal Department, such as technical troubleshooting, market analysis, and solutions to challenges in specific projects.

[0060] (Example 2) The AI-based specialized skill provision system according to an embodiment of the present invention is a system that provides specialized knowledge and skills that companies need, and supports improving business efficiency and problem solving. As a result, the AI-based specialized skill provision system enables companies that cannot hire experts due to budget constraints to utilize advanced specialized knowledge and skills to improve business efficiency and solve problems.

[0061] An AI-based specialized skill provision system according to an embodiment includes a specialized knowledge provision unit, a business efficiency improvement proposal unit, and a problem-solving support unit. The specialized knowledge provision unit provides specialized knowledge in response to a company's questions and challenges. For example, when a company inputs a marketing question, the specialized knowledge provision unit has a generation AI analyze the question and propose an appropriate marketing strategy. Furthermore, when a company submits a financial challenge, the specialized knowledge provision unit has a generation AI analyze the challenge and provide advice on financial analysis and budget management. Furthermore, when a company inputs a legal question, the specialized knowledge provision unit has a generation AI analyze the question and provide appropriate legal advice. The business efficiency improvement proposal unit analyzes business processes based on the specialized knowledge provided by the specialized knowledge provision unit and proposes efficiency improvements. For example, the business efficiency proposal unit analyzes a company's business flow, and the generation AI proposes workflow optimization. Furthermore, the business efficiency proposal unit can analyze a company's resource allocation, and the generation AI proposes optimal resource allocation. Furthermore, the business efficiency proposal unit can analyze a company's project management, and the generation AI proposes improvements to the project management. The problem-solving support unit proposes solutions to specific problems based on the efficiency proposals proposed by the business efficiency proposal unit. For example, if a company needs technical troubleshooting, the problem-solving support unit uses the generation AI to analyze the problem and propose a specific solution. If a company needs market analysis, the problem-solving support unit uses the generation AI to analyze market data and provide a competitive analysis and market trend forecast. When a company presents a challenge it faces in a specific project, the problem-solving support unit uses the generation AI to analyze the challenge and propose an optimal solution. In this way, the AI-based specialized skill provision system according to the embodiment can provide specialized knowledge for a company's questions and challenges, helping to streamline business processes and solve specific problems. For example, a company can receive quick and accurate advice through the AI ​​agent, thereby improving business efficiency and solving problems. Furthermore, a company can utilize specialized knowledge through the AI ​​agent to support business improvement and growth.

[0062] The expertise providing unit can generate personalized answers based on the user's past question history. In this case, for example, an AI agent analyzes the user's past question history and generates personalized answers based on the user's interests and needs. For example, a user who has asked many marketing-related questions in the past can be provided with answers specialized in marketing. In addition, the expertise providing unit identifies the user's knowledge level and field of expertise based on the user's past question history and provides appropriate expertise. For example, basic knowledge is provided for questions aimed at beginners, and advanced knowledge is provided for questions aimed at experts. In addition, the expertise providing unit allows the AI ​​agent to learn the user's past question history and generate answers to new questions based on answers the user previously received. For example, the AI ​​agent can provide more specific and detailed answers by referring to past answers. This makes it possible to provide more appropriate expertise by providing personalized answers based on the user's past question history.

[0063] The expert knowledge provision unit automatically incorporates the latest research papers and patent information, allowing it to always provide the latest information. For example, the expert knowledge provision unit uses an AI agent to regularly collect the latest research papers and patent information and update its expert knowledge based on that information. For example, it provides answers that incorporate the latest technological trends and research results. The expert knowledge provision unit also uses an AI agent to automatically analyze the latest research papers and patent information in a specific field, summarize the content, and provide it to the user. For example, it provides concise information on new technologies and methodologies. The expert knowledge provision unit also uses an AI agent to generate answers to user questions based on the latest research papers and patent information. For example, it provides specific solutions and suggestions while citing the latest research results. This allows the system to always provide the latest expert knowledge by incorporating the latest research papers and patent information.

[0064] The expert knowledge providing unit can use the emotion estimation function to provide expert knowledge in a tone and expression that corresponds to the user's emotional state. For example, the expert knowledge providing unit uses an AI agent to analyze the user's emotional state in real time and provide an answer in a tone and expression that corresponds to the emotion. For example, if the user is feeling stressed, an answer is provided in a gentle tone. The expert knowledge providing unit also uses the emotion estimation function to adjust the method of providing expert knowledge according to the user's emotional state. For example, if the user is excited, a concise answer is provided without detailed explanations. The expert knowledge providing unit also uses an AI agent to analyze the user's emotional state and provide expert knowledge using expressions and wording that correspond to the emotion. For example, if the user is feeling anxious, an answer is provided using expressions that give a sense of security. In this way, providing expert knowledge in a tone and expression that corresponds to the user's emotional state improves user satisfaction.

[0065] The expertise providing unit can make the expertise available through at least one different interface of a voice assistant or a chatbot. The expertise providing unit, for example, makes the expertise provided by an AI agent available through a voice assistant. For example, a user can input a question by voice and receive an answer by voice. The expertise providing unit also makes the expertise provided by the AI ​​agent available through a chatbot. For example, a user can input a question in chat format and receive an answer in real time. The expertise providing unit also builds an integrated system for making the expertise provided by the AI ​​agent available through different interfaces. For example, consistent answers are provided across multiple platforms, such as a voice assistant, a chatbot, and a web interface. This improves user convenience by providing expertise through different interfaces, such as a voice assistant or a chatbot.

[0066] The expertise provision unit can integrate expertise from different industries and provide cross-domain knowledge. For example, an AI agent can integrate expertise from different industries to provide cross-domain knowledge. For example, it can combine knowledge from the medical and technical fields to make suggestions for new medical technologies. The expertise provision unit can also build a database for integrating expertise from different industries, and the AI ​​agent can provide cross-domain knowledge based on that database. For example, it can combine knowledge from marketing and finance to propose effective marketing strategies. The expertise provision unit can also collect feedback from experts in different industries and provide cross-domain knowledge based on that information. For example, it can combine knowledge from technology development and legal affairs to make suggestions for solving technical and legal problems simultaneously. This makes it possible to provide a wider range of knowledge by integrating expertise from different industries.

[0067] The expert knowledge providing unit can use the emotion estimation function to provide expert knowledge specialized in the field in which the user is most interested. For example, the expert knowledge providing unit uses the emotion estimation function to identify the field in which the user is most interested and provide expert knowledge specialized in that field. For example, if the user shows a strong interest in technological development, detailed information on technological development is provided. The expert knowledge providing unit also analyzes the user's emotional state and builds a system to provide expert knowledge specialized in the field of interest. For example, if the user is interested in marketing, the latest trends and technologies related to marketing are provided. The expert knowledge providing unit also uses the emotion estimation function to identify the field in which the user is most interested in real time and provide expert knowledge specialized in that field. For example, if the user is interested in financial analysis, specific advice and suggestions related to financial analysis are provided. In this way, by providing expert knowledge specialized in the field in which the user is most interested, user satisfaction is improved.

[0068] The business efficiency proposal unit can build a predictive model based on past business data and propose future business efficiency improvements. For example, the business efficiency proposal unit proposes future business efficiency improvements by having an AI agent analyze past business data and build a predictive model. For example, it identifies bottlenecks in business flows based on past data and proposes improvement measures. The business efficiency proposal unit also has an AI agent run a simulation for future business efficiency improvements based on past business data and propose an optimal business flow. For example, it makes proposals to optimize resource allocation and task priorities. The business efficiency proposal unit also has an AI agent learn from past business data and build a predictive model for future business efficiency improvements. For example, it proposes business process automation and optimal resource allocation. In this way, by building a predictive model based on past business data, it is possible to propose future business efficiency improvements.

[0069] The business efficiency proposal unit can perform simulations of efficiency improvement plans and select the optimal business flow. The business efficiency proposal unit, for example, builds a system that performs simulations of efficiency improvement plans proposed by an AI agent and selects the optimal business flow. For example, it simulates multiple efficiency improvement plans and selects the most effective plan. The business efficiency proposal unit also evaluates the feasibility of the efficiency improvement plans proposed by the AI ​​agent through simulation and selects the optimal business flow. For example, it simulates resource allocation and task scheduling. The business efficiency proposal unit also performs simulations of the efficiency improvement plans proposed by the AI ​​agent and identifies areas for improvement in the business flow. For example, it identifies bottlenecks in the business process through simulation and proposes improvement measures. In this way, the optimal business flow can be selected by performing simulations of the efficiency improvement plans.

[0070] The work efficiency proposal unit can use the emotion estimation function to analyze the stress level of employees and make work efficiency improvement proposals to reduce stress. The work efficiency proposal unit, for example, uses the emotion estimation function to analyze the stress level of employees and make work efficiency proposals to reduce stress. For example, it identifies tasks that cause high stress and makes proposals to reduce the burden of those tasks. The work efficiency proposal unit also builds a system that analyzes the emotional state of employees in real time and makes work efficiency proposals according to their stress levels. For example, it makes proposals to adjust task priorities during periods of high stress. The work efficiency proposal unit also analyzes the stress level of employees based on the emotion estimation data and makes proposals to improve work flows to reduce stress. For example, it identifies work processes that cause high stress and makes proposals to improve those processes. In this way, by analyzing the stress level of employees and making work efficiency proposals to reduce stress, the health and work efficiency of employees are improved.

[0071] The Business Efficiency Proposal Department can apply the efficiency improvement proposals to different departments and projects, thereby achieving company-wide efficiency. For example, the Business Efficiency Proposal Department builds a system that applies the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide efficiency. For example, it integrates business flows between departments, thereby achieving company-wide efficiency. The Business Efficiency Proposal Department also applies the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide business efficiency. For example, it makes proposals to optimize resource allocation for each department. The Business Efficiency Proposal Department also builds an integrated system to apply the efficiency improvement proposals proposed by the AI ​​agent across the company. For example, it integrates project management tools, thereby achieving company-wide business efficiency. In this way, company-wide efficiency can be achieved by applying the efficiency proposals to different departments and projects.

[0072] The business efficiency proposal department can compare business efficiency proposals with best practices from other companies and industries and make optimal proposals. For example, the business efficiency proposal department builds a system that compares business efficiency proposals proposed by an AI agent with best practices from other companies and industries and makes optimal proposals. For example, it makes proposals that incorporate industry-standard efficiency methods. The business efficiency proposal department also evaluates business efficiency proposals proposed by the AI ​​agent based on best practices from other companies and industries and makes optimal proposals. For example, it makes proposals that refer to successful cases from competitors. The business efficiency proposal department also uses the AI ​​agent to collect best practices from other companies and industries and makes business efficiency proposals based on that information. For example, it proposes efficiency proposals that incorporate the latest industry trends. This makes it possible to make optimal business efficiency proposals by comparing with best practices from other companies and industries.

[0073] The business efficiency proposal unit can use the emotion estimation function to make business efficiency improvement proposals to increase employee motivation. The business efficiency proposal unit, for example, uses the emotion estimation function to make business efficiency proposals to increase employee motivation. For example, it proposes task reallocation or improvements to the work environment for employees whose motivation is declining. The business efficiency proposal unit also builds a system that analyzes employees' emotional states in real time and makes business efficiency proposals to increase motivation. For example, it proposes improvements to work flows that will increase motivation. The business efficiency proposal unit also makes business efficiency proposals to increase employee motivation based on the emotion estimation data. For example, it proposes task priorities and resource allocations that will increase motivation. In this way, business efficiency proposals to increase employee motivation are made, thereby improving employee performance.

[0074] The problem-solving support unit can propose optimal solutions based on past solutions and their results. For example, the problem-solving support unit uses an AI agent to analyze past problem-solving solutions and their results and propose optimal solutions. For example, it proposes solutions to similar problems based on solutions that have been successful in the past. The problem-solving support unit also builds a system in which the AI ​​agent proposes optimal solutions based on past problem-solving data. For example, it learns from past data and proposes the most effective solution. The problem-solving support unit also uses an AI agent to analyze past solutions and their results and propose optimal solutions with low risk. For example, it proposes solutions to avoid past failures. In this way, the accuracy of problem-solving is improved by proposing optimal solutions based on past solutions and their results.

[0075] The problem-solving support unit can perform risk assessments on solutions and prioritize low-risk solutions. The problem-solving support unit, for example, performs risk assessments on solutions proposed by an AI agent and builds a system that prioritizes low-risk solutions. For example, it quantifies the risk of solutions using a risk assessment model. The problem-solving support unit also determines the priority of solutions proposed by the AI ​​agent based on the risk assessment. For example, it prioritizes solutions with low risk. The problem-solving support unit also performs risk assessments on solutions proposed by the AI ​​agent and selects low-risk solutions. For example, it sets solution selection criteria based on the risk assessment results. In this way, risk assessments are performed and low-risk solutions are prioritized, thereby improving the safety of problem solving.

[0076] The problem-solving support unit can use the emotion estimation function to propose solutions to alleviate the user's anxiety and concerns. The problem-solving support unit, for example, uses the emotion estimation function to propose solutions to alleviate the user's anxiety and concerns. For example, if the user is feeling anxious, it proposes a solution that gives a sense of security. The problem-solving support unit also builds a system that analyzes the user's emotional state in real time and proposes solutions to alleviate the anxiety and concerns. For example, it proposes specific solutions that will make the user feel secure. The problem-solving support unit also proposes solutions to alleviate the user's anxiety and concerns based on the emotion estimation data. For example, it makes suggestions to provide support or resources that will make the user feel secure. In this way, by proposing solutions to alleviate the user's anxiety and concerns, the user's sense of security is improved.

[0077] The problem-solving support unit can apply a solution to different problems and challenges and provide a general-purpose solution. For example, the problem-solving support unit builds a system that applies a solution proposed by an AI agent to different problems and challenges and provides a general-purpose solution. For example, it applies a solution to a technical problem to other business processes. The problem-solving support unit also applies a solution proposed by an AI agent to different problems and challenges and provides a general-purpose solution. For example, it applies a solution to a marketing problem to a financial problem. The problem-solving support unit also builds an integrated system that applies the solution proposed by the AI ​​agent to different problems and challenges. For example, it provides a common solution for different business processes. In this way, a general-purpose solution can be provided by applying the proposed solution to different problems and challenges.

[0078] The problem-solving support unit can compare problem-solving proposals with success stories from other companies and industries to provide optimal solutions. For example, the problem-solving support unit compares problem-solving proposals made by an AI agent with success stories from other companies and industries to build a system that provides optimal solutions. For example, it makes proposals that incorporate industry-standard solutions. The problem-solving support unit also evaluates problem-solving proposals made by an AI agent based on success stories from other companies and industries to provide optimal solutions. For example, it makes proposals that refer to success stories from competitors. The problem-solving support unit also collects success stories from other companies and industries and makes problem-solving proposals based on that information. For example, it proposes solutions that incorporate the latest trends in the industry. This makes it possible to provide optimal solutions by comparing with success stories from other companies and industries.

[0079] The problem-solving support unit can use the emotion estimation function to propose a solution that gives the user the most peace of mind. The problem-solving support unit, for example, uses the emotion estimation function to propose a solution that gives the user the most peace of mind. For example, it provides a specific solution that gives the user a sense of security. The problem-solving support unit also analyzes the user's emotional state in real time and builds a system that proposes solutions that give the user a sense of security. For example, it makes suggestions to provide support and resources that will give the user a sense of security. The problem-solving support unit also proposes a solution that gives the user the most peace of mind based on the emotion estimation data. For example, it provides specific advice and suggestions that will give the user a sense of security. In this way, by proposing a solution that gives the user the most peace of mind, the user's sense of security is improved.

[0080] The system can collect feedback on the services it provides in real time and learn and improve instantly. For example, the system collects feedback on the services it provides from an AI agent in real time, and builds a system that learns and improves instantly based on that data. For example, the quality of the service is improved based on user feedback. The system also identifies areas for improvement in the services it provides from the AI ​​agent based on the feedback collected in real time, and learns and improves instantly. For example, it improves the service by reflecting user opinions. The system also analyzes feedback on the services it provides from the AI ​​agent in real time, and develops a system that learns and improves instantly. For example, it improves the quality of the service based on the feedback. In this way, the quality of the service is improved by collecting feedback in real time and learning and improving instantly.

[0081] The system can quantitatively evaluate the effectiveness of proposals and solutions provided and learn based on the results. For example, the system quantitatively evaluates the effectiveness of proposals and solutions provided by an AI agent and builds a system that learns based on the results. For example, the results after the proposal is implemented are evaluated numerically and used as learning data. The system also develops an evaluation model for quantitatively evaluating the effectiveness of proposals and solutions, and the AI ​​agent learns based on the results. For example, it evaluates the business efficiency and results after the proposal is implemented. The system also develops a system that quantitatively evaluates the effectiveness of proposals and solutions provided by an AI agent and learns based on that data. For example, it evaluates the results after the proposal is implemented numerically and reflects them in future proposals. In this way, the effectiveness of proposals and solutions can be quantitatively evaluated and learning based on the results can improve the accuracy of future proposals and solutions.

[0082] The system can use the emotion estimation function to analyze user satisfaction and learn to provide a service with high satisfaction. For example, the system uses the emotion estimation function to build a system that analyzes user satisfaction and learns to provide a service with high satisfaction. For example, the system improves the quality of the service based on the user's emotion score. The system also analyzes the user's emotional state in real time and learns to provide a service with high satisfaction. For example, it identifies areas for improvement in the service based on the user's emotion data. The system also develops a system that analyzes user satisfaction based on the emotion estimation data and learns to provide a service with high satisfaction. For example, the system improves the quality of the service based on the user's emotion score. In this way, the system analyzes user satisfaction and learns to provide a service with high satisfaction, thereby improving the quality of the service.

[0083] The system can collect learning data from different industries and fields, and improve services based on a wide range of knowledge. For example, the system can collect data for an AI agent to learn from different industries and fields, and build a system to improve services based on a wide range of knowledge. For example, data from different industries can be integrated to improve service quality. The system can also collect data from different industries and fields, and the AI ​​agent can learn from that data to improve services. For example, services can be improved by incorporating best practices from different industries. The system can also develop a system in which an AI agent collects data from different industries and fields, and improves services based on that information. For example, services can be improved by incorporating trends from different industries. In this way, by collecting data from different industries and fields, services can be improved based on a wide range of knowledge.

[0084] The system can share the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, the system builds a system for sharing the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, by sharing learning data, multiple AI agents simultaneously improve the quality of service. The system also develops an integrated system for sharing learning data with other AI agents to improve the overall quality of service. For example, different AI agents share learning data and improve services. The system also builds a platform for sharing the results of continuous learning and improvement with other AI agents to improve the overall quality of service. For example, by sharing learning data, multiple AI agents simultaneously improve the quality of service. In this way, by sharing the results of continuous learning and improvement with other AI agents, the overall quality of service is improved.

[0085] The system can use the emotion estimation function to emotionally analyze user feedback and make improvements based on the emotions. For example, the system uses the emotion estimation function to emotionally analyze user feedback and build a system that improves services based on the results. For example, the system improves the quality of services based on the user's emotion score. The system also analyzes the user's emotional state in real time and improves services based on emotions. For example, it identifies areas for improvement in services based on the user's emotion data. The system also develops a system that emotionally analyzes user feedback based on emotion estimation data and improves services based on emotions. For example, the system improves the quality of services based on the user's emotion score. In this way, the quality of services is improved by emotionally analyzing user feedback and making improvements based on emotions.

[0086] The system can customize the specialized skills provided to specialize them for specific projects and challenges of a company. For example, the system builds a system that customizes the specialized skills provided by an AI agent to specialize them for specific projects and challenges of a company. For example, it provides a skill set required for a specific project. The system also customizes the specialized skills provided by the AI ​​agent for a specific challenge of a company and provides an optimal solution. For example, it provides expertise on a specific technical problem. The system also develops a customization system that enables the AI ​​agent to provide specialized skills specialized for specific projects and challenges of a company. For example, it adjusts the skill set according to the progress of the project. In this way, more effective support can be provided by customizing specialized skills to specialize them for specific projects and challenges of a company.

[0087] The system can dynamically change the skill sets it provides depending on the growth stage of a company and the market environment. For example, the system builds a system that dynamically changes the skill sets provided by an AI agent depending on the growth stage of a company and the market environment. For example, it provides skill sets that are necessary as a company grows. The system also dynamically changes the skill sets provided by the AI ​​agent depending on the company's market environment to provide optimal skills. For example, it provides skill sets that respond to market changes. The system also develops a customization system that enables the AI ​​agent to dynamically change the skill sets depending on the growth stage of a company and the market environment. For example, it adjusts the skill sets as the company grows. This makes it possible to provide optimal support to meet the needs of a company by dynamically changing the skill sets depending on the growth stage of a company and the market environment.

[0088] The system can use the emotion estimation function to perform customization according to the user's needs and expectations. For example, the system uses the emotion estimation function to build a system that performs customization according to the user's needs and expectations. For example, it provides an optimal skill set based on the user's emotion score. The system also analyzes the user's emotional state in real time and performs customization according to the needs and expectations. For example, it adjusts the skill set based on the user's emotion data. The system also develops a system that performs customization according to the user's needs and expectations based on the emotion estimation data. For example, it provides a skill set based on the user's emotion score. In this way, customization according to the user's needs and expectations improves user satisfaction.

[0089] The system can apply the specialized skills it provides to different industries and applications, providing a generic skill set. For example, the system builds a system that applies specialized skills provided by an AI agent to different industries and applications, providing a generic skill set. For example, it can provide a skill set that combines the technical field with the consumer market. The system also applies specialized skills provided by an AI agent to different industries and applications, providing a generic skill set. For example, it can provide a skill set that applies medical field technology to everyday life. The system also builds an integrated system that applies specialized skills provided by an AI agent to different industries and applications. For example, it can provide a skill set that combines the needs of different industries. This makes it possible to provide a generic skill set by applying specialized skills to different industries and applications.

[0090] The system can apply customized specialized skills to other companies and projects to help solve common problems. For example, the system builds a system that applies customized specialized skills to other companies and projects to help solve common problems. For example, it provides a skill set for common problems in a specific industry. The system also applies customized specialized skills to other companies and projects to help solve common problems. For example, it provides a skill set for common problems in different companies. The system also builds an integrated system for applying customized specialized skills to other companies and projects. For example, it provides a skill set for common problems in different projects. In this way, the customized specialized skills can be applied to other companies and projects to help solve common problems.

[0091] The system can use the emotion estimation function to perform skill customization based on the user's emotions and provide an optimal skill set. For example, the system uses the emotion estimation function to perform skill customization based on the user's emotions and build a system that provides an optimal skill set. For example, the system adjusts the skill set based on the user's emotion score. The system also analyzes the user's emotional state in real time and performs skill customization based on emotions. For example, the system provides a skill set based on the user's emotion data. The system also develops a system that performs skill customization based on the user's emotions based on the emotion estimation data and provides an optimal skill set. For example, the system provides a skill set based on the user's emotion score. In this way, the optimal skill set can be provided by performing skill customization based on the user's emotions.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The expertise providing unit can generate personalized answers based on the user's past question history. For example, an AI agent analyzes the user's past question history and generates personalized answers based on the user's interests and needs. For example, a user who has asked many marketing-related questions in the past can be provided with answers specialized in marketing. The expertise providing unit also identifies the user's knowledge level and field of expertise based on the user's past question history and provides appropriate expertise. For example, it provides basic knowledge for questions aimed at beginners and advanced knowledge for questions aimed at experts. The expertise providing unit also allows the AI ​​agent to learn the user's past question history and generate answers to new questions based on answers the user previously received. For example, it can provide more specific and detailed answers by referring to past answers. This makes it possible to provide more appropriate expertise by providing personalized answers based on the user's past question history.

[0094] The expert knowledge provision unit automatically incorporates the latest research papers and patent information, enabling it to always provide the latest information. For example, an AI agent regularly collects the latest research papers and patent information and updates its expert knowledge based on that information. For example, it provides answers that incorporate the latest technological trends and research results. The expert knowledge provision unit also allows the AI ​​agent to automatically analyze the latest research papers and patent information in a specific field, summarize the content, and provide it to the user. For example, it provides concise information on new technologies and methodologies. The expert knowledge provision unit also allows the AI ​​agent to generate answers to user questions based on the latest research papers and patent information. For example, it provides specific solutions and suggestions while citing the latest research results. This allows the AI ​​agent to always provide the latest expert knowledge by incorporating the latest research papers and patent information.

[0095] The expert knowledge providing unit can use the emotion estimation function to provide expert knowledge in a tone and expression that corresponds to the user's emotional state. For example, the AI ​​agent analyzes the user's emotional state in real time and provides answers in a tone and expression that corresponds to the emotion. For example, if the user is feeling stressed, the answer is provided in a gentle tone. The expert knowledge providing unit also uses the emotion estimation function to adjust the way expert knowledge is provided according to the user's emotional state. For example, if the user is excited, the answer is provided in a concise manner, omitting detailed explanations. The expert knowledge providing unit also uses the AI ​​agent to analyze the user's emotional state and provide expert knowledge using expressions and wording that correspond to the emotion. For example, if the user is feeling anxious, the answer is provided in expressions that give a sense of security. In this way, expert knowledge is provided in a tone and expression that corresponds to the user's emotional state, thereby improving user satisfaction.

[0096] The expertise providing unit can make the expertise available through at least one different interface of a voice assistant or a chatbot. For example, the expertise provided by an AI agent can be made available through a voice assistant. For example, a user can input a question by voice and receive a response by voice. The expertise providing unit can also make the expertise provided by the AI ​​agent available through a chatbot. For example, a user can input a question in chat format and receive a response in real time. The expertise providing unit also builds an integrated system for making the expertise provided by the AI ​​agent available through different interfaces. For example, consistent responses are provided across multiple platforms, such as a voice assistant, a chatbot, and a web interface. This improves user convenience by providing expertise through different interfaces, such as a voice assistant or a chatbot.

[0097] The expertise provision unit can integrate expertise from different industries and provide cross-domain knowledge. For example, an AI agent can integrate expertise from different industries to provide cross-domain knowledge. For example, it can combine knowledge from the medical and technical fields to make suggestions for new medical technologies. The expertise provision unit can also build a database to integrate expertise from different industries, and the AI ​​agent can provide cross-domain knowledge based on that database. For example, it can combine knowledge from marketing and finance to propose effective marketing strategies. The expertise provision unit can also collect feedback from experts in different industries and provide cross-domain knowledge based on that information. For example, it can combine knowledge from technology development and legal affairs to make suggestions for solving technical and legal problems simultaneously. This makes it possible to provide a wider range of knowledge by integrating expertise from different industries.

[0098] The expert knowledge providing unit can use the emotion estimation function to provide expert knowledge specialized in the field in which the user is most interested. For example, the emotion estimation function can be used to identify the field in which the user is most interested and provide expert knowledge specialized in that field. For example, if the user shows a strong interest in technological development, detailed information on technological development can be provided. The expert knowledge providing unit can also analyze the user's emotional state and build a system to provide expert knowledge specialized in the field in which the user is interested. For example, if the user is interested in marketing, the latest trends and technologies related to marketing can be provided. The expert knowledge providing unit can also use the emotion estimation function to identify the field in which the user is most interested in real time and provide expert knowledge specialized in that field. For example, if the user is interested in financial analysis, specific advice and suggestions related to financial analysis can be provided. In this way, providing expert knowledge specialized in the field in which the user is most interested improves user satisfaction.

[0099] The business efficiency proposal unit can build a predictive model based on past business data and propose future business efficiency improvements. For example, an AI agent analyzes past business data and builds a predictive model to propose future business efficiency improvements. For example, it identifies bottlenecks in business flows based on past data and proposes improvement measures. The business efficiency proposal unit also uses an AI agent to perform simulations for future business efficiency improvements based on past business data and proposes optimal business flows. For example, it makes proposals to optimize resource allocation and task priorities. The business efficiency proposal unit also uses an AI agent to learn from past business data and build a predictive model for future business efficiency improvements. For example, it proposes business process automation and optimal resource allocation. In this way, by building a predictive model based on past business data, it is possible to propose future business efficiency improvements.

[0100] The business efficiency proposal unit can run simulations of efficiency improvement plans to select the optimal business flow. For example, a system can be built that runs simulations of efficiency improvement plans proposed by an AI agent to select the optimal business flow. For example, multiple efficiency improvement plans can be simulated and the most effective plan selected. The business efficiency proposal unit can also use simulations to evaluate the feasibility of the efficiency improvement plans proposed by the AI ​​agent and select the optimal business flow. For example, it can simulate resource allocation and task scheduling. The business efficiency proposal unit can also run simulations of the efficiency improvement plans proposed by the AI ​​agent to identify areas for improvement in the business flow. For example, it can identify bottlenecks in the business process through simulation and propose improvement measures. In this way, the optimal business flow can be selected by running simulations of the efficiency improvement plans.

[0101] The work efficiency proposal unit can use the emotion estimation function to analyze the stress levels of employees and make work efficiency improvement proposals to reduce stress. For example, the emotion estimation function can be used to analyze the stress levels of employees and make work efficiency improvement proposals to reduce stress. For example, the emotion estimation function can be used to identify tasks that cause high stress and make proposals to reduce the burden of those tasks. The work efficiency proposal unit can also build a system that analyzes the emotional states of employees in real time and makes work efficiency proposals based on their stress levels. For example, it can make proposals to adjust task priorities during periods of high stress. The work efficiency proposal unit can also analyze the stress levels of employees based on the emotion estimation data and make proposals to improve work flows to reduce stress. For example, it can identify work processes that cause high stress and make proposals to improve those processes. In this way, the stress levels of employees can be analyzed and work efficiency proposals made to reduce stress, thereby improving employee health and work efficiency.

[0102] The Business Efficiency Proposal Department can apply the efficiency improvement proposals to different departments and projects, thereby achieving company-wide efficiency. For example, a system can be built to apply the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide efficiency. For example, work flows between departments can be integrated to achieve company-wide efficiency. The Business Efficiency Proposal Department can also apply the efficiency improvement proposals proposed by the AI ​​agent to different departments and projects, thereby achieving company-wide business efficiency. For example, it can make proposals to optimize resource allocation for each department. The Business Efficiency Proposal Department can also build an integrated system to apply the efficiency improvement proposals proposed by the AI ​​agent across the company. For example, it can integrate project management tools to achieve company-wide business efficiency. In this way, company-wide efficiency can be achieved by applying the efficiency improvement proposals to different departments and projects.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The Expertise Provider provides expertise in response to a company's questions and challenges. For example, if a company inputs a marketing question, the Generative AI analyzes the question and suggests an appropriate marketing strategy. Alternatively, if a company presents a financial challenge, the Generative AI can analyze the challenge and provide advice on financial analysis and budget management. Furthermore, if a company inputs a legal question, the Generative AI can analyze the question and provide appropriate legal advice. Step 2: The Business Efficiency Proposal Department analyzes business processes based on the expertise provided by the Expert Knowledge Providing Department and makes proposals for improving efficiency, such as optimizing business flow, optimizing resource allocation, and improving project management. Step 3: The Problem-Solving Support Department proposes solutions to specific problems based on the efficiency improvement proposals proposed by the Business Efficiency Proposal Department, such as technical troubleshooting, market analysis, and solutions to challenges in specific projects.

[0105] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0156] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0157] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0162] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0163] 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.

[0164] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0167] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0169] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0170] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0171] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0172] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The Expertise Department provides expertise to answer questions and issues faced by companies. a business efficiency suggestion unit that analyzes business processes based on the expert knowledge provided by the expert knowledge providing unit and proposes improvements to efficiency; a problem-solving support unit that proposes solutions to specific problems based on the efficiency improvement proposals proposed by the business efficiency proposal unit; A system characterized by:

2. The expertise providing unit Generate personalized answers based on the user's past questions 2. The system of claim 1.

3. The expertise providing unit Automatically retrieves the latest research papers and patent information to always provide the latest information 2. The system of claim 1.

4. The expertise providing unit Deliver expertise in a tone and expression that reflects the user's emotional state 2. The system of claim 1.

5. The expertise providing unit Available in at least one different interface: voice assistant or chatbot 2. The system of claim 1.

6. The expertise providing unit Integrate expertise from different industries and provide cross-domain knowledge 2. The system of claim 1.

Images