system

Abstract

The system according to the embodiment is intended to efficiently convey knowledges and experiences of the Radio Law and the interpretation of law to new members.SOLUTION: A system according to an embodiment includes a knowledge storage unit, an AIBot generation unit, and a question answering unit. The knowledge-accumulating unit accumulates knowledges and experiences of the Radio Law and the interpretation of law. The AIBot generation unit generates an AIBot based on the knowledge accumulated by the knowledge accumulation unit. The question answering unit causes the AIBots generated by the AIBot-generating unit to provide appropriate answers to the new member's questions.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] With conventional technology, it was difficult to convey knowledge and experience of the Radio Law and its interpretation to new members in a short period of time, which posed the risk of violating the law and increased unnecessary man-hours.

[0005] The system according to the embodiment aims to efficiently impart knowledge and experience of the Radio Law and legal interpretation to new members. [Means for solving the problem]

[0006] The system according to the embodiment includes a knowledge accumulation unit, an AI Bot generation unit, and a question and answer unit. The knowledge accumulation unit accumulates knowledge and experience of the Radio Law and legal interpretations. The AI ​​Bot generation unit generates an AI Bot based on the knowledge accumulated by the knowledge accumulation unit. The question and answer unit allows the AI ​​Bot generated by the AI ​​Bot generation unit to provide appropriate answers to questions from new members. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently impart knowledge and experience of the Radio Law and legal interpretation to new members. [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 knowledge transfer system according to the embodiment of the present invention is a system that accumulates knowledge and experience of the Radio Law in AI and provides appropriate answers to questions from new members. As a result, the knowledge transfer system can transfer knowledge from the radio department and improve work efficiency.

[0029] The knowledge transfer system according to the embodiment includes a knowledge accumulation unit, an AI bot generation unit, and a question-answering unit. The knowledge accumulation unit accumulates knowledge and experience of the Radio Act and legal interpretations. For example, the knowledge accumulation unit trains the generation AI on provisions of the Radio Act and documents related to legal interpretations by the Ministry of Internal Affairs and Communications. The knowledge accumulation unit can also train the generation AI on past court cases and actual business cases. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. The AI ​​bot generation unit generates an AI bot based on the knowledge accumulated by the knowledge accumulation unit. For example, the AI ​​bot generation unit uses the generation AI to create an AI bot that provides appropriate answers to questions related to the Radio Act. The AI ​​bot generation unit can also learn users' past question history and generate an AI bot that provides answers optimized for individual users. For example, past questions and their answers are imported into a database, and the generation AI analyzes them. The question-answering unit causes the AI ​​bot generated by the AI ​​bot generation unit to provide appropriate answers to questions from new members. For example, in response to a question such as "Please tell me about the application procedure for a radio station license," the question answering unit may respond with, "The application procedure for a radio station license is carried out according to the following steps." The question answering unit may also use its emotion estimation function to analyze a user's emotional response to legal interpretations and provide information in a format that is easy for the user to understand. For example, the system may analyze a user's facial expressions and voice to measure their level of understanding and emotional response. This allows the knowledge transfer system according to the embodiment to transfer knowledge in the radio department and improve work efficiency. For example, this allows new members to quickly learn their work, reduces the risk of legal violations, and prevents unnecessary increases in labor hours and costs. This improves the work efficiency of the entire radio department and promotes organizational revitalization.

[0030] The knowledge accumulation unit can learn from past legal precedents and business cases in addition to the provisions of the Radio Law and documents related to legal interpretations. For example, the knowledge accumulation unit has the generation AI learn from past legal precedents in addition to the provisions of the Radio Law and documents related to legal interpretations. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn from actual business cases. For example, radio station license application procedures and cases of legal violations are recorded in detail, and the generation AI generates answers based on these. The knowledge accumulation unit also has the generation AI learn from specialized books and papers related to the Radio Law. For example, commentaries and academic papers on the Radio Law are imported into a database, and the generation AI analyzes them. This allows the knowledge accumulation unit to accumulate more practical knowledge and provide appropriate answers.

[0031] The knowledge accumulation unit can also learn international laws and regulations related to radio laws. For example, the knowledge accumulation unit has the generation AI learn international radio law regulations. For example, it imports ITU (International Telecommunication Union) regulations and radio laws of each country into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn documents related to international legal interpretation. For example, it imports minutes of international conferences and legal interpretation guidelines from each country into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn international cases in order to provide legal interpretations from a global perspective. For example, it imports cases of international legal violations and their countermeasures into a database, and the generation AI analyzes them. This allows the knowledge accumulation unit to provide legal interpretations from a global perspective.

[0032] The knowledge accumulation unit can also learn related laws and regulations other than the Radio Law. For example, the knowledge accumulation unit has the generation AI learn documents related to the Communications Law. For example, the provisions and interpretation guidelines of the Communications Law are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn documents related to the Information Protection Law. For example, the provisions and interpretation guidelines of the Information Protection Law are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn other laws and regulations related to the Radio Law, and provides a comprehensive interpretation of the laws and regulations. For example, the knowledge accumulation unit analyzes the interrelationships between the Radio Law, the Communications Law, and the Information Protection Law, and provides a comprehensive interpretation. This enables the knowledge accumulation unit to provide a comprehensive interpretation of the laws and regulations.

[0033] The question and answering unit can provide knowledge about the Radio Law as visual notes and infographics. For example, the question and answering unit provides the provisions and interpretations of the Radio Law as visual notes. For example, important points can be shown with diagrams and icons to make them easier to understand visually. The question and answering unit can also create infographics about the Radio Law to provide information visually. For example, it can illustrate the flow and procedures of laws and regulations. The question and answering unit can also train a generation AI to create visual notes and infographics, providing information in a format that is easy for users to understand visually. For example, it can present related visual materials in response to a user's question. This allows the question and answering unit to provide information in a format that is easy for users to understand visually.

[0034] The AI ​​Bot generation unit can learn the user's past question history and provide answers optimized for each individual user. For example, the AI ​​Bot generation unit makes the AI ​​Bot learn the user's past question history. For example, past questions and their answers are imported into a database, and the generation AI analyzes them. The AI ​​Bot generation unit also generates answers based on the user's question history to provide answers optimized for each individual user. For example, it provides related information based on the content of past questions. The AI ​​Bot generation unit also makes the AI ​​Bot provide answers optimized for each individual user based on the user's question history. For example, it analyzes the user's question patterns and generates optimal answers. This allows the AI ​​Bot generation unit to provide answers optimized for each individual user.

[0035] The question answering unit can collect feedback from users and continuously improve the accuracy of answers. For example, the question answering unit collects feedback from users regarding answers provided by the AI ​​Bot. For example, the user is asked to rate the satisfaction level of the answer and areas for improvement. The question answering unit also improves the accuracy of the AI ​​Bot's answers based on the user feedback. For example, the feedback data is analyzed to identify areas for improvement in the answers. In order to continuously improve the accuracy of the answers, the question answering unit also collects feedback from users in real time and reflects it in the AI ​​Bot. For example, the answers are revised based on the feedback. This allows the question answering unit to continuously improve the accuracy of the answers.

[0036] The question answering unit can also be operated as a voice assistant, enabling questions to be asked and answered via voice. For example, the question answering unit introduces voice recognition technology to operate an AI Bot as a voice assistant. For example, a user inputs a question via voice, and the AI ​​Bot provides an answer via voice. The question answering unit also develops an AI Bot as a voice assistant, enabling questions to be asked and answered via voice. For example, voice communication is performed through a smart speaker or a mobile device. The question answering unit also operates an AI Bot as a voice assistant, providing questions and answers via voice. For example, a user inputs a question via voice, and the AI ​​Bot provides an answer via voice. This allows the question answering unit to enable questions to be asked and answered via voice.

[0037] The question answering unit may also be provided as a mobile app, enabling questions to be asked and answered anytime, anywhere. For example, the question answering unit may develop a dedicated application to provide the AI ​​Bot as a mobile app. For example, an app may be developed for iOS or Android, allowing users to use it anytime, anywhere. The question answering unit may also develop the AI ​​Bot as a mobile app, allowing users to use it on smartphones or tablets. For example, a question may be entered through the app, and the AI ​​Bot may provide an answer. The question answering unit may also provide the AI ​​Bot as a mobile app, allowing users to use it anytime, anywhere. For example, a question may be entered through the app, and the AI ​​Bot may provide an answer. This allows the question answering unit to enable questions to be asked and answered anytime, anywhere.

[0038] The knowledge accumulation unit can study the work history and know-how of members before the transfer in detail and provide individual training plans for new members. For example, the knowledge accumulation unit has an AI Bot learn the work history of members before the transfer. For example, past projects and work content are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has an AI Bot learn the know-how of members before the transfer. For example, work tips and points to note are recorded in detail, and the generation AI provides training plans based on these. Furthermore, in order to provide individual training plans for new members, the knowledge accumulation unit has the generation AI generate training content based on the work history and know-how of members before the transfer. For example, specific training items are set based on past work content. This allows the knowledge accumulation unit to provide individual training plans for new members.

[0039] The question-answering unit can support a smooth handover by conducting a knowledge-sharing session via an AI Bot between the previous member and the new member. For example, the AI ​​Bot mediates between questions and answers, supporting efficient knowledge sharing. The question-answering unit also uses the AI ​​Bot to set up a session to convey the knowledge of the previous member to the new member. For example, the AI ​​Bot generates specific questions based on past work content and know-how, and the new member shares knowledge by answering those questions. The question-answering unit also uses the AI ​​Bot to convey the knowledge of the previous member to the new member through the knowledge-sharing session. For example, the AI ​​Bot creates specific scenarios based on past work history and know-how, and the new member learns according to those scenarios. In this way, the question-answering unit can support a smooth handover.

[0040] The knowledge accumulation unit can record the knowledge of members before the transfer as video or audio content and make it available for new members to view. For example, the knowledge accumulation unit can record the knowledge of members before the transfer as video and make it available for new members to view. For example, it can explain business procedures and know-how in video and store it in a database. The knowledge accumulation unit can also record the knowledge of members before the transfer as audio content and make it available for new members to view. For example, it can explain business tips and points to note in audio and store it in a database. The knowledge accumulation unit can also train a generation AI to learn the video or audio content and make it available for new members to view. For example, the generation AI can analyze the video or audio and extract important points and provide them. In this way, the knowledge accumulation unit can make it available for new members to view.

[0041] The knowledge accumulation department can provide the knowledge of pre-transfer members as an interactive e-learning platform, allowing new members to learn independently. The knowledge accumulation department, for example, provides the knowledge of pre-transfer members as an e-learning platform. For example, it can create online courses on business procedures and know-how to allow new members to learn independently. The knowledge accumulation department can also develop an interactive e-learning platform to allow new members to learn the knowledge of pre-transfer members. For example, it can provide practical learning through quizzes and simulations. The knowledge accumulation department can also use the e-learning platform to allow new members to learn the knowledge of pre-transfer members independently. For example, it can provide online courses and training programs and manage learning progress. In this way, the knowledge accumulation department can allow new members to learn independently.

[0042] The knowledge accumulation unit can learn from past cases of legal violations and provide an alert function to prevent similar risks from occurring in the future. The knowledge accumulation unit, for example, has the generation AI learn from past cases of legal violations. For example, detailed records of legal violations and countermeasures are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also provides an alert function to prevent similar risks from occurring in the future. For example, the generation AI detects signs of legal violations and issues a warning to the user. The knowledge accumulation unit also provides an alert function to prevent risks from occurring in the future based on past cases of legal violations. For example, the generation AI automatically issues an alert when certain conditions are met. In this way, the knowledge accumulation unit can provide an alert function to prevent similar risks from occurring in the future.

[0043] The legal interpretations provided by the question and answering unit can be reviewed by a third party to improve reliability. For example, the question and answering unit may have the legal interpretations provided by the AI ​​Bot reviewed by a third party. For example, reviews may be conducted by legal experts or regulatory authorities to confirm the accuracy of the interpretations. The question and answering unit may also improve the reliability of the legal interpretations provided by the AI ​​Bot through reviews by a third party. For example, the interpretations may be revised based on the review results to improve reliability. The question and answering unit may also regularly have the legal interpretations provided by the AI ​​Bot reviewed by a third party. For example, periodic audits and evaluations may be conducted to maintain the accuracy of the interpretations. This allows the question and answering unit to improve its reliability.

[0044] The question and answering unit is also operated as a monitoring tool for legal violation risks, and can detect risks in real time. The question and answering unit, for example, operates an AI Bot as a monitoring tool for legal violation risks. For example, it detects signs of legal violations in real time and issues a warning to the user. The question and answering unit also monitors signs of legal violations in order to detect risks in real time. For example, the AI ​​Bot automatically issues an alert when certain conditions are met. The question and answering unit also operates an AI Bot as a monitoring tool for legal violation risks, and can detect risks in real time. For example, it issues a warning to the user when it detects signs of legal violations. This allows the question and answering unit to detect risks in real time.

[0045] The question and answering unit can also be provided as an educational tool for legal violation risks, allowing employees to learn independently. The question and answering unit, for example, provides an AI bot as an educational tool for legal violation risks. For example, it can create an online course on legal violation risks and countermeasures, allowing employees to learn independently. The question and answering unit can also develop an AI bot as an educational tool for legal violation risks, allowing employees to learn independently. For example, it can provide practical learning through quizzes and simulations. The question and answering unit can also provide an AI bot as an educational tool for legal violation risks, allowing employees to learn independently. For example, it can provide online courses and training programs and manage learning progress. In this way, the question and answering unit can enable employees to learn independently.

[0046] The knowledge accumulation unit incorporates a business process optimization algorithm to automatically reduce wasted labor hours. For example, the knowledge accumulation unit incorporates a business process optimization algorithm into an AI Bot to automatically reduce wasted labor hours. For example, it analyzes business flows and identifies points for efficiency improvement. The knowledge accumulation unit also implements an algorithm for the AI ​​Bot to optimize business processes and reduce wasted labor hours. For example, it automatically detects duplicate work and unnecessary procedures and proposes improvements. The knowledge accumulation unit also uses the business process optimization algorithm to enable the AI ​​Bot to reduce wasted labor hours. For example, it monitors the progress of work in real time and automatically takes action to improve efficiency. In this way, the knowledge accumulation unit can automatically reduce wasted labor hours.

[0047] The question answering unit can collect user feedback on the information provided by the question answering unit, thereby continuously improving the accuracy of the information. The question answering unit, for example, collects user feedback on the information provided by the AI ​​Bot. For example, it asks the user to evaluate the accuracy and usefulness of the information. The question answering unit also improves the accuracy of the information provided by the AI ​​Bot based on the user feedback. For example, it analyzes the feedback data and identifies areas for improvement in the information. The question answering unit also collects user feedback in real time and reflects it in the AI ​​Bot in order to continuously improve the accuracy of the information. For example, it modifies the information based on the feedback. This allows the question answering unit to continuously improve the accuracy of the information.

[0048] The question answering unit can also be operated as a project management tool, allowing for the real-time management of work progress. For example, the question answering unit implements project management functions to operate the AI ​​Bot as a project management tool. For example, it monitors the progress of tasks in real time and generates progress reports. The question answering unit also develops the AI ​​Bot as a project management tool to manage work progress in real time. For example, it automates task assignment and deadline management. The question answering unit also operates the AI ​​Bot as a project management tool to manage work progress in real time. For example, it visualizes the project progress and shares it with team members. This allows the question answering unit to manage work progress in real time.

[0049] The question answering unit is also provided as a cost management tool, allowing for the monitoring of business costs in real time. For example, the question answering unit implements a cost management function to provide the AI ​​bot as a cost management tool. For example, it monitors business costs in real time and generates cost reports. The question answering unit also develops an AI bot as a cost management tool to monitor business costs in real time. For example, it automates budget management and cost optimization. The question answering unit also provides the AI ​​bot as a cost management tool to monitor business costs in real time. For example, it visualizes cost fluctuations and shares them with team members. This allows the question answering unit to monitor business costs in real time.

[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 knowledge transfer system can further include a progress management unit that tracks the user's learning progress. The progress management unit, for example, tracks in real time how much knowledge the user has acquired and visualizes the learning progress. The progress management unit can also suggest the next content to study based on the user's learning history. For example, if the user lacks knowledge of a specific law or procedure, the progress management unit can recommend studying that field. The progress management unit can also provide an individual training plan according to the user's learning progress. For example, if the user has weaknesses in a specific field, the progress management unit can suggest a plan to focus on studying that part. In this way, the knowledge transfer system can improve the user's learning efficiency.

[0052] The knowledge accumulation unit may further include a feedback collection unit that collects user feedback and improves the accuracy of the knowledge base. The feedback collection unit provides, for example, a function for users to evaluate answers provided by the users. For example, the feedback collection unit may ask users to evaluate the accuracy and usefulness of the answers. The feedback collection unit may also update the content of the knowledge base based on user feedback. For example, the feedback collection unit may revise the content of legal interpretations based on user feedback. The feedback collection unit may also analyze user feedback and identify areas for improvement in the knowledge base. For example, if many users have misunderstandings in a particular field, the feedback collection unit may strengthen the explanation of that field. This allows the knowledge accumulation unit to continuously improve the accuracy of the knowledge base.

[0053] The knowledge transfer system can further include a customization unit that provides customization functions according to the user's learning style. The customization unit, for example, suggests the optimal learning method based on the user's learning history and preferences. For example, a user who prefers visual learning can be provided with content that makes extensive use of infographics and visual notes. The customization unit can also adjust the learning schedule according to the user's learning pace. For example, it can provide content that can be learned in a short amount of time to busy users, and provide detailed explanations to users who have more time. The customization unit can also continuously improve the learning content based on user feedback. For example, if a particular piece of content is evaluated as difficult to understand, it can correct that part. This allows the knowledge transfer system to maximize the user's learning efficiency.

[0054] The knowledge transfer system can further include an evaluation unit that evaluates the user's learning progress and provides appropriate feedback. The evaluation unit, for example, provides a function for evaluating the content that the user has learned in the form of a test. For example, the evaluation unit measures the user's level of understanding through quizzes or simulations related to laws and regulations. The evaluation unit can also evaluate the user's learning progress based on the user's test results. For example, if the user's level of understanding in a particular field is low, the evaluation unit can make suggestions to strengthen learning in that field. The evaluation unit can also provide individual feedback according to the user's learning progress. For example, if the user answers a particular question incorrectly, the evaluation unit can provide a detailed explanation of that question. This allows the knowledge transfer system to maximize the user's learning effectiveness.

[0055] The knowledge transfer system can further include a plan proposal unit that proposes a future study plan based on the user's study history. The plan proposal unit, for example, analyzes the content and progress of the user's past studies and suggests what the user should study next. For example, if the user lacks knowledge of a specific law or procedure, the plan proposal unit recommends studying that field. The plan proposal unit can also create an individual study plan according to the user's study goals. For example, if the user wants to obtain a specific qualification, the plan proposal unit can propose a study schedule for that purpose. The plan proposal unit can also manage the user's study progress based on the user's study history. For example, the plan proposal unit can visualize the user's study progress and support the user in studying efficiently toward their goal. In this way, the knowledge transfer system can improve the user's study efficiency.

[0056] The knowledge transfer system can further include a visualization unit that visualizes the user's learning progress and increases motivation to learn. The visualization unit provides, for example, a function that displays the level of knowledge the user has acquired in graphs or charts. For example, it visually shows the learning progress, allowing the user to feel a sense of accomplishment. The visualization unit can also evaluate the learning results based on the user's learning history. For example, if the user's understanding in a specific field improves, the visualization unit can highlight this improvement. The visualization unit can also provide messages to increase motivation according to the user's learning progress. For example, if the user is approaching a goal, it can send an encouraging message. In this way, the knowledge transfer system can increase the user's motivation to learn.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The knowledge accumulation unit accumulates knowledge and experience of the Radio Law and legal interpretations. For example, the knowledge accumulation unit trains the generation AI on the provisions of the Radio Law and documents related to the Ministry of Internal Affairs and Communications' legal interpretations. The generation AI can also be trained on past legal precedents and actual business examples. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. Step 2: The AI ​​Bot Generation Unit generates an AI Bot based on the knowledge accumulated by the Knowledge Accumulation Unit. For example, the AI ​​Bot Generation Unit uses the Generation AI to create an AI Bot that provides appropriate answers to questions about the Radio Law. It can also learn the user's past question history and generate an AI Bot that provides answers optimized for each individual user. For example, past questions and their answers are imported into a database, and the Generation AI analyzes them. Step 3: The question answering unit uses the AI ​​Bot generated by the AI ​​Bot generation unit to provide appropriate answers to the new member's questions. For example, the question answering unit responds to the question, "Please tell me about the application procedure for a radio station license," by saying, "The application procedure for a radio station license is carried out according to the following steps." The question answering unit can also use its emotion estimation function to analyze the user's emotional response to legal interpretations and provide information in a format that is easy for the user to understand. For example, it can analyze the user's facial expressions and voice to measure their level of understanding and emotional response.

[0059] (Example 2) The knowledge transfer system according to the embodiment of the present invention is a system that accumulates knowledge and experience of the Radio Law in AI and provides appropriate answers to questions from new members. As a result, the knowledge transfer system can transfer knowledge from the radio department and improve work efficiency.

[0060] The knowledge transfer system according to the embodiment includes a knowledge accumulation unit, an AI bot generation unit, and a question-answering unit. The knowledge accumulation unit accumulates knowledge and experience of the Radio Act and legal interpretations. For example, the knowledge accumulation unit trains the generation AI on provisions of the Radio Act and documents related to legal interpretations by the Ministry of Internal Affairs and Communications. The knowledge accumulation unit can also train the generation AI on past court cases and actual business cases. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. The AI ​​bot generation unit generates an AI bot based on the knowledge accumulated by the knowledge accumulation unit. For example, the AI ​​bot generation unit uses the generation AI to create an AI bot that provides appropriate answers to questions related to the Radio Act. The AI ​​bot generation unit can also learn users' past question history and generate an AI bot that provides answers optimized for individual users. For example, past questions and their answers are imported into a database, and the generation AI analyzes them. The question-answering unit causes the AI ​​bot generated by the AI ​​bot generation unit to provide appropriate answers to questions from new members. For example, in response to a question such as "Please tell me about the application procedure for a radio station license," the question answering unit may respond with, "The application procedure for a radio station license is carried out according to the following steps." The question answering unit may also use its emotion estimation function to analyze a user's emotional response to legal interpretations and provide information in a format that is easy for the user to understand. For example, the system may analyze a user's facial expressions and voice to measure their level of understanding and emotional response. This allows the knowledge transfer system according to the embodiment to transfer knowledge in the radio department and improve work efficiency. For example, this allows new members to quickly learn their work, reduces the risk of legal violations, and prevents unnecessary increases in labor hours and costs. This improves the work efficiency of the entire radio department and promotes organizational revitalization.

[0061] The knowledge accumulation unit can learn from past legal precedents and business cases in addition to the provisions of the Radio Law and documents related to legal interpretations. For example, the knowledge accumulation unit has the generation AI learn from past legal precedents in addition to the provisions of the Radio Law and documents related to legal interpretations. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn from actual business cases. For example, radio station license application procedures and cases of legal violations are recorded in detail, and the generation AI generates answers based on these. The knowledge accumulation unit also has the generation AI learn from specialized books and papers related to the Radio Law. For example, commentaries and academic papers on the Radio Law are imported into a database, and the generation AI analyzes them. This allows the knowledge accumulation unit to accumulate more practical knowledge and provide appropriate answers.

[0062] The knowledge accumulation unit can also learn international laws and regulations related to radio laws. For example, the knowledge accumulation unit has the generation AI learn international radio law regulations. For example, it imports ITU (International Telecommunication Union) regulations and radio laws of each country into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn documents related to international legal interpretation. For example, it imports minutes of international conferences and legal interpretation guidelines from each country into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn international cases in order to provide legal interpretations from a global perspective. For example, it imports cases of international legal violations and their countermeasures into a database, and the generation AI analyzes them. This allows the knowledge accumulation unit to provide legal interpretations from a global perspective.

[0063] The question answering unit uses the emotion estimation function to analyze the user's emotional reaction to the legal interpretation and can provide information in a form that is easy for the user to understand. The question answering unit, for example, uses the emotion estimation function to analyze the user's emotional reaction to the legal interpretation in real time. For example, it analyzes the user's facial expressions and voice to measure the user's level of understanding and emotional reaction. The question answering unit also adjusts the method of providing the legal interpretation based on the user's emotional reaction data. For example, it may briefly explain difficult parts to make it easier for the user to understand. The question answering unit also uses the emotion estimation function to detect any anxieties or questions the user has about the legal interpretation and provide appropriate support. For example, it may provide additional explanations or related information. This allows the question answering unit to analyze the user's emotional reaction and provide information in a form that is easy for the user to understand.

[0064] The knowledge accumulation unit can also learn related laws and regulations other than the Radio Law. For example, the knowledge accumulation unit has the generation AI learn documents related to the Communications Law. For example, the provisions and interpretation guidelines of the Communications Law are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn documents related to the Information Protection Law. For example, the provisions and interpretation guidelines of the Information Protection Law are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has the generation AI learn other laws and regulations related to the Radio Law, and provides a comprehensive interpretation of the laws and regulations. For example, the knowledge accumulation unit analyzes the interrelationships between the Radio Law, the Communications Law, and the Information Protection Law, and provides a comprehensive interpretation. This enables the knowledge accumulation unit to provide a comprehensive interpretation of the laws and regulations.

[0065] The question and answering unit can provide knowledge about the Radio Law as visual notes and infographics. For example, the question and answering unit provides the provisions and interpretations of the Radio Law as visual notes. For example, important points can be shown with diagrams and icons to make them easier to understand visually. The question and answering unit can also create infographics about the Radio Law to provide information visually. For example, it can illustrate the flow and procedures of laws and regulations. The question and answering unit can also train a generation AI to create visual notes and infographics, providing information in a format that is easy for users to understand visually. For example, it can present related visual materials in response to a user's question. This allows the question and answering unit to provide information in a format that is easy for users to understand visually.

[0066] The question answering unit can use the emotion estimation function to detect in real time any anxieties or questions the user has about legal interpretation and provide appropriate support. The question answering unit, for example, uses the emotion estimation function to detect in real time any anxieties or questions the user has about legal interpretation. For example, it analyzes the user's facial expressions and voice to measure the emotional reaction. The question answering unit also provides appropriate support based on the user's emotional reaction data. For example, if the user feels anxious, it provides additional explanations or related information. The question answering unit also uses the emotion estimation function to detect any questions the user has about legal interpretation and provides appropriate answers. For example, it presents detailed explanations and specific examples in response to the user's questions. This allows the question answering unit to detect the user's anxieties or questions in real time and provide appropriate support.

[0067] The AI ​​Bot generation unit can learn the user's past question history and provide answers optimized for each individual user. For example, the AI ​​Bot generation unit makes the AI ​​Bot learn the user's past question history. For example, past questions and their answers are imported into a database, and the generation AI analyzes them. The AI ​​Bot generation unit also generates answers based on the user's question history to provide answers optimized for each individual user. For example, it provides related information based on the content of past questions. The AI ​​Bot generation unit also makes the AI ​​Bot provide answers optimized for each individual user based on the user's question history. For example, it analyzes the user's question patterns and generates optimal answers. This allows the AI ​​Bot generation unit to provide answers optimized for each individual user.

[0068] The question answering unit can collect feedback from users and continuously improve the accuracy of answers. For example, the question answering unit collects feedback from users regarding answers provided by the AI ​​Bot. For example, the user is asked to rate the satisfaction level of the answer and areas for improvement. The question answering unit also improves the accuracy of the AI ​​Bot's answers based on the user feedback. For example, the feedback data is analyzed to identify areas for improvement in the answers. In order to continuously improve the accuracy of the answers, the question answering unit also collects feedback from users in real time and reflects it in the AI ​​Bot. For example, the answers are revised based on the feedback. This allows the question answering unit to continuously improve the accuracy of the answers.

[0069] The question answering unit can use the emotion estimation function to analyze the emotion of the user when asking a question and provide an answer that corresponds to the emotion. The question answering unit, for example, uses the emotion estimation function to analyze the emotion of the user when asking a question in real time. For example, it analyzes the user's facial expression and voice to measure the emotional reaction. The question answering unit also generates an answer based on the emotion estimation data to provide an answer that corresponds to the user's emotion. For example, if the user is feeling anxious, it provides an answer that gives a sense of security. The question answering unit also uses the emotion estimation function to analyze the emotion of the user when asking a question and provide an appropriate answer. For example, if the user is excited, it provides a calm answer. This allows the question answering unit to provide an answer that corresponds to the user's emotion.

[0070] The question answering unit can also be operated as a voice assistant, enabling questions to be asked and answered via voice. For example, the question answering unit introduces voice recognition technology to operate an AI Bot as a voice assistant. For example, a user inputs a question via voice, and the AI ​​Bot provides an answer via voice. The question answering unit also develops an AI Bot as a voice assistant, enabling questions to be asked and answered via voice. For example, voice communication is performed through a smart speaker or a mobile device. The question answering unit also operates an AI Bot as a voice assistant, providing questions and answers via voice. For example, a user inputs a question via voice, and the AI ​​Bot provides an answer via voice. This allows the question answering unit to enable questions to be asked and answered via voice.

[0071] The question answering unit may also be provided as a mobile app, enabling questions to be asked and answered anytime, anywhere. For example, the question answering unit may develop a dedicated application to provide the AI ​​Bot as a mobile app. For example, an app may be developed for iOS or Android, allowing users to use it anytime, anywhere. The question answering unit may also develop the AI ​​Bot as a mobile app, allowing users to use it on smartphones or tablets. For example, a question may be entered through the app, and the AI ​​Bot may provide an answer. The question answering unit may also provide the AI ​​Bot as a mobile app, allowing users to use it anytime, anywhere. For example, a question may be entered through the app, and the AI ​​Bot may provide an answer. This allows the question answering unit to enable questions to be asked and answered anytime, anywhere.

[0072] The question answering unit uses the emotion estimation function to analyze the emotion of the user when asking a question in real time, and can make suggestions that elicit positive emotions. The question answering unit, for example, uses the emotion estimation function to analyze the emotion of the user when asking a question in real time. For example, the question answering unit analyzes the user's facial expressions and voice to measure the emotional response. The question answering unit also analyzes the user's emotion in real time and makes suggestions that elicit positive emotions. For example, if the user is feeling anxious, the question answering unit makes suggestions that give the user a sense of security. The question answering unit also uses the emotion estimation function to analyze the emotion of the user when asking a question, and makes suggestions that elicit positive emotions. For example, if the user is excited, the question answering unit makes calm suggestions. This allows the question answering unit to make suggestions that elicit positive emotions.

[0073] The knowledge accumulation unit can study the work history and know-how of members before the transfer in detail and provide individual training plans for new members. For example, the knowledge accumulation unit has an AI Bot learn the work history of members before the transfer. For example, past projects and work content are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also has an AI Bot learn the know-how of members before the transfer. For example, work tips and points to note are recorded in detail, and the generation AI provides training plans based on these. Furthermore, in order to provide individual training plans for new members, the knowledge accumulation unit has the generation AI generate training content based on the work history and know-how of members before the transfer. For example, specific training items are set based on past work content. This allows the knowledge accumulation unit to provide individual training plans for new members.

[0074] The question-answering unit can support a smooth handover by conducting a knowledge-sharing session via an AI Bot between the previous member and the new member. For example, the AI ​​Bot mediates between questions and answers, supporting efficient knowledge sharing. The question-answering unit also uses the AI ​​Bot to set up a session to convey the knowledge of the previous member to the new member. For example, the AI ​​Bot generates specific questions based on past work content and know-how, and the new member shares knowledge by answering those questions. The question-answering unit also uses the AI ​​Bot to convey the knowledge of the previous member to the new member through the knowledge-sharing session. For example, the AI ​​Bot creates specific scenarios based on past work history and know-how, and the new member learns according to those scenarios. In this way, the question-answering unit can support a smooth handover.

[0075] The question answering unit can use the emotion estimation function to detect the anxiety and stress of new members and provide appropriate support. The question answering unit, for example, uses the emotion estimation function to detect the anxiety and stress of new members in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. The question answering unit also provides appropriate support based on the emotional reaction data of the new member. For example, if the new member is feeling anxious, it provides additional explanations or encouraging messages. The question answering unit also uses the emotion estimation function to detect the stress of the new member and provide appropriate support. For example, if the stress level is high, it provides advice on relaxation methods and stress management. In this way, the question answering unit can detect the anxiety and stress of new members and provide appropriate support.

[0076] The knowledge accumulation unit can record the knowledge of members before the transfer as video or audio content and make it available for new members to view. For example, the knowledge accumulation unit can record the knowledge of members before the transfer as video and make it available for new members to view. For example, it can explain business procedures and know-how in video and store it in a database. The knowledge accumulation unit can also record the knowledge of members before the transfer as audio content and make it available for new members to view. For example, it can explain business tips and points to note in audio and store it in a database. The knowledge accumulation unit can also train a generation AI to learn the video or audio content and make it available for new members to view. For example, the generation AI can analyze the video or audio and extract important points and provide them. In this way, the knowledge accumulation unit can make it available for new members to view.

[0077] The knowledge accumulation department can provide the knowledge of pre-transfer members as an interactive e-learning platform, allowing new members to learn independently. The knowledge accumulation department, for example, provides the knowledge of pre-transfer members as an e-learning platform. For example, it can create online courses on business procedures and know-how to allow new members to learn independently. The knowledge accumulation department can also develop an interactive e-learning platform to allow new members to learn the knowledge of pre-transfer members. For example, it can provide practical learning through quizzes and simulations. The knowledge accumulation department can also use the e-learning platform to allow new members to learn the knowledge of pre-transfer members independently. For example, it can provide online courses and training programs and manage learning progress. In this way, the knowledge accumulation department can allow new members to learn independently.

[0078] The question answering unit uses the emotion estimation function to monitor the emotional state of the new member in real time and provide support at an appropriate time. The question answering unit, for example, uses the emotion estimation function to monitor the emotional state of the new member in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. The question answering unit also provides support at an appropriate time based on the emotional state of the new member. For example, if the new member is feeling anxious, it provides additional explanations or encouraging messages. The question answering unit also uses the emotion estimation function to monitor the emotional state of the new member and provide support at an appropriate time. For example, if the new member is feeling high in stress, it provides advice on relaxation methods and stress management. In this way, the question answering unit can monitor the emotional state of the new member in real time and provide support at an appropriate time.

[0079] The knowledge accumulation unit can learn from past cases of legal violations and provide an alert function to prevent similar risks from occurring in the future. The knowledge accumulation unit, for example, has the generation AI learn from past cases of legal violations. For example, detailed records of legal violations and countermeasures are imported into a database, and the generation AI analyzes them. The knowledge accumulation unit also provides an alert function to prevent similar risks from occurring in the future. For example, the generation AI detects signs of legal violations and issues a warning to the user. The knowledge accumulation unit also provides an alert function to prevent risks from occurring in the future based on past cases of legal violations. For example, the generation AI automatically issues an alert when certain conditions are met. In this way, the knowledge accumulation unit can provide an alert function to prevent similar risks from occurring in the future.

[0080] The legal interpretations provided by the question and answering unit can be reviewed by a third party to improve reliability. For example, the question and answering unit may have the legal interpretations provided by the AI ​​Bot reviewed by a third party. For example, reviews may be conducted by legal experts or regulatory authorities to confirm the accuracy of the interpretations. The question and answering unit may also improve the reliability of the legal interpretations provided by the AI ​​Bot through reviews by a third party. For example, the interpretations may be revised based on the review results to improve reliability. The question and answering unit may also regularly have the legal interpretations provided by the AI ​​Bot reviewed by a third party. For example, periodic audits and evaluations may be conducted to maintain the accuracy of the interpretations. This allows the question and answering unit to improve its reliability.

[0081] The question answering unit can use the emotion estimation function to detect anxiety the user has about legal interpretation and provide appropriate support. The question answering unit, for example, uses the emotion estimation function to detect anxiety the user has about legal interpretation in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. Furthermore, if the question answering unit detects the user's anxiety, it provides appropriate support. For example, it provides additional explanations or related information to alleviate the anxiety. Furthermore, the question answering unit can use the emotion estimation function to detect anxiety the user has about legal interpretation and provide appropriate support. For example, if the user is feeling anxious, it provides an answer that gives a sense of security. In this way, the question answering unit can detect anxiety the user has about legal interpretation and provide appropriate support.

[0082] The question and answering unit is also operated as a monitoring tool for legal violation risks, and can detect risks in real time. The question and answering unit, for example, operates an AI Bot as a monitoring tool for legal violation risks. For example, it detects signs of legal violations in real time and issues a warning to the user. The question and answering unit also monitors signs of legal violations in order to detect risks in real time. For example, the AI ​​Bot automatically issues an alert when certain conditions are met. The question and answering unit also operates an AI Bot as a monitoring tool for legal violation risks, and can detect risks in real time. For example, it issues a warning to the user when it detects signs of legal violations. This allows the question and answering unit to detect risks in real time.

[0083] The question and answering unit can also be provided as an educational tool for legal violation risks, allowing employees to learn independently. The question and answering unit, for example, provides an AI bot as an educational tool for legal violation risks. For example, it can create an online course on legal violation risks and countermeasures, allowing employees to learn independently. The question and answering unit can also develop an AI bot as an educational tool for legal violation risks, allowing employees to learn independently. For example, it can provide practical learning through quizzes and simulations. The question and answering unit can also provide an AI bot as an educational tool for legal violation risks, allowing employees to learn independently. For example, it can provide online courses and training programs and manage learning progress. In this way, the question and answering unit can enable employees to learn independently.

[0084] The question answering unit uses the emotion estimation function to analyze the emotions the user has regarding the risk of violating laws and regulations, and can propose appropriate countermeasures. The question answering unit, for example, uses the emotion estimation function to analyze the emotions the user has regarding the risk of violating laws and regulations in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. The question answering unit also proposes appropriate countermeasures based on the user's emotional reaction data. For example, if the user is feeling anxious, it proposes countermeasures that give the user a sense of security. The question answering unit also uses the emotion estimation function to analyze the emotions the user has regarding the risk of violating laws and regulations, and proposes appropriate countermeasures. For example, if the user is feeling anxious, it provides specific countermeasures. This allows the question answering unit to analyze the emotions the user has regarding the risk of violating laws and regulations, and propose appropriate countermeasures.

[0085] The knowledge accumulation unit incorporates a business process optimization algorithm to automatically reduce wasted labor hours. For example, the knowledge accumulation unit incorporates a business process optimization algorithm into an AI Bot to automatically reduce wasted labor hours. For example, it analyzes business flows and identifies points for efficiency improvement. The knowledge accumulation unit also implements an algorithm for the AI ​​Bot to optimize business processes and reduce wasted labor hours. For example, it automatically detects duplicate work and unnecessary procedures and proposes improvements. The knowledge accumulation unit also uses the business process optimization algorithm to enable the AI ​​Bot to reduce wasted labor hours. For example, it monitors the progress of work in real time and automatically takes action to improve efficiency. In this way, the knowledge accumulation unit can automatically reduce wasted labor hours.

[0086] The question answering unit can collect user feedback on the information provided by the question answering unit, thereby continuously improving the accuracy of the information. The question answering unit, for example, collects user feedback on the information provided by the AI ​​Bot. For example, it asks the user to evaluate the accuracy and usefulness of the information. The question answering unit also improves the accuracy of the information provided by the AI ​​Bot based on the user feedback. For example, it analyzes the feedback data and identifies areas for improvement in the information. The question answering unit also collects user feedback in real time and reflects it in the AI ​​Bot in order to continuously improve the accuracy of the information. For example, it modifies the information based on the feedback. This allows the question answering unit to continuously improve the accuracy of the information.

[0087] The question answering unit can use the emotion estimation function to detect the stress the user is feeling from work and provide appropriate support. The question answering unit, for example, uses the emotion estimation function to detect the stress the user is feeling from work in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. Furthermore, if the question answering unit detects the user's stress, it provides appropriate support. For example, it provides advice and resources for reducing stress. Furthermore, the question answering unit can use the emotion estimation function to detect the stress the user is feeling from work and provide appropriate support. For example, if the user is feeling stressed, it provides advice on relaxation methods and stress management. In this way, the question answering unit can detect the stress the user is feeling from work and provide appropriate support.

[0088] The question answering unit can also be operated as a project management tool, allowing for the real-time management of work progress. For example, the question answering unit implements project management functions to operate the AI ​​Bot as a project management tool. For example, it monitors the progress of tasks in real time and generates progress reports. The question answering unit also develops the AI ​​Bot as a project management tool to manage work progress in real time. For example, it automates task assignment and deadline management. The question answering unit also operates the AI ​​Bot as a project management tool to manage work progress in real time. For example, it visualizes the project progress and shares it with team members. This allows the question answering unit to manage work progress in real time.

[0089] The question answering unit is also provided as a cost management tool, allowing for the monitoring of business costs in real time. For example, the question answering unit implements a cost management function to provide the AI ​​bot as a cost management tool. For example, it monitors business costs in real time and generates cost reports. The question answering unit also develops an AI bot as a cost management tool to monitor business costs in real time. For example, it automates budget management and cost optimization. The question answering unit also provides the AI ​​bot as a cost management tool to monitor business costs in real time. For example, it visualizes cost fluctuations and shares them with team members. This allows the question answering unit to monitor business costs in real time.

[0090] The question answering unit can use the emotion estimation function to analyze the emotions the user has toward work and make suggestions to improve work efficiency. The question answering unit, for example, uses the emotion estimation function to analyze the emotions the user has toward work in real time. For example, it analyzes facial expressions and voice to measure emotional reactions. The question answering unit also makes suggestions to improve work efficiency based on the user's emotional reaction data. For example, if the user is feeling stressed, it suggests ways to improve the work. The question answering unit also uses the emotion estimation function to analyze the emotions the user has toward work and make suggestions to improve work efficiency. For example, if the user is feeling dissatisfied, it provides specific improvement measures. This allows the question answering unit to analyze the emotions the user has toward work and make suggestions to improve work efficiency.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The knowledge transfer system can further include a progress management unit that tracks the user's learning progress. The progress management unit, for example, tracks in real time how much knowledge the user has acquired and visualizes the learning progress. The progress management unit can also suggest the next content to study based on the user's learning history. For example, if the user lacks knowledge of a specific law or procedure, the progress management unit can recommend studying that field. The progress management unit can also provide an individual training plan according to the user's learning progress. For example, if the user has weaknesses in a specific field, the progress management unit can suggest a plan to focus on studying that part. In this way, the knowledge transfer system can improve the user's learning efficiency.

[0093] The knowledge accumulation unit may further include a feedback collection unit that collects user feedback and improves the accuracy of the knowledge base. The feedback collection unit provides, for example, a function for users to evaluate answers provided by the users. For example, the feedback collection unit may ask users to evaluate the accuracy and usefulness of the answers. The feedback collection unit may also update the content of the knowledge base based on user feedback. For example, the feedback collection unit may revise the content of legal interpretations based on user feedback. The feedback collection unit may also analyze user feedback and identify areas for improvement in the knowledge base. For example, if many users have misunderstandings in a particular field, the feedback collection unit may strengthen the explanation of that field. This allows the knowledge accumulation unit to continuously improve the accuracy of the knowledge base.

[0094] The knowledge transfer system can further include a customization unit that provides customization functions according to the user's learning style. The customization unit, for example, suggests the optimal learning method based on the user's learning history and preferences. For example, a user who prefers visual learning can be provided with content that makes extensive use of infographics and visual notes. The customization unit can also adjust the learning schedule according to the user's learning pace. For example, it can provide content that can be learned in a short amount of time to busy users, and provide detailed explanations to users who have more time. The customization unit can also continuously improve the learning content based on user feedback. For example, if a particular piece of content is evaluated as difficult to understand, it can correct that part. This allows the knowledge transfer system to maximize the user's learning efficiency.

[0095] The knowledge transfer system can further include an emotion support unit that estimates the user's emotions and provides learning support according to the emotions. The emotion support unit, for example, analyzes the user's facial expressions and voice to estimate the user's emotional state during learning in real time. For example, if the user is tired, it suggests taking a break. The emotion support unit can also adjust the learning content according to the user's emotional state. For example, if the user is feeling stressed, it can provide relaxing content. The emotion support unit can also provide encouraging and motivational messages based on the user's emotional state. For example, if the user is feeling anxious about learning, it can send an encouraging message. In this way, the knowledge transfer system can improve the user's learning experience.

[0096] The knowledge transfer system can further include an evaluation unit that evaluates the user's learning progress and provides appropriate feedback. The evaluation unit, for example, provides a function for evaluating the content that the user has learned in the form of a test. For example, the evaluation unit measures the user's level of understanding through quizzes or simulations related to laws and regulations. The evaluation unit can also evaluate the user's learning progress based on the user's test results. For example, if the user's level of understanding in a particular field is low, the evaluation unit can make suggestions to strengthen learning in that field. The evaluation unit can also provide individual feedback according to the user's learning progress. For example, if the user answers a particular question incorrectly, the evaluation unit can provide a detailed explanation of that question. This allows the knowledge transfer system to maximize the user's learning effectiveness.

[0097] The knowledge transfer system can further include an emotion adaptation unit that estimates the user's emotions and provides learning content according to the emotions. The emotion adaptation unit, for example, analyzes the user's facial expressions and voice to estimate the user's emotional state during learning in real time. For example, if the user is excited, it provides content that allows the user to study calmly. The emotion adaptation unit can also adjust the learning content according to the user's emotional state. For example, if the user is tired, it provides content that allows the user to relax. The emotion adaptation unit can also provide messages that support the user's learning progress based on the user's emotional state. For example, if the user is feeling anxious about learning, it sends a message that provides reassurance. In this way, the knowledge transfer system can improve the user's learning experience.

[0098] The knowledge transfer system can further include a plan proposal unit that proposes a future study plan based on the user's study history. The plan proposal unit, for example, analyzes the content and progress of the user's past studies and suggests what the user should study next. For example, if the user lacks knowledge of a specific law or procedure, the plan proposal unit recommends studying that field. The plan proposal unit can also create an individual study plan according to the user's study goals. For example, if the user wants to obtain a specific qualification, the plan proposal unit can propose a study schedule for that purpose. The plan proposal unit can also manage the user's study progress based on the user's study history. For example, the plan proposal unit can visualize the user's study progress and support the user in studying efficiently toward their goal. In this way, the knowledge transfer system can improve the user's study efficiency.

[0099] The knowledge transfer system can further include an environment adjustment unit that estimates the user's emotions and provides a learning environment that corresponds to the emotions. The environment adjustment unit, for example, analyzes the user's facial expressions and voice to estimate the user's emotional state during learning in real time. For example, if the user is lacking in concentration, the environment adjustment unit suggests an environment that makes it easier to concentrate. The environment adjustment unit can also adjust the learning environment according to the user's emotional state. For example, it can adjust background music and lighting to help the user relax. The environment adjustment unit can also provide messages that support the user's learning progress based on the user's emotional state. For example, if the user is feeling anxious about learning, it can send a message that provides reassurance. In this way, the knowledge transfer system can improve the user's learning experience.

[0100] The knowledge transfer system can further include a visualization unit that visualizes the user's learning progress and increases motivation to learn. The visualization unit provides, for example, a function that displays the level of knowledge the user has acquired in graphs or charts. For example, it visually shows the learning progress, allowing the user to feel a sense of accomplishment. The visualization unit can also evaluate the learning results based on the user's learning history. For example, if the user's understanding in a specific field improves, the visualization unit can highlight this improvement. The visualization unit can also provide messages to increase motivation according to the user's learning progress. For example, if the user is approaching a goal, it can send an encouraging message. In this way, the knowledge transfer system can increase the user's motivation to learn.

[0101] The knowledge transfer system can further include an advice unit that estimates the user's emotions and provides learning advice according to the emotions. The advice unit, for example, analyzes the user's facial expressions and voice to estimate the user's emotional state during learning in real time. For example, if the user is tired, it suggests taking a break. The advice unit can also provide advice to support learning progress according to the user's emotional state. For example, if the user is feeling stressed, it provides advice on relaxation methods and stress management. The advice unit can also provide messages to support learning progress based on the user's emotional state. For example, if the user is feeling anxious about learning, it sends a message that provides reassurance. In this way, the knowledge transfer system can improve the user's learning experience.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The knowledge accumulation unit accumulates knowledge and experience of the Radio Law and legal interpretations. For example, the knowledge accumulation unit trains the generation AI on the provisions of the Radio Law and documents related to the Ministry of Internal Affairs and Communications' legal interpretations. The generation AI can also be trained on past legal precedents and actual business examples. For example, past court records and case law collections are imported into a database, and the generation AI analyzes them. Step 2: The AI ​​Bot Generation Unit generates an AI Bot based on the knowledge accumulated by the Knowledge Accumulation Unit. For example, the AI ​​Bot Generation Unit uses the Generation AI to create an AI Bot that provides appropriate answers to questions about the Radio Law. It can also learn the user's past question history and generate an AI Bot that provides answers optimized for each individual user. For example, past questions and their answers are imported into a database, and the Generation AI analyzes them. Step 3: The question answering unit uses the AI ​​Bot generated by the AI ​​Bot generation unit to provide appropriate answers to the new member's questions. For example, the question answering unit responds to the question, "Please tell me about the application procedure for a radio station license," by saying, "The application procedure for a radio station license is carried out according to the following steps." The question answering unit can also use its emotion estimation function to analyze the user's emotional response to legal interpretations and provide information in a format that is easy for the user to understand. For example, it can analyze the user's facial expressions and voice to measure their level of understanding and emotional response.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A knowledge accumulation department that accumulates knowledge and experience in the Radio Law and legal interpretations; an AI Bot generation unit that generates an AI Bot based on the knowledge accumulated by the knowledge accumulation unit; a question answering unit in which the AI ​​Bot generated by the AI ​​Bot generating unit provides appropriate answers to questions from new members. A system characterized by:

2. The knowledge accumulation unit In addition to the provisions of the Radio Law and documents related to the interpretation of the law, students will also learn about past legal precedents and business cases.

2. The system of claim 1.

3. The knowledge accumulation unit Learn about international laws and regulations related to radio law 2. The system of claim 1.

4. The question answering unit Analyzing the user's emotional response to the legal interpretation and providing the information in a format that is easy for the user to understand 2. The system of claim 1.

5. The knowledge accumulation unit Learn about related laws and regulations other than the Radio Law 2. The system of claim 1.

Images