system

Abstract

We provide the system. [Solution] A means of storing information by having users input specific professional skills and knowledge, A computing device searches for educators based on user-specified conditions and lists suitable candidates; A communication means having a call or chat function that allows users and educators to conduct online training sessions via a terminal, A computing device records the progress of self-driving technology training sessions and user feedback, and provides compensation to educators. A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the progress of AI technology, it is an issue to effectively improve the specific skills and practical abilities required for AI agents in various fields of practice in a short period of time. For this reason, direct guidance by a person with specialized knowledge is required, but there is a lack of a system for efficiently matching skill trainers and AI agent users, implementing training, and appropriately evaluating and rewarding the results.

Means for Solving the Problems

[0005] To address this challenge, the present invention provides a means for users to register their professional skills and practical experience in a database, and for a server to match users with trainers who meet their criteria. Furthermore, the system includes a mechanism for conducting online training sessions via a terminal, recording session progress and evaluations on the server, and providing rewards to trainers based on the results. This entire process allows for the improvement of AI agent capabilities and enables trainers to receive appropriate compensation.

[0006] A "user" is an individual or legal entity that registers their professional skills and work experience in the system and is matched with a trainer for the purpose of improving the capabilities of the AI ​​agent.

[0007] A "database" is an information management system that records user and trainer information and is used for searching and matching.

[0008] A "server" is a central processing unit that processes user input information, matches users with trainers, manages training session schedules, and records evaluations.

[0009] A "trainer" is an individual or group that possesses specific practical skills or expertise and whose role is to teach them to AI agents.

[0010] A "device" refers to the device used by the user and trainer during online sessions, and primarily includes personal computers and smartphones.

[0011] An "online session" refers to a time and place where users and trainers communicate interactively via a digital platform to provide skill instruction.

[0012] "Evaluation" refers to the act of a user evaluating the trainer and the content of their instruction based on the results they achieved through a training session, and it is a factor that influences the determination of compensation.

[0013] "Compensation" refers to the monetary payment made to trainers based on the implementation and evaluation of training sessions, and serves as an incentive. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), etc.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] In an embodiment of this invention, the platform consists of a user, a trainer, a server, and a terminal. When a user wants to train an AI agent using their professional skills and practical experience, they first access the platform to find a trainer that meets their needs. Upon receiving the search criteria from the user, the server generates the most suitable candidates based on trainer information in the database.

[0036] The user selects a trainer via their device and schedules a session. Based on this, the server schedules the training session and notifies both parties. The training is conducted online via video calls and chat through the device. The trainer conveys specific skills and know-how to the AI ​​agent and provides education while monitoring progress.

[0037] During the training session, the server records the instruction content and progress. After the session ends, the user evaluates the degree of improvement in the AI ​​agent's abilities, and this evaluation is sent to the server. Based on this evaluation, the server determines the trainer's compensation and provides financial incentives.

[0038] As a concrete example, suppose a user is developing an AI agent specializing in the financial industry. If this user wants to teach the AI ​​the latest market analysis techniques, they would search for a trainer knowledgeable in market trends on the platform. The selected trainer would then teach the AI ​​using their own analysis methods and tools. As a result, the AI ​​can improve the accuracy of its market analysis in a short period of time, and the user can achieve greater efficiency in financial operations.

[0039] This system makes it possible to efficiently convey the expertise of trainers with specialized knowledge to AI agents, providing benefits to both parties.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] A user accesses the server using their device to search for trainers with specialized skills and practical experience, and enters their search criteria. The server receives this information and prepares to query its database.

[0043] Step 2:

[0044] Based on the search criteria received by the server, it extracts suitable trainer candidates from the database and generates a recommendation list. The server then sends this list to the user's terminal.

[0045] Step 3:

[0046] The user selects the most suitable trainer from a list and adjusts the date, time, and content of the training session. The user then sends this information to the server via their device.

[0047] Step 4:

[0048] The server confirms the training session schedule and sends confirmation notifications to both the trainer and the user. At this point, the necessary infrastructure is set up.

[0049] Step 5:

[0050] The user and trainer begin an online session using their devices at a designated time. The server establishes the connection for this session and supports communication via video calls and chat functions.

[0051] Step 6:

[0052] A trainer instructs an AI agent on specific skills and knowledge via a terminal, and provides the user with feedback and progress information generated during the process. The server records this information.

[0053] Step 7:

[0054] After the session ends, the user sends an evaluation from their device to the server, indicating the degree of improvement in the AI ​​agent's abilities and their assessment of the trainer's instruction. The server stores this evaluation in a database and calculates the trainer's compensation.

[0055] Step 8:

[0056] The server initiates the process of paying the trainer based on their performance and reflects the reward information in the trainer's account. This completes the training cycle.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In today's information society, having efficient means of training and education is crucial, especially in fields requiring specialized skills and knowledge. However, users often struggle to effectively find educators suited to their needs, and methods for objectively evaluating educational progress and outcomes and reflecting this in compensation are limited. A system that addresses these challenges is necessary.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes an information management means for users to register information by inputting their specialized skills and practical experience, a selection means for the server to search for educators based on conditions specified by the user and list appropriate candidates, and a means having a communication function that allows users and educators to conduct online learning sessions via a terminal. This makes it possible to efficiently match and implement specialized education, and to appropriately determine educators' compensation based on results.

[0062] An "information management system" is a method that has the function of registering information by inputting specialized skills and practical experience from users.

[0063] The "selection method" refers to a technique in which the server searches for suitable educators based on conditions specified by the user and lists the candidates.

[0064] "Communication functionality" refers to technology that provides the ability for users and educators to conduct online learning sessions through a terminal.

[0065] A "learning session" is an online educational activity conducted by users and educators to transmit specific skills or knowledge.

[0066] "Provision of rewards" refers to the act of a server providing monetary or other incentives based on the results of the educator's teaching.

[0067] This invention is a system that efficiently matches educators with specialized knowledge and skills with users to support online learning. Specific embodiments are described below.

[0068] Users utilize information management tools to register their professional skills and practical experience. This is supported by a database management system (DBMS), and users can input data via a terminal. The entered data is used for matching in subsequent processes.

[0069] The server searches for suitable educators based on the conditions entered by the user. This selection method utilizes SQL queries to list educators that match the criteria from the database. For example, if a user specifies their preference using keywords such as "educator who can teach the latest market analysis techniques," the server will select educators that match that description.

[0070] The device provides communication capabilities for users and educators to communicate. This utilizes video calls and chat systems. Users can learn online with selected educators. These sessions proceed in real time, and the educational content is recorded digitally.

[0071] The server records the progress of learning sessions and stores it in a database along with user ratings. This rating information is used as a reference for future matching. Furthermore, the evaluation of the learning content is an important indicator when determining compensation for educators. Compensation is determined through an automated system and provided appropriately to educators.

[0072] As a concrete example, a prompt might read, "Please find a suitable educator to learn market analysis skills." Based on this prompt, the server lists relevant educators and presents them to the user.

[0073] This system will enable users to learn efficiently from educators with specialized knowledge, resulting in a meaningful learning experience for both parties.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] Users input their specialized skills, work experience, and learning goals. The entered data is registered in a database using an information management system. Specifically, users access a dedicated screen on their terminal and enter their desired skills and technologies as keywords in an input form.

[0077] Step 2:

[0078] The server receives the user's input criteria and starts the search process. It searches the database for educators that match the criteria using an SQL query. In this process, filtering is performed based on the user's input criteria, and a list of suitable educators (output) is generated. Specifically, the server executes the query, extracts the results, and generates a candidate list.

[0079] Step 3:

[0080] The server presents the user with a list of candidates obtained through the search. The user then selects a desired educator from this list. Based on this selection, the server begins preparing to coordinate the schedule. Specifically, the user views the profiles of educators of interest from the list and presses the "Select" button.

[0081] Step 4:

[0082] The server uses the user's selection information to schedule the learning session. During this process, communication methods (video calls or chat systems) for conducting the learning session online are prepared. The schedule information is sent to both parties via email or push notification. Specifically, the server uses a scheduling system to determine and notify the user of an appropriate date and time.

[0083] Step 5:

[0084] The device activates the necessary communication functions during the learning session. Users and educators exchange data in real time on this device, progressing through learning via video calls and chat. Specifically, the device activates the camera and microphone and launches the communication software.

[0085] Step 6:

[0086] The server records the content and progress of the learning session. After the session ends, it collects feedback from the user and stores it in a database. This feedback is output as data used for educator evaluation and compensation calculation. Specifically, the server records the learning content in a log file and provides the user with an evaluation form.

[0087] Step 7:

[0088] The server determines the reward for educators based on the collected evaluation information. The reward calculation uses the evaluation score and pre-set reward criteria, and the reward is provided to the educators based on the result. Specifically, the server executes the reward calculation algorithm and sends the result to the educators via the payment system.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] Currently, training AI agents in autonomous driving technology is highly specialized and conducted with limited resources. This results in limited contact with educators possessing the necessary expertise, leading to insufficient improvement in the capabilities of autonomous mobile agents. To address this, efficient matching with educators possessing a broader range of expertise and the smooth implementation of online training sessions are required.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes storage means for registering information by inputting specific professional skills and knowledge from the user, matching means for a computing device to search for educators based on conditions specified by the user and list suitable candidates, and communication means having a call or chat function that allows the user and educator to conduct training sessions online via a terminal. This enables appropriate improvement of the capabilities of the autonomous mobile agent and the realization of more accurate autonomous driving technology.

[0094] A "user" refers to an individual or corporation that possesses specific expertise or skills and wishes to find an educator suited to their needs to train an AI agent.

[0095] "Specialized competence" refers to knowledge and skills acquired through advanced training and experience in a particular field.

[0096] "Knowledge" refers to information, understanding, and theories acquired through experience and education.

[0097] A "computational device" refers to a computer system used to process data and to search for educators and generate candidate lists.

[0098] An "educator" refers to a person who possesses specialized skills and knowledge in a particular field and whose role is to provide training to AI agents.

[0099] "Storage means" refers to a method or system for recording and retaining professional skills and knowledge entered by users.

[0100] "Integration means" refers to a method or system for organizing educator information based on user needs and listing the most suitable candidates.

[0101] "Communication methods" refers to systems that provide the necessary call or chat functions for users and educators to interact online.

[0102] An "autonomous mobile agent" refers to an artificial intelligence system that has the ability to move independently and perform tasks by utilizing sensors and analytical functions for its environment.

[0103] To implement this invention, users must input their specialized knowledge and skills and register them in a database using a storage means. The server then searches for educators based on the user's specified conditions using this data. A machine learning algorithm using Python is employed for the search, listing the most suitable candidates from the educators' profile data. The listed candidates are displayed on the user's terminal.

[0104] Next, the user conducts an online training session with a selected educator via their device. The session is conducted using video conferencing software such as Zoom or Google Meet®, which are used as the means of communication. The educator imparts knowledge and expertise in a specific field to the AI ​​agent, thereby improving the AI ​​agent's skills necessary for autonomous navigation technology.

[0105] During a session, the server records training progress and user feedback in real time and stores it in a MySQL® database. This feedback information is used to determine compensation for educators and to create a list of candidates for future sessions.

[0106] One concrete example is a scenario in which the AI ​​agent of an autonomous vehicle receives training to recognize traffic conditions and respond appropriately. An example of a prompt in this scenario would be, "Please tell me what training content is necessary for the AI ​​agent of an autonomous vehicle to accurately recognize emergency vehicles and respond appropriately." In this way, by utilizing generative AI models, AI agents can acquire more advanced decision-making capabilities.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] Users input their professional skills and knowledge into a terminal, and this information is transmitted to a server via a storage system. The input data includes their area of ​​expertise and specific skill sets. This information is registered in a database and used to select future educators.

[0110] Step 2:

[0111] The server uses computing power to search for educators based on the conditions specified by the user. The input here is the training conditions and objectives desired by the user, and the output is a list of educators that meet the conditions. The server uses a Python machine learning algorithm to extract profiles of suitable educators from the database and generate a list of candidate educators.

[0112] Step 3:

[0113] The terminal displays a list of educators received from the server to the user. The user selects an appropriate educator from the displayed candidates, specifies the desired training session date, and sends it to the server. The input in this step is the user's selection, and the output is the reserved session information.

[0114] Step 4:

[0115] The server sets up communication between the selected educator and user and conducts online training sessions. Inputs include terminal information of the selected educator and user, and output is the connected call or chat session. Zoom or Google® Meet is used for these calls. The educator transmits their expertise to the AI ​​agent.

[0116] Step 5:

[0117] During a session, the server records training progress and user feedback in real time. Inputs are progress data and user feedback during the training session, while output is information stored in the server's evaluation database. The recorded data is used to improve training and determine compensation for educators.

[0118] Step 6:

[0119] After a training session, the user evaluates the performance of the autonomous mobile agent and sends the results to the server. The input is the degree of improvement in the agent's capabilities and the user's evaluation, and the output is the evaluation value used for reward calculation. This information is also used as optimization prompts generated by the generative AI model.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] In a mode of carrying out this invention, by incorporating an emotion engine into the skill transfer platform, it becomes possible to understand the user's emotional state and provide more effective training sessions.

[0122] Users access the platform via their devices and search for trainers to improve their professional skills. During this process, an emotion engine recognizes the user's emotional state from their facial expressions and voice, and helps select the most suitable trainer based on that state. For example, if a user is feeling stressed, the emotion engine can recommend a trainer with a relaxed teaching style.

[0123] During training sessions, the server analyzes the user's emotional changes in real time via an emotion engine. This information is provided to the trainer as feedback, allowing the trainer to adjust their teaching methods as needed.

[0124] When users provide feedback after a session, the emotion engine analyzes the emotional data from the session and incorporates it into the evaluation. As a result, the server more accurately measures the effectiveness of the training and adjusts the rewards for the trainer.

[0125] For example, consider a scenario where a user wants to train an AI agent to acquire advanced presentation skills. During a session that begins with the user under high stress, the emotion engine can detect the user's anxiety, allowing the trainer to provide more reassuring guidance. In this way, the user can improve their presentation skills more effectively.

[0126] This system utilizes an emotion engine to conduct AI education while considering the user's psychological factors, thereby improving the quality of training.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The user logs into the platform using their device and searches for a trainer suitable for training the AI ​​agent. The device captures the user's voice and facial expressions and prepares to send them to the emotion engine.

[0130] Step 2:

[0131] The emotion engine analyzes the user's voice and facial expression data to estimate their emotional state at that moment. For example, it can identify emotions such as stress, anxiety, and relaxation.

[0132] Step 3:

[0133] The server searches a database based on emotional state information from the emotion engine to select the most suitable trainer for the user. It creates a list that recommends trainers with different teaching approaches depending on the user's emotional state.

[0134] Step 4:

[0135] The user selects the most suitable trainer from the recommended trainers via their device and sets the date and time for the training session. The server confirms this and notifies both parties of the schedule.

[0136] Step 5:

[0137] Once a training session begins, the device transmits the user's facial expressions and voice to the emotion engine in real time. The emotion engine analyzes this data in real time and monitors changes in the user's emotions.

[0138] Step 6:

[0139] The server provides trainers with feedback from the emotion engine, helping them adjust their instruction to match the user's emotional state. This allows trainers to maintain user focus and provide effective instruction.

[0140] Step 7:

[0141] After the session ends, the user evaluates the trainer based on their performance. During this process, the emotion engine analyzes the emotional data from the session and reflects it on the server as evaluation information.

[0142] Step 8:

[0143] The server calculates and pays trainers based on user evaluation data and emotion engine analysis. This result is also reflected in the trainer evaluation database and used for future matching.

[0144] (Example 2)

[0145] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0146] Traditional online education systems often provide standardized training without considering the user's emotional state, resulting in ineffective instruction. Furthermore, the lack of real-time information that allows educators to provide flexible instruction tailored to the user's condition can lead to a decline in the quality of education.

[0147] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0148] In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis device, means for selecting the most suitable educator, and means for providing real-time feedback to the educator and adjusting the teaching method. This makes it possible to provide optimal instruction tailored to the user's emotional state, thereby improving the quality of education.

[0149] A "user" is an individual or group that uses an educational system to improve their abilities or skills in a specific field.

[0150] A "field" refers to an area or category in which specific knowledge or skills are applied.

[0151] "Practical experience" refers to the knowledge and skills gained from actual work and activities performed by a user in a specific field.

[0152] A "data set" is a collection of information that registers a user's abilities and experience in a specific field.

[0153] "Conditions" refer to the factors and criteria that users consider when selecting a trainer.

[0154] An "educator" is someone who provides users with specific skills and knowledge, and who offers guidance and support.

[0155] A "matching mechanism" refers to a process or system in which a server searches for educators based on conditions specified by the user and lists suitable candidates.

[0156] "Telecommunication" refers to a method of communication that transmits information electronically, transcending physical distance.

[0157] "Communication functionality" refers to features that enable users and educators to exchange information online.

[0158] "Compensation" refers to money or other valuable benefits paid to educators for the instruction or services they provide.

[0159] An "emotion analysis device" is a technology or device that identifies and analyzes a user's emotions from their facial expressions and voice.

[0160] "Analysis" is the act or process of breaking down data and understanding its structure and meaning.

[0161] "Feedback" refers to evaluation information, including emotional states, that educators use to adjust their teaching methods based on real-time information.

[0162] "Teaching methods" refer to the educational approaches and strategies that educators use with users.

[0163] To implement this invention, a server, terminal, and user collaborate to operate the system. The server incorporates an emotion analysis device, enabling real-time analysis of the user's emotional state. Specifically, the server uses technologies such as facial recognition software and voice analysis software to analyze the user's emotions in detail and selects the most appropriate educator based on the results. It also continuously monitors changes in the user's emotions during the lesson and provides feedback to the educator. The educator adjusts their teaching methods based on this feedback to provide the user with the optimal learning experience.

[0164] The terminal serves as a means for users to access the system and captures facial expressions and voice data through its camera and microphone. This data is sent to a server and used for analysis. The terminal is equipped with calling and chat functions for users and educators to communicate online, enabling efficient exchange of educational content via remote communication.

[0165] Users register information in the system using their devices to improve their abilities and skills in specific areas. At every step the user experiences, the results of sentiment analysis are used to provide personalized learning support, maximizing the user's skill improvement.

[0166] As a concrete example, if a user wants to improve their presentation skills, they can start training through their device. Once the session begins, the server can detect the user's anxiety level through an emotion analysis device and recommend an educator with a relaxed teaching style. As a result, the user can develop their skills smoothly without feeling pressured.

[0167] A concrete example of a prompt might be, "Please describe an educational system that can adjust its teaching style according to the user's emotional state." This aims to improve the overall effectiveness of the system by emphasizing an educational approach based on the user's emotions.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] Users access the skill transfer platform using a terminal and input information about a specific field. This input includes the user's current abilities, target skill level, and desired training content. This data is registered in a database and used as foundational information for subsequent processes.

[0171] Step 2:

[0172] The terminal transmits user information to the server based on registered data. The server receives this information and uses an emotion analysis device to analyze the user's facial expressions and voice data captured from the camera and microphone. This analysis recognizes the user's emotional state (e.g., tension, stress, relaxation) and extracts it as data.

[0173] Step 3:

[0174] The server uses the sentiment analysis results to select the most suitable educator. Specifically, it searches the educator database using a matching mechanism and lists the educators best suited to the user's emotional state and preferences. This result is output to the terminal as a recommendation list.

[0175] Step 4:

[0176] The user reviews the recommended list of educators on their device and selects their preferred educator. The selected educator's information is sent to the server, and the training session schedule is finalized.

[0177] Step 5:

[0178] Once a training session begins, the server continuously monitors the user's emotional state via an emotion analysis device. Real-time emotional data is provided as feedback from the server to the educator, who then adjusts their teaching methods based on this feedback.

[0179] Step 6:

[0180] After the session ends, the user enters their training evaluation on their device. The server integrates this evaluation with sentiment data from the session to assess the educator's performance. Based on these results, the educator's reward is determined and recorded as feedback that will be reflected in the user's future training.

[0181] (Application Example 2)

[0182] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0183] Traditional training systems had the problem of not maximizing the effectiveness of instruction because they provided uniform instruction without considering the emotional state of the user. Furthermore, there was a lack of means to provide instructors with immediate, emotion-based feedback, making it difficult to appropriately adjust instruction methods. In addition, there were no criteria to accurately determine whether the instruction content was suitable for improving the learner's abilities.

[0184] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0185] In this invention, the server includes means having an information storage device, selection means, means having a communication function, means for analyzing emotional states using an emotion recognition device, and means for providing rewards to instructors. This enables more effective instruction based on the user's emotions, and allows instructors to adjust their instruction methods in real time. Furthermore, it enables accurate evaluation of the effectiveness of instruction and determination of rewards based on that evaluation.

[0186] An "information storage device" is a device that allows a user to input specific abilities or knowledge and save that information.

[0187] The "selection method" refers to a means of searching for suitable instructors based on the conditions specified by the user and listing the candidates.

[0188] "Communication function" refers to the ability to make calls or communicate via the device to allow users and instructors to conduct online training sessions.

[0189] An "emotion recognition device" is a device that analyzes the user's emotional state and provides the results to the instructor.

[0190] "Means of providing rewards" refers to means of rewarding instructors based on the progress and evaluation of training sessions.

[0191] In this embodiment of the invention, an information processing device plays a central role in realizing the training system. The information storage device is a data recording device that receives and stores data for users to register specific abilities and knowledge. The server uses selection means to select the most suitable instructor based on the registered information. This selection process is realized by combining a search algorithm and data mining technology. Scalable and efficient selection can be achieved by utilizing Microsoft® Azure® and Amazon Web Services.

[0192] During training, the device connects the user and instructor using its communication functions. This function supports voice and video calls over the internet, enabling real-time communication. The device also works in conjunction with an emotion recognition device to recognize the user's emotional state. This device collects data from the user's facial expressions and voice, and passes it to an emotion analysis API to determine the user's emotions.

[0193] The server provides information to instructors based on data obtained from emotion recognition devices, enabling instructors to provide appropriate guidance tailored to the user's emotions. This data can be processed, for example, using Python, and then displayed on a dashboard.

[0194] For example, if it is determined that an elderly person needs relaxation, the server suggests a music session and transmits this information to the instructor via the terminal. This type of application enables efficient and humane care.

[0195] An example of a prompt for a generative AI model would be: "Recognize the smiles of elderly people and determine the emotion behind those smiles. Based on the discovered emotion, suggest appropriate care actions."

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server receives specific abilities and knowledge registered by the user in the information storage device. Based on this input data, the server processes the information and saves it to the database. During this process, data verification is performed to confirm the accuracy and format of the information, and a list of registered information is compiled.

[0199] Step 2:

[0200] The user enters the desired criteria for a coach. The server searches for coach information in the existing database based on these criteria. Using a selection algorithm, it lists the coaches that best match the criteria and generates output providing this information to the user. The database search is performed using SQL queries.

[0201] Step 3:

[0202] The terminal initiates a connection with the instructors listed by the selection method. Communication functions allow users and instructors to communicate in real time. During this process, audio and video data are transmitted and received. Video stream data is compressed and efficiently transmitted over the network.

[0203] Step 4:

[0204] The user's device uses a built-in emotion recognition device to capture the user's facial expressions and voice, and sends this data to the server. The server inputs the received data into an emotion analysis API to analyze the user's emotional state. It outputs the analysis results and provides feedback to the instructor in real time. This allows the instructor to adjust their teaching methods according to the situation.

[0205] Step 5:

[0206] The server records all session data and analyzes training progress and results. It evaluates instructors based on user ratings and sentiment data, and uses the results to determine instructor rewards. Data analysis is performed at this stage, and the results are processed by a reward calculation algorithm.

[0207] Step 6:

[0208] After the user ends the session, the server saves all processing results to an information storage device. This data serves as the basis for selecting the next instructor and improving the session. The prompts to the generated AI model are updated as needed to facilitate interventions optimized for the user's environment.

[0209] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0210] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0225] In an embodiment of this invention, the platform consists of a user, a trainer, a server, and a terminal. When a user wants to train an AI agent using their professional skills and practical experience, they first access the platform to find a trainer that meets their needs. Upon receiving the search criteria from the user, the server generates the most suitable candidates based on trainer information in the database.

[0226] The user selects a trainer via their device and schedules a session. Based on this, the server schedules the training session and notifies both parties. The training is conducted online via video calls and chat through the device. The trainer conveys specific skills and know-how to the AI ​​agent and provides education while monitoring progress.

[0227] During the training session, the server records the instruction content and progress. After the session ends, the user evaluates the degree of improvement in the AI ​​agent's abilities, and this evaluation is sent to the server. Based on this evaluation, the server determines the trainer's compensation and provides financial incentives.

[0228] As a concrete example, suppose a user is developing an AI agent specializing in the financial industry. If this user wants to teach the AI ​​the latest market analysis techniques, they would search for a trainer knowledgeable in market trends on the platform. The selected trainer would then teach the AI ​​using their own analysis methods and tools. As a result, the AI ​​can improve the accuracy of its market analysis in a short period of time, and the user can achieve greater efficiency in financial operations.

[0229] This system makes it possible to efficiently convey the expertise of trainers with specialized knowledge to AI agents, providing benefits to both parties.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] A user accesses the server using their device to search for trainers with specialized skills and practical experience, and enters their search criteria. The server receives this information and prepares to query its database.

[0233] Step 2:

[0234] Based on the search criteria received by the server, it extracts suitable trainer candidates from the database and generates a recommendation list. The server then sends this list to the user's terminal.

[0235] Step 3:

[0236] The user selects the most suitable trainer from a list and adjusts the date, time, and content of the training session. The user then sends this information to the server via their device.

[0237] Step 4:

[0238] The server confirms the training session schedule and sends confirmation notifications to both the trainer and the user. At this point, the necessary infrastructure is set up.

[0239] Step 5:

[0240] The user and trainer begin an online session using their devices at a designated time. The server establishes the connection for this session and supports communication via video calls and chat functions.

[0241] Step 6:

[0242] A trainer instructs an AI agent on specific skills and knowledge via a terminal, and provides the user with feedback and progress information generated during the process. The server records this information.

[0243] Step 7:

[0244] After the session ends, the user sends an evaluation from their device to the server, indicating the degree of improvement in the AI ​​agent's abilities and their assessment of the trainer's instruction. The server stores this evaluation in a database and calculates the trainer's compensation.

[0245] Step 8:

[0246] The server initiates the process of paying the trainer based on their performance and reflects the reward information in the trainer's account. This completes the training cycle.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] In today's information society, having efficient means of training and education is crucial, especially in fields requiring specialized skills and knowledge. However, users often struggle to effectively find educators suited to their needs, and methods for objectively evaluating educational progress and outcomes and reflecting this in compensation are limited. A system that addresses these challenges is necessary.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes an information management means for users to register information by inputting their specialized skills and practical experience, a selection means for the server to search for educators based on conditions specified by the user and list appropriate candidates, and a means having a communication function that allows users and educators to conduct online learning sessions via a terminal. This makes it possible to efficiently match and implement specialized education, and to appropriately determine educators' compensation based on results.

[0252] An "information management system" is a method that has the function of registering information by inputting specialized skills and practical experience from users.

[0253] The "selection method" refers to a technique in which the server searches for suitable educators based on conditions specified by the user and lists the candidates.

[0254] "Communication functionality" refers to technology that provides the ability for users and educators to conduct online learning sessions through a terminal.

[0255] A "learning session" is an online educational activity conducted by users and educators to transmit specific skills or knowledge.

[0256] "Provision of rewards" refers to the act of a server providing monetary or other incentives based on the results of the educator's teaching.

[0257] This invention is a system that efficiently matches educators with specialized knowledge and skills with users to support online learning. Specific embodiments are described below.

[0258] Users utilize information management tools to register their professional skills and practical experience. This is supported by a database management system (DBMS), and users can input data via a terminal. The entered data is used for matching in subsequent processes.

[0259] The server searches for suitable educators based on the conditions entered by the user. This selection method utilizes SQL queries to list educators that match the criteria from the database. For example, if a user specifies their preference using keywords such as "educator who can teach the latest market analysis techniques," the server will select educators that match that description.

[0260] The device provides communication capabilities for users and educators to communicate. This utilizes video calls and chat systems. Users can learn online with selected educators. These sessions proceed in real time, and the educational content is recorded digitally.

[0261] The server records the progress of learning sessions and stores it in a database along with user ratings. This rating information is used as a reference for future matching. Furthermore, the evaluation of the learning content is an important indicator when determining compensation for educators. Compensation is determined through an automated system and provided appropriately to educators.

[0262] As a concrete example, a prompt might read, "Please find a suitable educator to learn market analysis skills." Based on this prompt, the server lists relevant educators and presents them to the user.

[0263] This system will enable users to learn efficiently from educators with specialized knowledge, resulting in a meaningful learning experience for both parties.

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] Users input their specialized skills, work experience, and learning goals. The entered data is registered in a database using an information management system. Specifically, users access a dedicated screen on their terminal and enter their desired skills and technologies as keywords in an input form.

[0267] Step 2:

[0268] The server receives the user's input criteria and starts the search process. It searches the database for educators that match the criteria using an SQL query. In this process, filtering is performed based on the user's input criteria, and a list of suitable educators (output) is generated. Specifically, the server executes the query, extracts the results, and generates a candidate list.

[0269] Step 3:

[0270] The server presents the user with a list of candidates obtained through the search. The user then selects a desired educator from this list. Based on this selection, the server begins preparing to coordinate the schedule. Specifically, the user views the profiles of educators of interest from the list and presses the "Select" button.

[0271] Step 4:

[0272] The server uses the user's selection information to schedule the learning session. During this process, communication methods (video calls or chat systems) for conducting the learning session online are prepared. The schedule information is sent to both parties via email or push notification. Specifically, the server uses a scheduling system to determine and notify the user of an appropriate date and time.

[0273] Step 5:

[0274] The device activates the necessary communication functions during the learning session. Users and educators exchange data in real time on this device, progressing through learning via video calls and chat. Specifically, the device activates the camera and microphone and launches the communication software.

[0275] Step 6:

[0276] The server records the content and progress of the learning session. After the session ends, it collects feedback from the user and stores it in a database. This feedback is output as data used for educator evaluation and compensation calculation. Specifically, the server records the learning content in a log file and provides the user with an evaluation form.

[0277] Step 7:

[0278] The server determines the remuneration for educators based on the collected evaluation information. In calculating the remuneration, the evaluation score and the pre-set remuneration criteria are used, and based on the result, the remuneration is provided to the educator. As a specific operation, the server executes a remuneration calculation algorithm and transfers the result to the educator via a settlement system.

[0279] (Application Example 1)

[0280] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0281] The education of AI agents in current autonomous driving technology is highly specialized and is only carried out with limited resources. Therefore, there is a problem that there are few contacts with educators having specialized knowledge and skills, and the improvement of the capabilities of autonomous mobile agents is not sufficient. To solve this, efficient matching with educators having a wider range of specialized knowledge and the implementation of smooth online education sessions are required.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0283] In this invention, the server includes a storage means for registering information by the user inputting specific specialized capabilities or knowledge, a matching means for the computing device to search for educators based on the conditions specified by the user and list up suitable candidates, and a communication means having a call or chat function through which the user and the educator can conduct a training session online via the terminal. Thereby, it becomes possible to appropriately improve the capabilities of autonomous mobile agents and to realize a more highly accurate autonomous driving technology.

[0284] The "user" refers to an individual or a corporation having specific specialized knowledge or skills and desiring to search for an educator suitable for their needs and conduct training for AI agents.

[0285] "Specialized ability" refers to knowledge and skills acquired through advanced training and experience in a specific field.

[0286] "Knowledge" refers to information, understanding, and theories acquired through experience and education.

[0287] "Computing device" refers to a computer system that processes data and performs searches for educators and generates candidate lists.

[0288] "Educator" refers to a person who has specialized skills and knowledge in a specific field and plays a role in providing training to AI agents.

[0289] "Storage means" refers to a method or system for recording and storing specialized abilities and knowledge input by users.

[0290] "Matching means" refers to a method or system for sorting educator information based on user needs and listing the optimal candidates.

[0291] "Communication means" refers to a system that provides call or chat functions necessary for online interaction between users and educators.

[0292] "Autonomous mobile agent" refers to an artificial intelligence system that uses sensors and analysis functions for the environment to move independently and perform tasks.

[0293] To implement this invention, it is necessary for the user to input specialized knowledge and skills and register them in the database by means of storage. Based on that data, the server searches for educators according to the conditions specified by the user. For the search, a machine learning algorithm using Python is used to list the optimal candidates from the educator profile data. The listed candidates are displayed on the terminal used by the user.

[0294] Next, the user conducts an online training session with a selected educator via their device. The session takes place via video conferencing software such as Zoom or Google Meet, which is used as the means of communication. The educator imparts knowledge and expertise in a specific field to the AI ​​agent, thereby improving the AI ​​agent's skills necessary for autonomous navigation technology.

[0295] During a session, the server records training progress and user feedback in real time and stores it in a MySQL database. This feedback information is used to determine compensation for educators and to create a list of candidates for future sessions.

[0296] One concrete example is a scenario in which the AI ​​agent of an autonomous vehicle receives training to recognize traffic conditions and respond appropriately. An example of a prompt in this scenario would be, "Please tell me what training content is necessary for the AI ​​agent of an autonomous vehicle to accurately recognize emergency vehicles and respond appropriately." In this way, by utilizing generative AI models, AI agents can acquire more advanced decision-making capabilities.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] Users input their professional skills and knowledge into a terminal, and this information is transmitted to a server via a storage system. The input data includes their area of ​​expertise and specific skill sets. This information is registered in a database and used to select future educators.

[0300] Step 2:

[0301] The server searches for educators using a computing device based on the conditions specified by the user. The input here is the conditions and objectives of the training desired by the user, and the output is a list of educators who meet the conditions. The server uses a machine learning algorithm in Python to extract the profiles of suitable educators from the database and generate a list of candidate educators.

[0302] Step 3:

[0303] The terminal displays the list of educators received from the server to the user. The user selects a suitable educator from the displayed candidates and specifies the schedule of the desired training session and sends it to the server. The input in this step is the user's selection, and the output is the reserved session information.

[0304] Step 4:

[0305] The server sets up a communication means between the selected educator and the user and conducts an online training session. The inputs are the information of the selected educator and the user's terminal, and the output is the connected call or chat session. Zoom or Google Meet is used for this call. The educator conveys their expertise to the AI agent.

[0306] Step 5:

[0307] During the session, the server records the progress of the training and the evaluations from the user in real time. The inputs are the progress data during the education session and the evaluations by the user, and the output is the information stored in the server's evaluation database. The recorded data is used for improving the training and determining the rewards for the educators.

[0308] Step 6:

[0309] After a training session, the user evaluates the performance of the autonomous mobile agent and sends the results to the server. The input is the degree of improvement in the agent's capabilities and the user's evaluation, and the output is the evaluation value used for reward calculation. This information is also used as optimization prompts generated by the generative AI model.

[0310] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0311] In a mode of carrying out this invention, by incorporating an emotion engine into the skill transfer platform, it becomes possible to understand the user's emotional state and provide more effective training sessions.

[0312] Users access the platform via their devices and search for trainers to improve their professional skills. During this process, an emotion engine recognizes the user's emotional state from their facial expressions and voice, and helps select the most suitable trainer based on that state. For example, if a user is feeling stressed, the emotion engine can recommend a trainer with a relaxed teaching style.

[0313] During training sessions, the server analyzes the user's emotional changes in real time via an emotion engine. This information is provided to the trainer as feedback, allowing the trainer to adjust their teaching methods as needed.

[0314] When users provide feedback after a session, the emotion engine analyzes the emotional data from the session and incorporates it into the evaluation. As a result, the server more accurately measures the effectiveness of the training and adjusts the rewards for the trainer.

[0315] For example, consider a scenario where a user wants to train an AI agent to acquire advanced presentation skills. During a session that begins with the user under high stress, the emotion engine can detect the user's anxiety, allowing the trainer to provide more reassuring guidance. In this way, the user can improve their presentation skills more effectively.

[0316] This system utilizes an emotion engine to conduct AI education while considering the user's psychological factors, thereby improving the quality of training.

[0317] The following describes the processing flow.

[0318] Step 1:

[0319] The user logs into the platform using their device and searches for a trainer suitable for training the AI ​​agent. The device captures the user's voice and facial expressions and prepares to send them to the emotion engine.

[0320] Step 2:

[0321] The emotion engine analyzes the user's voice and facial expression data to estimate their emotional state at that moment. For example, it can identify emotions such as stress, anxiety, and relaxation.

[0322] Step 3:

[0323] The server searches a database based on emotional state information from the emotion engine to select the most suitable trainer for the user. It creates a list that recommends trainers with different teaching approaches depending on the user's emotional state.

[0324] Step 4:

[0325] The user selects the most suitable trainer from the recommended trainers via their device and sets the date and time for the training session. The server confirms this and notifies both parties of the schedule.

[0326] Step 5:

[0327] Once a training session begins, the device transmits the user's facial expressions and voice to the emotion engine in real time. The emotion engine analyzes this data in real time and monitors changes in the user's emotions.

[0328] Step 6:

[0329] The server provides trainers with feedback from the emotion engine, helping them adjust their instruction to match the user's emotional state. This allows trainers to maintain user focus and provide effective instruction.

[0330] Step 7:

[0331] After the session ends, the user evaluates the trainer based on their performance. During this process, the emotion engine analyzes the emotional data from the session and reflects it on the server as evaluation information.

[0332] Step 8:

[0333] The server calculates and pays trainers based on user evaluation data and emotion engine analysis. This result is also reflected in the trainer evaluation database and used for future matching.

[0334] (Example 2)

[0335] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0336] Traditional online education systems often provide standardized training without considering the user's emotional state, resulting in ineffective instruction. Furthermore, the lack of real-time information that allows educators to provide flexible instruction tailored to the user's condition can lead to a decline in the quality of education.

[0337] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0338] In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis device, means for selecting the most suitable educator, and means for providing real-time feedback to the educator and adjusting the teaching method. This makes it possible to provide optimal instruction tailored to the user's emotional state, thereby improving the quality of education.

[0339] A "user" is an individual or group that uses an educational system to improve their abilities or skills in a specific field.

[0340] A "field" refers to an area or category in which specific knowledge or skills are applied.

[0341] "Practical experience" refers to the knowledge and skills gained from actual work and activities performed by a user in a specific field.

[0342] A "data set" is a collection of information that registers a user's abilities and experience in a specific field.

[0343] "Conditions" refer to the factors and criteria that users consider when selecting a trainer.

[0344] An "educator" is someone who provides users with specific skills and knowledge, and who offers guidance and support.

[0345] A "matching mechanism" refers to a process or system in which a server searches for educators based on conditions specified by the user and lists suitable candidates.

[0346] "Telecommunication" refers to a method of communication that transmits information electronically, transcending physical distance.

[0347] "Communication functionality" refers to features that enable users and educators to exchange information online.

[0348] "Compensation" refers to money or other valuable benefits paid to educators for the instruction or services they provide.

[0349] An "emotion analysis device" is a technology or device that identifies and analyzes a user's emotions from their facial expressions and voice.

[0350] "Analysis" is the act or process of breaking down data and understanding its structure and meaning.

[0351] "Feedback" refers to evaluation information, including emotional states, that educators use to adjust their teaching methods based on real-time information.

[0352] "Teaching methods" refer to the educational approaches and strategies that educators use with users.

[0353] To implement this invention, a server, terminal, and user collaborate to operate the system. The server incorporates an emotion analysis device, enabling real-time analysis of the user's emotional state. Specifically, the server uses technologies such as facial recognition software and voice analysis software to analyze the user's emotions in detail and selects the most appropriate educator based on the results. It also continuously monitors changes in the user's emotions during the lesson and provides feedback to the educator. The educator adjusts their teaching methods based on this feedback to provide the user with the optimal learning experience.

[0354] The terminal serves as a means for users to access the system and captures facial expressions and voice data through its camera and microphone. This data is sent to a server and used for analysis. The terminal is equipped with calling and chat functions for users and educators to communicate online, enabling efficient exchange of educational content via remote communication.

[0355] Users register information in the system using their devices to improve their abilities and skills in specific areas. At every step the user experiences, the results of sentiment analysis are used to provide personalized learning support, maximizing the user's skill improvement.

[0356] As a concrete example, if a user wants to improve their presentation skills, they can start training through their device. Once the session begins, the server can detect the user's anxiety level through an emotion analysis device and recommend an educator with a relaxed teaching style. As a result, the user can develop their skills smoothly without feeling pressured.

[0357] A concrete example of a prompt might be, "Please describe an educational system that can adjust its teaching style according to the user's emotional state." This aims to improve the overall effectiveness of the system by emphasizing an educational approach based on the user's emotions.

[0358] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0359] Step 1:

[0360] Users access the skill transfer platform using a terminal and input information about a specific field. This input includes the user's current abilities, target skill level, and desired training content. This data is registered in a database and used as foundational information for subsequent processes.

[0361] Step 2:

[0362] The terminal transmits user information to the server based on registered data. The server receives this information and uses an emotion analysis device to analyze the user's facial expressions and voice data captured from the camera and microphone. This analysis recognizes the user's emotional state (e.g., tension, stress, relaxation) and extracts it as data.

[0363] Step 3:

[0364] The server uses the sentiment analysis results to select the most suitable educator. Specifically, it searches the educator database using a matching mechanism and lists the educators best suited to the user's emotional state and preferences. This result is output to the terminal as a recommendation list.

[0365] Step 4:

[0366] The user reviews the recommended list of educators on their device and selects their preferred educator. The selected educator's information is sent to the server, and the training session schedule is finalized.

[0367] Step 5:

[0368] Once a training session begins, the server continuously monitors the user's emotional state via an emotion analysis device. Real-time emotional data is provided as feedback from the server to the educator, who then adjusts their teaching methods based on this feedback.

[0369] Step 6:

[0370] After the session ends, the user enters their training evaluation on their device. The server integrates this evaluation with sentiment data from the session to assess the educator's performance. Based on these results, the educator's reward is determined and recorded as feedback that will be reflected in the user's future training.

[0371] (Application Example 2)

[0372] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0373] Traditional training systems had the problem of not maximizing the effectiveness of instruction because they provided uniform instruction without considering the emotional state of the user. Furthermore, there was a lack of means to provide instructors with immediate, emotion-based feedback, making it difficult to appropriately adjust instruction methods. In addition, there were no criteria to accurately determine whether the instruction content was suitable for improving the learner's abilities.

[0374] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0375] In this invention, the server includes means having an information storage device, selection means, means having a communication function, means for analyzing emotional states using an emotion recognition device, and means for providing rewards to instructors. This enables more effective instruction based on the user's emotions, and allows instructors to adjust their instruction methods in real time. Furthermore, it enables accurate evaluation of the effectiveness of instruction and determination of rewards based on that evaluation.

[0376] An "information storage device" is a device that allows a user to input specific abilities or knowledge and save that information.

[0377] The "selection method" refers to a means of searching for suitable instructors based on the conditions specified by the user and listing the candidates.

[0378] "Communication function" refers to the ability to make calls or communicate via the device to allow users and instructors to conduct online training sessions.

[0379] An "emotion recognition device" is a device that analyzes the user's emotional state and provides the results to the instructor.

[0380] "Means of providing rewards" refers to means of rewarding instructors based on the progress and evaluation of training sessions.

[0381] In this embodiment of the invention, an information processing device plays a central role in realizing the training system. The information storage device is a data recording device that receives and stores data for users to register specific abilities and knowledge. The server uses selection means to select the most suitable instructor based on the registered information. This selection process is realized by combining a search algorithm and data mining technology. By utilizing Microsoft Azure or Amazon Web Services, scalable and efficient selection can be achieved.

[0382] During training, the device connects the user and instructor using its communication functions. This function supports voice and video calls over the internet, enabling real-time communication. The device also works in conjunction with an emotion recognition device to recognize the user's emotional state. This device collects data from the user's facial expressions and voice, and passes it to an emotion analysis API to determine the user's emotions.

[0383] The server provides information to instructors based on data obtained from emotion recognition devices, enabling instructors to provide appropriate guidance tailored to the user's emotions. This data can be processed, for example, using Python, and then displayed on a dashboard.

[0384] For example, if it is determined that an elderly person needs relaxation, the server suggests a music session and transmits this information to the instructor via the terminal. This type of application enables efficient and humane care.

[0385] An example of a prompt for a generative AI model would be: "Recognize the smiles of elderly people and determine the emotion behind those smiles. Based on the discovered emotion, suggest appropriate care actions."

[0386] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0387] Step 1:

[0388] The server receives specific abilities and knowledge registered by the user in the information storage device. Based on this input data, the server processes the information and saves it to the database. During this process, data verification is performed to confirm the accuracy and format of the information, and a list of registered information is compiled.

[0389] Step 2:

[0390] The user enters the desired criteria for a coach. The server searches for coach information in the existing database based on these criteria. Using a selection algorithm, it lists the coaches that best match the criteria and generates output providing this information to the user. The database search is performed using SQL queries.

[0391] Step 3:

[0392] The terminal initiates a connection with the instructors listed by the selection method. Communication functions allow users and instructors to communicate in real time. During this process, audio and video data are transmitted and received. Video stream data is compressed and efficiently transmitted over the network.

[0393] Step 4:

[0394] The user's device uses a built-in emotion recognition device to capture the user's facial expressions and voice, and sends this data to the server. The server inputs the received data into an emotion analysis API to analyze the user's emotional state. It outputs the analysis results and provides feedback to the instructor in real time. This allows the instructor to adjust their teaching methods according to the situation.

[0395] Step 5:

[0396] The server records all session data and analyzes training progress and results. It evaluates instructors based on user ratings and sentiment data, and uses the results to determine instructor rewards. Data analysis is performed at this stage, and the results are processed by a reward calculation algorithm.

[0397] Step 6:

[0398] After the user ends the session, the server saves all processing results to an information storage device. This data serves as the basis for selecting the next instructor and improving the session. The prompts to the generated AI model are updated as needed to facilitate interventions optimized for the user's environment.

[0399] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] In an embodiment of this invention, the platform consists of a user, a trainer, a server, and a terminal. When a user wants to train an AI agent using their professional skills and practical experience, they first access the platform to find a trainer that meets their needs. Upon receiving the search criteria from the user, the server generates the most suitable candidates based on trainer information in the database.

[0416] The user selects a trainer via their device and schedules a session. Based on this, the server schedules the training session and notifies both parties. The training is conducted online via video calls and chat through the device. The trainer conveys specific skills and know-how to the AI ​​agent and provides education while monitoring progress.

[0417] During the training session, the server records the instruction content and progress. After the session ends, the user evaluates the degree of improvement in the AI ​​agent's abilities, and this evaluation is sent to the server. Based on this evaluation, the server determines the trainer's compensation and provides financial incentives.

[0418] As a concrete example, suppose a user is developing an AI agent specializing in the financial industry. If this user wants to teach the AI ​​the latest market analysis techniques, they would search for a trainer knowledgeable in market trends on the platform. The selected trainer would then teach the AI ​​using their own analysis methods and tools. As a result, the AI ​​can improve the accuracy of its market analysis in a short period of time, and the user can achieve greater efficiency in financial operations.

[0419] This system makes it possible to efficiently convey the expertise of trainers with specialized knowledge to AI agents, providing benefits to both parties.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] A user accesses the server using their device to search for trainers with specialized skills and practical experience, and enters their search criteria. The server receives this information and prepares to query its database.

[0423] Step 2:

[0424] Based on the search criteria received by the server, it extracts suitable trainer candidates from the database and generates a recommendation list. The server then sends this list to the user's terminal.

[0425] Step 3:

[0426] The user selects the most suitable trainer from a list and adjusts the date, time, and content of the training session. The user then sends this information to the server via their device.

[0427] Step 4:

[0428] The server confirms the training session schedule and sends confirmation notifications to both the trainer and the user. At this point, the necessary infrastructure is set up.

[0429] Step 5:

[0430] The user and trainer begin an online session using their devices at a designated time. The server establishes the connection for this session and supports communication via video calls and chat functions.

[0431] Step 6:

[0432] A trainer instructs an AI agent on specific skills and knowledge via a terminal, and provides the user with feedback and progress information generated during the process. The server records this information.

[0433] Step 7:

[0434] After the session ends, the user sends an evaluation from their device to the server, indicating the degree of improvement in the AI ​​agent's abilities and their assessment of the trainer's instruction. The server stores this evaluation in a database and calculates the trainer's compensation.

[0435] Step 8:

[0436] The server initiates the process of paying the trainer based on their performance and reflects the reward information in the trainer's account. This completes the training cycle.

[0437] (Example 1)

[0438] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0439] In today's information society, having efficient means of training and education is crucial, especially in fields requiring specialized skills and knowledge. However, users often struggle to effectively find educators suited to their needs, and methods for objectively evaluating educational progress and outcomes and reflecting this in compensation are limited. A system that addresses these challenges is necessary.

[0440] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0441] In this invention, the server includes an information management means for users to register information by inputting their specialized skills and practical experience, a selection means for the server to search for educators based on conditions specified by the user and list appropriate candidates, and a means having a communication function that allows users and educators to conduct online learning sessions via a terminal. This makes it possible to efficiently match and implement specialized education, and to appropriately determine educators' compensation based on results.

[0442] An "information management system" is a method that has the function of registering information by inputting specialized skills and practical experience from users.

[0443] The "selection method" refers to a technique in which the server searches for suitable educators based on conditions specified by the user and lists the candidates.

[0444] "Communication functionality" refers to technology that provides the ability for users and educators to conduct online learning sessions through a terminal.

[0445] A "learning session" is an online educational activity conducted by users and educators to transmit specific skills or knowledge.

[0446] "Provision of rewards" refers to the act of a server providing monetary or other incentives based on the results of the educator's teaching.

[0447] This invention is a system that efficiently matches educators with specialized knowledge and skills with users to support online learning. Specific embodiments are described below.

[0448] Users utilize information management tools to register their professional skills and practical experience. This is supported by a database management system (DBMS), and users can input data via a terminal. The entered data is used for matching in subsequent processes.

[0449] The server searches for suitable educators based on the conditions entered by the user. This selection method utilizes SQL queries to list educators that match the criteria from the database. For example, if a user specifies their preference using keywords such as "educator who can teach the latest market analysis techniques," the server will select educators that match that description.

[0450] The device provides communication capabilities for users and educators to communicate. This utilizes video calls and chat systems. Users can learn online with selected educators. These sessions proceed in real time, and the educational content is recorded digitally.

[0451] The server records the progress of learning sessions and stores it in a database along with user ratings. This rating information is used as a reference for future matching. Furthermore, the evaluation of the learning content is an important indicator when determining compensation for educators. Compensation is determined through an automated system and provided appropriately to educators.

[0452] As a concrete example, a prompt might read, "Please find a suitable educator to learn market analysis skills." Based on this prompt, the server lists relevant educators and presents them to the user.

[0453] This system will enable users to learn efficiently from educators with specialized knowledge, resulting in a meaningful learning experience for both parties.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] Users input their specialized skills, work experience, and learning goals. The entered data is registered in a database using an information management system. Specifically, users access a dedicated screen on their terminal and enter their desired skills and technologies as keywords in an input form.

[0457] Step 2:

[0458] The server receives the user's input criteria and starts the search process. It searches the database for educators that match the criteria using an SQL query. In this process, filtering is performed based on the user's input criteria, and a list of suitable educators (output) is generated. Specifically, the server executes the query, extracts the results, and generates a candidate list.

[0459] Step 3:

[0460] The server presents the user with a list of candidates obtained through the search. The user then selects a desired educator from this list. Based on this selection, the server begins preparing to coordinate the schedule. Specifically, the user views the profiles of educators of interest from the list and presses the "Select" button.

[0461] Step 4:

[0462] The server uses the user's selection information to schedule the learning session. During this process, communication methods (video calls or chat systems) for conducting the learning session online are prepared. The schedule information is sent to both parties via email or push notification. Specifically, the server uses a scheduling system to determine and notify the user of an appropriate date and time.

[0463] Step 5:

[0464] The device activates the necessary communication functions during the learning session. Users and educators exchange data in real time on this device, progressing through learning via video calls and chat. Specifically, the device activates the camera and microphone and launches the communication software.

[0465] Step 6:

[0466] The server records the content and progress of the learning session. After the session ends, it collects feedback from the user and stores it in a database. This feedback is output as data used for educator evaluation and compensation calculation. Specifically, the server records the learning content in a log file and provides the user with an evaluation form.

[0467] Step 7:

[0468] The server determines the reward for educators based on the collected evaluation information. The reward calculation uses the evaluation score and pre-set reward criteria, and the reward is provided to the educators based on the result. Specifically, the server executes the reward calculation algorithm and sends the result to the educators via the payment system.

[0469] (Application Example 1)

[0470] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0471] Currently, training AI agents in autonomous driving technology is highly specialized and conducted with limited resources. This results in limited contact with educators possessing the necessary expertise, leading to insufficient improvement in the capabilities of autonomous mobile agents. To address this, efficient matching with educators possessing a broader range of expertise and the smooth implementation of online training sessions are required.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0473] In this invention, the server includes storage means for registering information by inputting specific professional skills and knowledge from the user, matching means for a computing device to search for educators based on conditions specified by the user and list suitable candidates, and communication means having a call or chat function that allows the user and educator to conduct training sessions online via a terminal. This enables appropriate improvement of the capabilities of the autonomous mobile agent and the realization of more accurate autonomous driving technology.

[0474] A "user" refers to an individual or corporation that possesses specific expertise or skills and wishes to find an educator suited to their needs to train an AI agent.

[0475] "Specialized competence" refers to knowledge and skills acquired through advanced training and experience in a particular field.

[0476] "Knowledge" refers to information, understanding, and theories acquired through experience and education.

[0477] A "computational device" refers to a computer system used to process data and to search for educators and generate candidate lists.

[0478] An "educator" refers to a person who possesses specialized skills and knowledge in a particular field and whose role is to provide training to AI agents.

[0479] "Storage means" refers to a method or system for recording and retaining professional skills and knowledge entered by users.

[0480] "Integration means" refers to a method or system for organizing educator information based on user needs and listing the most suitable candidates.

[0481] "Communication methods" refers to systems that provide the necessary call or chat functions for users and educators to interact online.

[0482] An "autonomous mobile agent" refers to an artificial intelligence system that has the ability to move independently and perform tasks by utilizing sensors and analytical functions for its environment.

[0483] To implement this invention, users must input their specialized knowledge and skills and register them in a database using a storage means. The server then searches for educators based on the user's specified conditions using this data. A machine learning algorithm using Python is employed for the search, listing the most suitable candidates from the educators' profile data. The listed candidates are displayed on the user's terminal.

[0484] Next, the user conducts an online training session with a selected educator via their device. The session takes place via video conferencing software such as Zoom or Google Meet, which is used as the means of communication. The educator imparts knowledge and expertise in a specific field to the AI ​​agent, thereby improving the AI ​​agent's skills necessary for autonomous navigation technology.

[0485] During a session, the server records training progress and user feedback in real time and stores it in a MySQL database. This feedback information is used to determine compensation for educators and to create a list of candidates for future sessions.

[0486] One concrete example is a scenario in which the AI ​​agent of an autonomous vehicle receives training to recognize traffic conditions and respond appropriately. An example of a prompt in this scenario would be, "Please tell me what training content is necessary for the AI ​​agent of an autonomous vehicle to accurately recognize emergency vehicles and respond appropriately." In this way, by utilizing generative AI models, AI agents can acquire more advanced decision-making capabilities.

[0487] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0488] Step 1:

[0489] Users input their professional skills and knowledge into a terminal, and this information is transmitted to a server via a storage system. The input data includes their area of ​​expertise and specific skill sets. This information is registered in a database and used to select future educators.

[0490] Step 2:

[0491] The server uses computing power to search for educators based on the conditions specified by the user. The input here is the training conditions and objectives desired by the user, and the output is a list of educators that meet the conditions. The server uses a Python machine learning algorithm to extract profiles of suitable educators from the database and generate a list of candidate educators.

[0492] Step 3:

[0493] The terminal displays a list of educators received from the server to the user. The user selects an appropriate educator from the displayed candidates, specifies the desired training session date, and sends it to the server. The input in this step is the user's selection, and the output is the reserved session information.

[0494] Step 4:

[0495] The server sets up communication between the selected educator and user and conducts online training sessions. Inputs include the device information of the selected educator and user, and output is the connected call or chat session. Zoom or Google Meet is used for these calls. The educator transmits their expertise to the AI ​​agent.

[0496] Step 5:

[0497] During a session, the server records training progress and user feedback in real time. Inputs are progress data and user feedback during the training session, while output is information stored in the server's evaluation database. The recorded data is used to improve training and determine compensation for educators.

[0498] Step 6:

[0499] After a training session, the user evaluates the performance of the autonomous mobile agent and sends the results to the server. The input is the degree of improvement in the agent's capabilities and the user's evaluation, and the output is the evaluation value used for reward calculation. This information is also used as optimization prompts generated by the generative AI model.

[0500] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0501] In a mode of carrying out this invention, by incorporating an emotion engine into the skill transfer platform, it becomes possible to understand the user's emotional state and provide more effective training sessions.

[0502] Users access the platform via their devices and search for trainers to improve their professional skills. During this process, an emotion engine recognizes the user's emotional state from their facial expressions and voice, and helps select the most suitable trainer based on that state. For example, if a user is feeling stressed, the emotion engine can recommend a trainer with a relaxed teaching style.

[0503] During training sessions, the server analyzes the user's emotional changes in real time via an emotion engine. This information is provided to the trainer as feedback, allowing the trainer to adjust their teaching methods as needed.

[0504] When users provide feedback after a session, the emotion engine analyzes the emotional data from the session and incorporates it into the evaluation. As a result, the server more accurately measures the effectiveness of the training and adjusts the rewards for the trainer.

[0505] For example, consider a scenario where a user wants to train an AI agent to acquire advanced presentation skills. During a session that begins with the user under high stress, the emotion engine can detect the user's anxiety, allowing the trainer to provide more reassuring guidance. In this way, the user can improve their presentation skills more effectively.

[0506] This system utilizes an emotion engine to conduct AI education while considering the user's psychological factors, thereby improving the quality of training.

[0507] The following describes the processing flow.

[0508] Step 1:

[0509] The user logs into the platform using their device and searches for a trainer suitable for training the AI ​​agent. The device captures the user's voice and facial expressions and prepares to send them to the emotion engine.

[0510] Step 2:

[0511] The emotion engine analyzes the user's voice and facial expression data to estimate their emotional state at that moment. For example, it can identify emotions such as stress, anxiety, and relaxation.

[0512] Step 3:

[0513] The server searches a database based on emotional state information from the emotion engine to select the most suitable trainer for the user. It creates a list that recommends trainers with different teaching approaches depending on the user's emotional state.

[0514] Step 4:

[0515] The user selects the most suitable trainer from the recommended trainers via their device and sets the date and time for the training session. The server confirms this and notifies both parties of the schedule.

[0516] Step 5:

[0517] Once a training session begins, the device transmits the user's facial expressions and voice to the emotion engine in real time. The emotion engine analyzes this data in real time and monitors changes in the user's emotions.

[0518] Step 6:

[0519] The server provides trainers with feedback from the emotion engine, helping them adjust their instruction to match the user's emotional state. This allows trainers to maintain user focus and provide effective instruction.

[0520] Step 7:

[0521] After the session ends, the user evaluates the trainer based on their performance. During this process, the emotion engine analyzes the emotional data from the session and reflects it on the server as evaluation information.

[0522] Step 8:

[0523] The server calculates and pays trainers based on user evaluation data and emotion engine analysis. This result is also reflected in the trainer evaluation database and used for future matching.

[0524] (Example 2)

[0525] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0526] Traditional online education systems often provide standardized training without considering the user's emotional state, resulting in ineffective instruction. Furthermore, the lack of real-time information that allows educators to provide flexible instruction tailored to the user's condition can lead to a decline in the quality of education.

[0527] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0528] In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis device, means for selecting the most suitable educator, and means for providing real-time feedback to the educator and adjusting the teaching method. This makes it possible to provide optimal instruction tailored to the user's emotional state, thereby improving the quality of education.

[0529] A "user" is an individual or group that uses an educational system to improve their abilities or skills in a specific field.

[0530] A "field" refers to an area or category in which specific knowledge or skills are applied.

[0531] "Practical experience" refers to the knowledge and skills gained from actual work and activities performed by a user in a specific field.

[0532] A "data set" is a collection of information that registers a user's abilities and experience in a specific field.

[0533] "Conditions" refer to the factors and criteria that users consider when selecting a trainer.

[0534] An "educator" is someone who provides users with specific skills and knowledge, and who offers guidance and support.

[0535] A "matching mechanism" refers to a process or system in which a server searches for educators based on conditions specified by the user and lists suitable candidates.

[0536] "Telecommunication" refers to a method of communication that transmits information electronically, transcending physical distance.

[0537] "Communication functionality" refers to features that enable users and educators to exchange information online.

[0538] "Compensation" refers to money or other valuable benefits paid to educators for the instruction or services they provide.

[0539] An "emotion analysis device" is a technology or device that identifies and analyzes a user's emotions from their facial expressions and voice.

[0540] "Analysis" is the act or process of breaking down data and understanding its structure and meaning.

[0541] "Feedback" refers to evaluation information, including emotional states, that educators use to adjust their teaching methods based on real-time information.

[0542] "Teaching methods" refer to the educational approaches and strategies that educators use with users.

[0543] To implement this invention, a server, terminal, and user collaborate to operate the system. The server incorporates an emotion analysis device, enabling real-time analysis of the user's emotional state. Specifically, the server uses technologies such as facial recognition software and voice analysis software to analyze the user's emotions in detail and selects the most appropriate educator based on the results. It also continuously monitors changes in the user's emotions during the lesson and provides feedback to the educator. The educator adjusts their teaching methods based on this feedback to provide the user with the optimal learning experience.

[0544] The terminal serves as a means for users to access the system and captures facial expressions and voice data through its camera and microphone. This data is sent to a server and used for analysis. The terminal is equipped with calling and chat functions for users and educators to communicate online, enabling efficient exchange of educational content via remote communication.

[0545] Users register information in the system using their devices to improve their abilities and skills in specific areas. At every step the user experiences, the results of sentiment analysis are used to provide personalized learning support, maximizing the user's skill improvement.

[0546] As a concrete example, if a user wants to improve their presentation skills, they can start training through their device. Once the session begins, the server can detect the user's anxiety level through an emotion analysis device and recommend an educator with a relaxed teaching style. As a result, the user can develop their skills smoothly without feeling pressured.

[0547] A concrete example of a prompt might be, "Please describe an educational system that can adjust its teaching style according to the user's emotional state." This aims to improve the overall effectiveness of the system by emphasizing an educational approach based on the user's emotions.

[0548] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0549] Step 1:

[0550] Users access the skill transfer platform using a terminal and input information about a specific field. This input includes the user's current abilities, target skill level, and desired training content. This data is registered in a database and used as foundational information for subsequent processes.

[0551] Step 2:

[0552] The terminal transmits user information to the server based on registered data. The server receives this information and uses an emotion analysis device to analyze the user's facial expressions and voice data captured from the camera and microphone. This analysis recognizes the user's emotional state (e.g., tension, stress, relaxation) and extracts it as data.

[0553] Step 3:

[0554] The server uses the sentiment analysis results to select the most suitable educator. Specifically, it searches the educator database using a matching mechanism and lists the educators best suited to the user's emotional state and preferences. This result is output to the terminal as a recommendation list.

[0555] Step 4:

[0556] The user reviews the recommended list of educators on their device and selects their preferred educator. The selected educator's information is sent to the server, and the training session schedule is finalized.

[0557] Step 5:

[0558] Once a training session begins, the server continuously monitors the user's emotional state via an emotion analysis device. Real-time emotional data is provided as feedback from the server to the educator, who then adjusts their teaching methods based on this feedback.

[0559] Step 6:

[0560] After the session ends, the user enters their training evaluation on their device. The server integrates this evaluation with sentiment data from the session to assess the educator's performance. Based on these results, the educator's reward is determined and recorded as feedback that will be reflected in the user's future training.

[0561] (Application Example 2)

[0562] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0563] Traditional training systems had the problem of not maximizing the effectiveness of instruction because they provided uniform instruction without considering the emotional state of the user. Furthermore, there was a lack of means to provide instructors with immediate, emotion-based feedback, making it difficult to appropriately adjust instruction methods. In addition, there were no criteria to accurately determine whether the instruction content was suitable for improving the learner's abilities.

[0564] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0565] In this invention, the server includes means having an information storage device, selection means, means having a communication function, means for analyzing emotional states using an emotion recognition device, and means for providing rewards to instructors. This enables more effective instruction based on the user's emotions, and allows instructors to adjust their instruction methods in real time. Furthermore, it enables accurate evaluation of the effectiveness of instruction and determination of rewards based on that evaluation.

[0566] An "information storage device" is a device that allows a user to input specific abilities or knowledge and save that information.

[0567] The "selection method" refers to a means of searching for suitable instructors based on the conditions specified by the user and listing the candidates.

[0568] "Communication function" refers to the ability to make calls or communicate via the device to allow users and instructors to conduct online training sessions.

[0569] An "emotion recognition device" is a device that analyzes the user's emotional state and provides the results to the instructor.

[0570] "Means of providing rewards" refers to means of rewarding instructors based on the progress and evaluation of training sessions.

[0571] In this embodiment of the invention, an information processing device plays a central role in realizing the training system. The information storage device is a data recording device that receives and stores data for users to register specific abilities and knowledge. The server uses selection means to select the most suitable instructor based on the registered information. This selection process is realized by combining a search algorithm and data mining technology. By utilizing Microsoft Azure or Amazon Web Services, scalable and efficient selection can be achieved.

[0572] During training, the device connects the user and instructor using its communication functions. This function supports voice and video calls over the internet, enabling real-time communication. The device also works in conjunction with an emotion recognition device to recognize the user's emotional state. This device collects data from the user's facial expressions and voice, and passes it to an emotion analysis API to determine the user's emotions.

[0573] The server provides information to instructors based on data obtained from emotion recognition devices, enabling instructors to provide appropriate guidance tailored to the user's emotions. This data can be processed, for example, using Python, and then displayed on a dashboard.

[0574] For example, if it is determined that an elderly person needs relaxation, the server suggests a music session and transmits this information to the instructor via the terminal. This type of application enables efficient and humane care.

[0575] An example of a prompt for a generative AI model would be: "Recognize the smiles of elderly people and determine the emotion behind those smiles. Based on the discovered emotion, suggest appropriate care actions."

[0576] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0577] Step 1:

[0578] The server receives specific abilities and knowledge registered by the user in the information storage device. Based on this input data, the server processes the information and saves it to the database. During this process, data verification is performed to confirm the accuracy and format of the information, and a list of registered information is compiled.

[0579] Step 2:

[0580] The user enters the desired criteria for a coach. The server searches for coach information in the existing database based on these criteria. Using a selection algorithm, it lists the coaches that best match the criteria and generates output providing this information to the user. The database search is performed using SQL queries.

[0581] Step 3:

[0582] The terminal initiates a connection with the instructors listed by the selection method. Communication functions allow users and instructors to communicate in real time. During this process, audio and video data are transmitted and received. Video stream data is compressed and efficiently transmitted over the network.

[0583] Step 4:

[0584] The user's device uses a built-in emotion recognition device to capture the user's facial expressions and voice, and sends this data to the server. The server inputs the received data into an emotion analysis API to analyze the user's emotional state. It outputs the analysis results and provides feedback to the instructor in real time. This allows the instructor to adjust their teaching methods according to the situation.

[0585] Step 5:

[0586] The server records all session data and analyzes training progress and results. It evaluates instructors based on user ratings and sentiment data, and uses the results to determine instructor rewards. Data analysis is performed at this stage, and the results are processed by a reward calculation algorithm.

[0587] Step 6:

[0588] After the user ends the session, the server saves all processing results to an information storage device. This data serves as the basis for selecting the next instructor and improving the session. The prompts to the generated AI model are updated as needed to facilitate interventions optimized for the user's environment.

[0589] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0590] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0591] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0592] [Fourth Embodiment]

[0593] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0594] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0595] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0596] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0597] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0598] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0599] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0600] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0601] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0602] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0603] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0604] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0605] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] In an embodiment of this invention, the platform consists of a user, a trainer, a server, and a terminal. When a user wants to train an AI agent using their professional skills and practical experience, they first access the platform to find a trainer that meets their needs. Upon receiving the search criteria from the user, the server generates the most suitable candidates based on trainer information in the database.

[0607] The user selects a trainer via their device and schedules a session. Based on this, the server schedules the training session and notifies both parties. The training is conducted online via video calls and chat through the device. The trainer conveys specific skills and know-how to the AI ​​agent and provides education while monitoring progress.

[0608] During the training session, the server records the instruction content and progress. After the session ends, the user evaluates the degree of improvement in the AI ​​agent's abilities, and this evaluation is sent to the server. Based on this evaluation, the server determines the trainer's compensation and provides financial incentives.

[0609] As a concrete example, suppose a user is developing an AI agent specializing in the financial industry. If this user wants to teach the AI ​​the latest market analysis techniques, they would search for a trainer knowledgeable in market trends on the platform. The selected trainer would then teach the AI ​​using their own analysis methods and tools. As a result, the AI ​​can improve the accuracy of its market analysis in a short period of time, and the user can achieve greater efficiency in financial operations.

[0610] This system makes it possible to efficiently convey the expertise of trainers with specialized knowledge to AI agents, providing benefits to both parties.

[0611] The following describes the processing flow.

[0612] Step 1:

[0613] A user accesses the server using their device to search for trainers with specialized skills and practical experience, and enters their search criteria. The server receives this information and prepares to query its database.

[0614] Step 2:

[0615] Based on the search criteria received by the server, it extracts suitable trainer candidates from the database and generates a recommendation list. The server then sends this list to the user's terminal.

[0616] Step 3:

[0617] The user selects the most suitable trainer from a list and adjusts the date, time, and content of the training session. The user then sends this information to the server via their device.

[0618] Step 4:

[0619] The server confirms the training session schedule and sends confirmation notifications to both the trainer and the user. At this point, the necessary infrastructure is set up.

[0620] Step 5:

[0621] The user and trainer begin an online session using their devices at a designated time. The server establishes the connection for this session and supports communication via video calls and chat functions.

[0622] Step 6:

[0623] A trainer instructs an AI agent on specific skills and knowledge via a terminal, and provides the user with feedback and progress information generated during the process. The server records this information.

[0624] Step 7:

[0625] After the session ends, the user sends an evaluation from their device to the server, indicating the degree of improvement in the AI ​​agent's abilities and their assessment of the trainer's instruction. The server stores this evaluation in a database and calculates the trainer's compensation.

[0626] Step 8:

[0627] The server initiates the process of paying the trainer based on their performance and reflects the reward information in the trainer's account. This completes the training cycle.

[0628] (Example 1)

[0629] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] In today's information society, having efficient means of training and education is crucial, especially in fields requiring specialized skills and knowledge. However, users often struggle to effectively find educators suited to their needs, and methods for objectively evaluating educational progress and outcomes and reflecting this in compensation are limited. A system that addresses these challenges is necessary.

[0631] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0632] In this invention, the server includes an information management means for users to register information by inputting their specialized skills and practical experience, a selection means for the server to search for educators based on conditions specified by the user and list appropriate candidates, and a means having a communication function that allows users and educators to conduct online learning sessions via a terminal. This makes it possible to efficiently match and implement specialized education, and to appropriately determine educators' compensation based on results.

[0633] An "information management system" is a method that has the function of registering information by inputting specialized skills and practical experience from users.

[0634] The "selection method" refers to a technique in which the server searches for suitable educators based on conditions specified by the user and lists the candidates.

[0635] "Communication functionality" refers to technology that provides the ability for users and educators to conduct online learning sessions through a terminal.

[0636] A "learning session" is an online educational activity conducted by users and educators to transmit specific skills or knowledge.

[0637] "Provision of rewards" refers to the act of a server providing monetary or other incentives based on the results of the educator's teaching.

[0638] This invention is a system that efficiently matches educators with specialized knowledge and skills with users to support online learning. Specific embodiments are described below.

[0639] Users utilize information management tools to register their professional skills and practical experience. This is supported by a database management system (DBMS), and users can input data via a terminal. The entered data is used for matching in subsequent processes.

[0640] The server searches for suitable educators based on the conditions entered by the user. This selection method utilizes SQL queries to list educators that match the criteria from the database. For example, if a user specifies their preference using keywords such as "educator who can teach the latest market analysis techniques," the server will select educators that match that description.

[0641] The device provides communication capabilities for users and educators to communicate. This utilizes video calls and chat systems. Users can learn online with selected educators. These sessions proceed in real time, and the educational content is recorded digitally.

[0642] The server records the progress of learning sessions and stores it in a database along with user ratings. This rating information is used as a reference for future matching. Furthermore, the evaluation of the learning content is an important indicator when determining compensation for educators. Compensation is determined through an automated system and provided appropriately to educators.

[0643] As a concrete example, a prompt might read, "Please find a suitable educator to learn market analysis skills." Based on this prompt, the server lists relevant educators and presents them to the user.

[0644] This system will enable users to learn efficiently from educators with specialized knowledge, resulting in a meaningful learning experience for both parties.

[0645] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0646] Step 1:

[0647] Users input their specialized skills, work experience, and learning goals. The entered data is registered in a database using an information management system. Specifically, users access a dedicated screen on their terminal and enter their desired skills and technologies as keywords in an input form.

[0648] Step 2:

[0649] The server receives the user's input criteria and starts the search process. It searches the database for educators that match the criteria using an SQL query. In this process, filtering is performed based on the user's input criteria, and a list of suitable educators (output) is generated. Specifically, the server executes the query, extracts the results, and generates a candidate list.

[0650] Step 3:

[0651] The server presents the user with a list of candidates obtained through the search. The user then selects a desired educator from this list. Based on this selection, the server begins preparing to coordinate the schedule. Specifically, the user views the profiles of educators of interest from the list and presses the "Select" button.

[0652] Step 4:

[0653] The server uses the user's selection information to schedule the learning session. During this process, communication methods (video calls or chat systems) for conducting the learning session online are prepared. The schedule information is sent to both parties via email or push notification. Specifically, the server uses a scheduling system to determine and notify the user of an appropriate date and time.

[0654] Step 5:

[0655] The device activates the necessary communication functions during the learning session. Users and educators exchange data in real time on this device, progressing through learning via video calls and chat. Specifically, the device activates the camera and microphone and launches the communication software.

[0656] Step 6:

[0657] The server records the content and progress of the learning session. After the session ends, it collects feedback from the user and stores it in a database. This feedback is output as data used for educator evaluation and compensation calculation. Specifically, the server records the learning content in a log file and provides the user with an evaluation form.

[0658] Step 7:

[0659] The server determines the reward for educators based on the collected evaluation information. The reward calculation uses the evaluation score and pre-set reward criteria, and the reward is provided to the educators based on the result. Specifically, the server executes the reward calculation algorithm and sends the result to the educators via the payment system.

[0660] (Application Example 1)

[0661] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] Currently, training AI agents in autonomous driving technology is highly specialized and conducted with limited resources. This results in limited contact with educators possessing the necessary expertise, leading to insufficient improvement in the capabilities of autonomous mobile agents. To address this, efficient matching with educators possessing a broader range of expertise and the smooth implementation of online training sessions are required.

[0663] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0664] In this invention, the server includes storage means for registering information by inputting specific professional skills and knowledge from the user, matching means for a computing device to search for educators based on conditions specified by the user and list suitable candidates, and communication means having a call or chat function that allows the user and educator to conduct training sessions online via a terminal. This enables appropriate improvement of the capabilities of the autonomous mobile agent and the realization of more accurate autonomous driving technology.

[0665] A "user" refers to an individual or corporation that possesses specific expertise or skills and wishes to find an educator suited to their needs to train an AI agent.

[0666] "Specialized competence" refers to knowledge and skills acquired through advanced training and experience in a particular field.

[0667] "Knowledge" refers to information, understanding, and theories acquired through experience and education.

[0668] A "computational device" refers to a computer system used to process data and to search for educators and generate candidate lists.

[0669] An "educator" refers to a person who possesses specialized skills and knowledge in a particular field and whose role is to provide training to AI agents.

[0670] "Storage means" refers to a method or system for recording and retaining professional skills and knowledge entered by users.

[0671] "Integration means" refers to a method or system for organizing educator information based on user needs and listing the most suitable candidates.

[0672] "Communication methods" refers to systems that provide the necessary call or chat functions for users and educators to interact online.

[0673] An "autonomous mobile agent" refers to an artificial intelligence system that has the ability to move independently and perform tasks by utilizing sensors and analytical functions for its environment.

[0674] To implement this invention, users must input their specialized knowledge and skills and register them in a database using a storage means. The server then searches for educators based on the user's specified conditions using this data. A machine learning algorithm using Python is employed for the search, listing the most suitable candidates from the educators' profile data. The listed candidates are displayed on the user's terminal.

[0675] Next, the user conducts an online training session with a selected educator via their device. The session takes place via video conferencing software such as Zoom or Google Meet, which is used as the means of communication. The educator imparts knowledge and expertise in a specific field to the AI ​​agent, thereby improving the AI ​​agent's skills necessary for autonomous navigation technology.

[0676] During a session, the server records training progress and user feedback in real time and stores it in a MySQL database. This feedback information is used to determine compensation for educators and to create a list of candidates for future sessions.

[0677] One concrete example is a scenario in which the AI ​​agent of an autonomous vehicle receives training to recognize traffic conditions and respond appropriately. An example of a prompt in this scenario would be, "Please tell me what training content is necessary for the AI ​​agent of an autonomous vehicle to accurately recognize emergency vehicles and respond appropriately." In this way, by utilizing generative AI models, AI agents can acquire more advanced decision-making capabilities.

[0678] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0679] Step 1:

[0680] Users input their professional skills and knowledge into a terminal, and this information is transmitted to a server via a storage system. The input data includes their area of ​​expertise and specific skill sets. This information is registered in a database and used to select future educators.

[0681] Step 2:

[0682] The server uses computing power to search for educators based on the conditions specified by the user. The input here is the training conditions and objectives desired by the user, and the output is a list of educators that meet the conditions. The server uses a Python machine learning algorithm to extract profiles of suitable educators from the database and generate a list of candidate educators.

[0683] Step 3:

[0684] The terminal displays a list of educators received from the server to the user. The user selects an appropriate educator from the displayed candidates, specifies the desired training session date, and sends it to the server. The input in this step is the user's selection, and the output is the reserved session information.

[0685] Step 4:

[0686] The server sets up communication between the selected educator and user and conducts online training sessions. Inputs include the device information of the selected educator and user, and output is the connected call or chat session. Zoom or Google Meet is used for these calls. The educator transmits their expertise to the AI ​​agent.

[0687] Step 5:

[0688] During a session, the server records training progress and user feedback in real time. Inputs are progress data and user feedback during the training session, while output is information stored in the server's evaluation database. The recorded data is used to improve training and determine compensation for educators.

[0689] Step 6:

[0690] After a training session, the user evaluates the performance of the autonomous mobile agent and sends the results to the server. The input is the degree of improvement in the agent's capabilities and the user's evaluation, and the output is the evaluation value used for reward calculation. This information is also used as optimization prompts generated by the generative AI model.

[0691] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0692] In a mode of carrying out this invention, by incorporating an emotion engine into the skill transfer platform, it becomes possible to understand the user's emotional state and provide more effective training sessions.

[0693] Users access the platform via their devices and search for trainers to improve their professional skills. During this process, an emotion engine recognizes the user's emotional state from their facial expressions and voice, and helps select the most suitable trainer based on that state. For example, if a user is feeling stressed, the emotion engine can recommend a trainer with a relaxed teaching style.

[0694] During training sessions, the server analyzes the user's emotional changes in real time via an emotion engine. This information is provided to the trainer as feedback, allowing the trainer to adjust their teaching methods as needed.

[0695] When users provide feedback after a session, the emotion engine analyzes the emotional data from the session and incorporates it into the evaluation. As a result, the server more accurately measures the effectiveness of the training and adjusts the rewards for the trainer.

[0696] For example, consider a scenario where a user wants to train an AI agent to acquire advanced presentation skills. During a session that begins with the user under high stress, the emotion engine can detect the user's anxiety, allowing the trainer to provide more reassuring guidance. In this way, the user can improve their presentation skills more effectively.

[0697] This system utilizes an emotion engine to conduct AI education while considering the user's psychological factors, thereby improving the quality of training.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The user logs into the platform using their device and searches for a trainer suitable for training the AI ​​agent. The device captures the user's voice and facial expressions and prepares to send them to the emotion engine.

[0701] Step 2:

[0702] The emotion engine analyzes the user's voice and facial expression data to estimate their emotional state at that moment. For example, it can identify emotions such as stress, anxiety, and relaxation.

[0703] Step 3:

[0704] The server searches a database based on emotional state information from the emotion engine to select the most suitable trainer for the user. It creates a list that recommends trainers with different teaching approaches depending on the user's emotional state.

[0705] Step 4:

[0706] The user selects the most suitable trainer from the recommended trainers via their device and sets the date and time for the training session. The server confirms this and notifies both parties of the schedule.

[0707] Step 5:

[0708] Once a training session begins, the device transmits the user's facial expressions and voice to the emotion engine in real time. The emotion engine analyzes this data in real time and monitors changes in the user's emotions.

[0709] Step 6:

[0710] The server provides trainers with feedback from the emotion engine, helping them adjust their instruction to match the user's emotional state. This allows trainers to maintain user focus and provide effective instruction.

[0711] Step 7:

[0712] After the session ends, the user evaluates the trainer based on their performance. During this process, the emotion engine analyzes the emotional data from the session and reflects it on the server as evaluation information.

[0713] Step 8:

[0714] The server calculates and pays trainers based on user evaluation data and emotion engine analysis. This result is also reflected in the trainer evaluation database and used for future matching.

[0715] (Example 2)

[0716] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0717] Traditional online education systems often provide standardized training without considering the user's emotional state, resulting in ineffective instruction. Furthermore, the lack of real-time information that allows educators to provide flexible instruction tailored to the user's condition can lead to a decline in the quality of education.

[0718] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0719] In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis device, means for selecting the most suitable educator, and means for providing real-time feedback to the educator and adjusting the teaching method. This makes it possible to provide optimal instruction tailored to the user's emotional state, thereby improving the quality of education.

[0720] A "user" is an individual or group that uses an educational system to improve their abilities or skills in a specific field.

[0721] A "field" refers to an area or category in which specific knowledge or skills are applied.

[0722] "Practical experience" refers to the knowledge and skills gained from actual work and activities performed by a user in a specific field.

[0723] A "data set" is a collection of information that registers a user's abilities and experience in a specific field.

[0724] "Conditions" refer to the factors and criteria that users consider when selecting a trainer.

[0725] An "educator" is someone who provides users with specific skills and knowledge, and who offers guidance and support.

[0726] A "matching mechanism" refers to a process or system in which a server searches for educators based on conditions specified by the user and lists suitable candidates.

[0727] "Telecommunication" refers to a method of communication that transmits information electronically, transcending physical distance.

[0728] "Communication functionality" refers to features that enable users and educators to exchange information online.

[0729] "Compensation" refers to money or other valuable benefits paid to educators for the instruction or services they provide.

[0730] An "emotion analysis device" is a technology or device that identifies and analyzes a user's emotions from their facial expressions and voice.

[0731] "Analysis" is the act or process of breaking down data and understanding its structure and meaning.

[0732] "Feedback" refers to evaluation information, including emotional states, that educators use to adjust their teaching methods based on real-time information.

[0733] "Teaching methods" refer to the educational approaches and strategies that educators use with users.

[0734] To implement this invention, a server, terminal, and user collaborate to operate the system. The server incorporates an emotion analysis device, enabling real-time analysis of the user's emotional state. Specifically, the server uses technologies such as facial recognition software and voice analysis software to analyze the user's emotions in detail and selects the most appropriate educator based on the results. It also continuously monitors changes in the user's emotions during the lesson and provides feedback to the educator. The educator adjusts their teaching methods based on this feedback to provide the user with the optimal learning experience.

[0735] The terminal serves as a means for users to access the system and captures facial expressions and voice data through its camera and microphone. This data is sent to a server and used for analysis. The terminal is equipped with calling and chat functions for users and educators to communicate online, enabling efficient exchange of educational content via remote communication.

[0736] Users register information in the system using their devices to improve their abilities and skills in specific areas. At every step the user experiences, the results of sentiment analysis are used to provide personalized learning support, maximizing the user's skill improvement.

[0737] As a concrete example, if a user wants to improve their presentation skills, they can start training through their device. Once the session begins, the server can detect the user's anxiety level through an emotion analysis device and recommend an educator with a relaxed teaching style. As a result, the user can develop their skills smoothly without feeling pressured.

[0738] A concrete example of a prompt might be, "Please describe an educational system that can adjust its teaching style according to the user's emotional state." This aims to improve the overall effectiveness of the system by emphasizing an educational approach based on the user's emotions.

[0739] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0740] Step 1:

[0741] Users access the skill transfer platform using a terminal and input information about a specific field. This input includes the user's current abilities, target skill level, and desired training content. This data is registered in a database and used as foundational information for subsequent processes.

[0742] Step 2:

[0743] The terminal transmits user information to the server based on registered data. The server receives this information and uses an emotion analysis device to analyze the user's facial expressions and voice data captured from the camera and microphone. This analysis recognizes the user's emotional state (e.g., tension, stress, relaxation) and extracts it as data.

[0744] Step 3:

[0745] The server uses the sentiment analysis results to select the most suitable educator. Specifically, it searches the educator database using a matching mechanism and lists the educators best suited to the user's emotional state and preferences. This result is output to the terminal as a recommendation list.

[0746] Step 4:

[0747] The user reviews the recommended list of educators on their device and selects their preferred educator. The selected educator's information is sent to the server, and the training session schedule is finalized.

[0748] Step 5:

[0749] Once a training session begins, the server continuously monitors the user's emotional state via an emotion analysis device. Real-time emotional data is provided as feedback from the server to the educator, who then adjusts their teaching methods based on this feedback.

[0750] Step 6:

[0751] After the session ends, the user enters their training evaluation on their device. The server integrates this evaluation with sentiment data from the session to assess the educator's performance. Based on these results, the educator's reward is determined and recorded as feedback that will be reflected in the user's future training.

[0752] (Application Example 2)

[0753] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] Traditional training systems had the problem of not maximizing the effectiveness of instruction because they provided uniform instruction without considering the emotional state of the user. Furthermore, there was a lack of means to provide instructors with immediate, emotion-based feedback, making it difficult to appropriately adjust instruction methods. In addition, there were no criteria to accurately determine whether the instruction content was suitable for improving the learner's abilities.

[0755] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0756] In this invention, the server includes means having an information storage device, selection means, means having a communication function, means for analyzing emotional states using an emotion recognition device, and means for providing rewards to instructors. This enables more effective instruction based on the user's emotions, and allows instructors to adjust their instruction methods in real time. Furthermore, it enables accurate evaluation of the effectiveness of instruction and determination of rewards based on that evaluation.

[0757] An "information storage device" is a device that allows a user to input specific abilities or knowledge and save that information.

[0758] The "selection method" refers to a means of searching for suitable instructors based on the conditions specified by the user and listing the candidates.

[0759] "Communication function" refers to the ability to make calls or communicate via the device to allow users and instructors to conduct online training sessions.

[0760] An "emotion recognition device" is a device that analyzes the user's emotional state and provides the results to the instructor.

[0761] "Means of providing rewards" refers to means of rewarding instructors based on the progress and evaluation of training sessions.

[0762] In this embodiment of the invention, an information processing device plays a central role in realizing the training system. The information storage device is a data recording device that receives and stores data for users to register specific abilities and knowledge. The server uses selection means to select the most suitable instructor based on the registered information. This selection process is realized by combining a search algorithm and data mining technology. By utilizing Microsoft Azure or Amazon Web Services, scalable and efficient selection can be achieved.

[0763] During training, the device connects the user and instructor using its communication functions. This function supports voice and video calls over the internet, enabling real-time communication. The device also works in conjunction with an emotion recognition device to recognize the user's emotional state. This device collects data from the user's facial expressions and voice, and passes it to an emotion analysis API to determine the user's emotions.

[0764] The server provides information to instructors based on data obtained from emotion recognition devices, enabling instructors to provide appropriate guidance tailored to the user's emotions. This data can be processed, for example, using Python, and then displayed on a dashboard.

[0765] For example, if it is determined that an elderly person needs relaxation, the server suggests a music session and transmits this information to the instructor via the terminal. This type of application enables efficient and humane care.

[0766] An example of a prompt for a generative AI model would be: "Recognize the smiles of elderly people and determine the emotion behind those smiles. Based on the discovered emotion, suggest appropriate care actions."

[0767] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0768] Step 1:

[0769] The server receives specific abilities and knowledge registered by the user in the information storage device. Based on this input data, the server processes the information and saves it to the database. During this process, data verification is performed to confirm the accuracy and format of the information, and a list of registered information is compiled.

[0770] Step 2:

[0771] The user enters the desired criteria for a coach. The server searches for coach information in the existing database based on these criteria. Using a selection algorithm, it lists the coaches that best match the criteria and generates output providing this information to the user. The database search is performed using SQL queries.

[0772] Step 3:

[0773] The terminal initiates a connection with the instructors listed by the selection method. Communication functions allow users and instructors to communicate in real time. During this process, audio and video data are transmitted and received. Video stream data is compressed and efficiently transmitted over the network.

[0774] Step 4:

[0775] The user's device uses a built-in emotion recognition device to capture the user's facial expressions and voice, and sends this data to the server. The server inputs the received data into an emotion analysis API to analyze the user's emotional state. It outputs the analysis results and provides feedback to the instructor in real time. This allows the instructor to adjust their teaching methods according to the situation.

[0776] Step 5:

[0777] The server records all session data and analyzes training progress and results. It evaluates instructors based on user ratings and sentiment data, and uses the results to determine instructor rewards. Data analysis is performed at this stage, and the results are processed by a reward calculation algorithm.

[0778] Step 6:

[0779] After the user ends the session, the server saves all processing results to an information storage device. This data serves as the basis for selecting the next instructor and improving the session. The prompts to the generated AI model are updated as needed to facilitate interventions optimized for the user's environment.

[0780] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0781] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0782] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0783] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0784] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0785] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0786] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0787] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0788] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0789] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0790] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0791] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0792] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0793] 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.

[0794] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0795] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0796] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0797] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0798] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0799] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0800] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0801] The following is further disclosed regarding the embodiments described above.

[0802] (Claim 1)

[0803] A means of having a database in which users register information by inputting specific professional skills and work experience,

[0804] A matching mechanism in which the server searches for trainers based on conditions specified by the user and lists suitable candidates,

[0805] A means having a call or chat function that allows users and trainers to conduct online training sessions via a terminal,

[0806] The server records the progress of training sessions and user feedback, and provides a means to reward trainers.

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, wherein a user evaluates a trainer who possesses specific professional skills or knowledge, and this evaluation information is recorded in a database and used as reference information for the next matching.

[0810] (Claim 3)

[0811] The system according to claim 1, wherein the user evaluates the extent to which the training content provided by the trainer contributes to improving the capabilities of the AI ​​agent, and the server determines the reward for the trainer based on that evaluation.

[0812] "Example 1"

[0813] (Claim 1)

[0814] An information management system in which users register information by inputting their specialized skills and practical experience,

[0815] A selection mechanism in which the server searches for educators based on conditions specified by the user and lists suitable candidates,

[0816] A means having communication capabilities that allow users and educators to conduct online learning sessions via a terminal,

[0817] A management system in which the server records the progress of learning sessions and user evaluations, and provides rewards to educators,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, wherein users evaluate educators with specialized skills, and the evaluation information is recorded in a database and used as reference information for future selections.

[0821] (Claim 3)

[0822] The system according to claim 1, wherein a user evaluates the extent to which the learning content provided by an educator contributes to improving the capabilities of a machine learning agent, and the server determines a reward for the educator based on that evaluation.

[0823] "Application Example 1"

[0824] (Claim 1)

[0825] A means of storing information by having users input specific professional skills and knowledge,

[0826] A computing device searches for educators based on user-specified conditions and lists suitable candidates;

[0827] A communication means having a call or chat function that allows users and educators to conduct online training sessions via a terminal,

[0828] A computing device records the progress of self-driving technology training sessions and user feedback, and provides compensation to educators.

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, wherein a user evaluates an educator who possesses specific professional skills or knowledge, and the evaluation information is recorded in a storage medium and used as reference information during the next matching process.

[0832] (Claim 3)

[0833] The system according to claim 1, wherein the user evaluates the extent to which the training content provided by the educator contributes to improving the capabilities of the autonomous mobile agent, and a computing device determines a reward for the educator based on that evaluation.

[0834] "Example 2 of combining an emotion engine"

[0835] (Claim 1)

[0836] A means having a data set in which users register information by inputting their abilities and work experience in a specific field,

[0837] A matching means that the server searches for educators based on conditions specified by the user and lists suitable candidates,

[0838] A means having a communication function that allows users and educators to conduct education remotely via terminal,

[0839] The server records the progress of educational implementation and user evaluations, and provides a means to reward educators.

[0840] A server uses an emotion analysis device to analyze the user's emotional state and, based on that information, selects the most suitable educator.

[0841] A means by which a server monitors changes in users' emotions during training, provides real-time feedback to educators, and enables educators to adjust their teaching methods.

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, wherein a user evaluates the extent to which the educational content provided by an educator contributes to improving the capabilities of a program agent, and the server determines the reward for the educator based on that evaluation.

[0845] (Claim 3)

[0846] The system according to claim 1, characterized in that, in order for the user to enhance their abilities in a specific field, an emotion analysis device recognizes the user's emotional state, recommends the most suitable educator, and the educator adjusts the teaching method based on real-time emotional feedback.

[0847] "Application example 2 when combining with an emotional engine"

[0848] (Claim 1)

[0849] A means having an information storage device that registers information by having a user input specific abilities or knowledge,

[0850] A selection method in which the server searches for instructors based on conditions specified by the user and lists suitable candidates,

[0851] A means having a call or communication function that allows users and instructors to conduct online training sessions via a terminal,

[0852] A means by which a server uses an emotion recognition device during a training session to analyze the user's emotional state, provides the results to the instructor, and enables the instructor to adjust the teaching method in real time.

[0853] The server records the progress of training sessions and user evaluations, and provides a means to reward instructors.

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, wherein a user evaluates an instructor who possesses specific abilities or knowledge, and this evaluation information is recorded in an information storage device and used as reference information when selecting an instructor in the future.

[0857] (Claim 3)

[0858] The system according to claim 1, wherein the user evaluates the extent to which the training content provided by the instructor contributes to improving the capabilities of the artificial intelligence agent, and the server determines the instructor's reward based on that evaluation. [Explanation of Symbols]

[0859] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of storing information by having users input specific professional skills and knowledge, A computing device searches for educators based on user-specified conditions and lists suitable candidates; A communication means having a call or chat function that allows users and educators to conduct online training sessions via a terminal, A computing device records the progress of self-driving technology training sessions and user feedback, and provides compensation to educators. A system that includes this.

2. The system according to claim 1, wherein a user evaluates an educator who possesses specific professional skills or knowledge, and the evaluation information is recorded in a storage medium and used as reference information during the next matching process.

3. The system according to claim 1, wherein the user evaluates the extent to which the training content provided by the educator contributes to improving the capabilities of the autonomous mobile agent, and a computing device determines a reward for the educator based on that evaluation.

Images