System

Abstract

A system is provided.SOLUTION: Data input means for a user to input expertise and experience, communication means for a terminal to transmit input data to a server, data management means for the server to organize and classify the received data and store the organized and classified data in a database, AI model training means for the server to train an AI model using the stored data, and deployment means for deploying the trained AI model; A system, comprising: AI model providing means for making available to a user; registration means for a user to register as a coach; searching means for a user who wants to be coached to search for and match a coach; and session initiating means for initiating a AI coaching session based on a search result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional coaching platforms have limited means for users to effectively share their expertise and experience, making it difficult to find a suitable coach. Furthermore, it is difficult to achieve sufficient learning benefits through video materials or one-way information provision. This creates a need for even higher-quality coaching experiences in fields that require highly individualized instruction. Furthermore, there is a need for an environment that allows users with specialized knowledge to easily start providing coaching services. [Means for solving the problem]

[0005] The present invention provides a system in which a user inputs their own expertise and experience, and an AI provides coaching based on that input. The system includes a data input means for the user to input their expertise and experience, a communication means for the terminal to send the input data to a server, a data management means for the server to organize and classify the received data and store it in a database, an AI model training means for training an AI model using the stored data, an AI model provision means for deploying the trained AI model and making it available to users, a registration means for a user to register as a coach, a search means for a user seeking coaching to search for and match with a coach, and a session initiation means for starting an AI coaching session based on the search results. This system allows users to easily digitize their expertise and provide services as an AI coach based on that data. Furthermore, users seeking coaching can easily find an appropriate coach and receive high-quality coaching.

[0006] Understood. Below are definitions of important terms contained in the claims.

[0007] "Data input means" refers to an interface or tool that allows a user to input their own specialized knowledge and experience.

[0008] "Communication means" refers to the protocol or mechanism by which the terminal transmits data entered by the user to the server.

[0009] "Data management means" refers to the systems and algorithms used by the server to analyze, classify, organize, and store the data received in a database.

[0010] "AI model training methods" are processes or methods for training AI models using collected data using machine learning or deep learning techniques.

[0011] "AI model provision means" refers to infrastructure and APIs that deploy trained AI models in a form that users can use and provide their functions.

[0012] "Registration means" refers to the function or format that allows a user to register their coaching profile and areas of expertise.

[0013] A "search tool" is a search engine or matching algorithm that allows a user looking for a coach to search for and find a suitable coach.

[0014] "Session initiation means" refers to the functionality and protocols for initiating an AI coaching session after the user selects the desired coach. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention provides a system in which a user inputs their own expertise and experience and an AI provides coaching based on that input. This system includes: a data input means for the user to input their expertise and experience; a communication means for a terminal to send the input data to a server; a data management means for the server to organize and classify the data received and store it in a database; an AI model training means for training an AI model using the stored data; an AI model providing means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user who wants to be coached to search for and match with a coach; and a session initiation means for starting an AI coaching session based on the search results.

[0037] Steps for users to digitize their specialized knowledge

[0038] 1. Data Entry

[0039] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[0040] 2. Data Transmission

[0041] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[0042] 3. Data reception and organization

[0043] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[0044] Training and serving AI models

[0045] 1. Data collection

[0046] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[0047] 2. Training the AI ​​model

[0048] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[0049] 3. Evaluate and deploy the model

[0050] The server evaluates the trained model on a validation dataset to check its performance, and then deploys the passed model, making it available to users.

[0051] Providing coaching services

[0052] 1. Coach Registration

[0053] Users enter their coaching profile, describing their areas of expertise and achievements, and this information is sent from the device to the server and stored in a database.

[0054] 2. Coach search and matching

[0055] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[0056] 3. Beginning a coaching session

[0057] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[0058] Examples:

[0059] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0060] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[0061] 2. The device sends this data to the server, which organizes it and stores it in a database.

[0062] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0063] 4. User B wants cooking coaching and searches on the platform.

[0064] 5. If User B finds a suitable coach, the device sends a session request to the server.

[0065] 6. The server starts the session and User B receives coaching from the AI.

[0066] This system allows users to easily digitize their own expertise and provide services as an AI coach based on that data. Users who want to be coached can easily find the right coach and receive high-quality coaching.

[0067] The processing flow will be explained below.

[0068] Understood. Below I will explain the process in concrete steps.

[0069] Steps for users to digitize their specialized knowledge

[0070] Step 1: Data entry

[0071] Users input their expertise and experience through a browser or application.

[0072] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[0073] Step 2: Send data

[0074] The terminal converts the data entered by the user into JSON format.

[0075] The terminal sends the converted data to the server as an HTTP request.

[0076] Step 3: Analyze and store the data

[0077] The server receives the HTTP request and parses the JSON data.

[0078] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[0079] Training and serving AI models

[0080] Step 1: Collect data

[0081] The server retrieves data related to a particular category from the database.

[0082] The server prepares the acquired data as a dataset for training an AI model.

[0083] Step 2: Training the AI ​​model

[0084] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[0085] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[0086] Step 3: Evaluate and deploy the model

[0087] The server evaluates the trained AI model on a validation dataset to check its performance.

[0088] The server deploys the approved AI model and makes it accessible to users.

[0089] Providing coaching services

[0090] Step 1: Register as a coach

[0091] The user fills out an input form about their coaching profile and areas of expertise.

[0092] The terminal transmits the input coach information to the server.

[0093] Step 2: Save your coach information

[0094] The server stores the coach information in a database.

[0095] The server prepares an appropriate AI model based on the stored coach information.

[0096] Step 3: Find a coach

[0097] Users who want to be coached access the platform and search for a specific category or coach.

[0098] The device sends a search query to the server.

[0099] Step 4: Providing matching results

[0100] The server filters suitable coaches from the database based on the search query.

[0101] The server sends the filtering results to the terminal and displays them to the user.

[0102] Step 5: Begin the coaching session

[0103] The user selects the desired coach.

[0104] The terminal sends a session request to the server.

[0105] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[0106] These are the specific processing steps of the program in this system. This allows users to easily digitize their own expertise and use it to provide AI coaching services. Users who want to be coached can easily find the right coach and receive high-quality coaching services.

[0107] Example 1

[0108] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] Conventional AI coaching systems have had difficulty quickly and accurately converting users' expertise and experience into data, and then training and deploying advanced AI models based on that data. Furthermore, the coach search and matching process was not smooth, resulting in a poor user experience.

[0110] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0111] In this invention, the server includes a data management means, a data collection means, an AI model training means, and an AI model evaluation and provision means, which enables fast and accurate data classification and storage, effective AI model training and evaluation, and smooth coach search and matching.

[0112] "Data input means" refers to an interface that allows a user to input their own specialized knowledge and experience, and includes browsers, application input forms, and the like.

[0113] "Communication means" refers to a technology for transmitting data input from a terminal to a server, and includes HTTP requests based on the Internet Protocol.

[0114] "Data management means" refers to a system for analyzing and classifying data received by the server and storing it in a database, and includes analysis scripts and database management systems.

[0115] The "data collection means" is a system that allows the server to retrieve the necessary data from the database and prepare it as a training dataset for building an AI model.

[0116] An "AI model training means" is a system for training an AI model using machine learning or deep learning techniques with data that has been preprocessed by a server using a natural language processing algorithm.

[0117] The "AI model evaluation and provision means" is a system in which a server evaluates trained AI models and deploys approved models in a form that users can use.

[0118] The "registration means" is an interface that allows a user to input a profile as a coach and describe their area of ​​expertise and achievements.

[0119] "Search means" is a function that allows users who wish to be coached to access the platform and search for specific categories or coaches.

[0120] The "matching means" is a system that sends a search query to the server using a communication means based on the Internet Protocol, and the server filters suitable coaches.

[0121] The "session initiation means" is a function that allows the user to select a desired coach and start a coaching session.

[0122] This invention is a system in which users input their own expertise and experience, and AI provides coaching based on that. This system uses the following hardware and software:

[0123] First, users enter their expertise and experience using a form in a browser or dedicated application. The hardware used includes PCs, smartphones, tablets, etc. The software used includes any web browser (e.g., Google Chrome, Mozilla Firefox, etc.) or a dedicated application.

[0124] Next, the terminal converts the input data into JSON format and sends it to the server as an HTTP request. This communication method uses HTTP based on the Internet Protocol (TCP / IP). Specifically, a POST request is sent using the JavaScript fetch API.

[0125] The server analyzes the received data, categorizes it, and stores it in a database. This data analysis is performed using Python scripts, and database management systems such as MySQL or PostgreSQL are used for database management. For example, cooking data is categorized into categories such as "recipes," "cooking steps," and "tips."

[0126] The server then retrieves the necessary data from the database and prepares a training dataset for building an AI model. SQL queries and Python scripts are used to extract the data. The server then preprocesses the data using natural language processing algorithms and trains the model using machine learning and deep learning techniques. Libraries used include TensorFlow and PyTorch. For example, a Transformer-based model (such as BERT or GPT) is used to create a question-answering system.

[0127] The trained model is evaluated using a validation dataset. The server calculates the model's accuracy and F1 score, and deploys the model if it passes. Deployment is performed using cloud services such as AWS SageMaker or Azure ML, and the model is provided as an endpoint.

[0128] The system also provides an interface for users to enter their coaching profile, including their areas of expertise and achievements. This information is sent from the device to a server and stored in a database.

[0129] Users who want to be coached access the platform and search for a specific category or coach. This search is performed using a search engine such as Elasticsearch, and the user sends a search query from the device to the server. The server then filters the search results and returns the appropriate coaches.

[0130] Finally, once the user selects the desired coach, the device sends a session request to the server, which then calls the selected coach's AI model and starts the coaching session. This process uses technologies such as WebRTC and Socket.io for real-time communication.

[0131] Specific examples

[0132] Here's a real-world example:

[0133] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0134] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[0135] 2. The device converts this data into JSON format and sends it to the server.

[0136] 3. The server receives the data, analyzes and classifies it, and stores it in a database.

[0137] 4. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0138] 5. User B wants cooking coaching and searches on the platform.

[0139] 6. If User B finds a suitable coach, he sends a session request to the server.

[0140] 7. The server starts the session and User B receives coaching from the AI.

[0141] Prompt Sentence Examples

[0142] "Please explain the steps to train a Transformer-based AI model using cooking recipe data entered by User A."

[0143] "Please explain the process from when User B found the coach they wanted to coach to when they started the session."

[0144] This system allows users to effectively digitize their specialized knowledge and receive coaching based on high-quality AI models. Users who want to be coached can also easily find a suitable coach and receive high-quality coaching sessions.

[0145] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0146] Step 1:

[0147] The user enters their expertise and experience using a browser or application input form.

[0148] Example of operation: A user accesses a dedicated web application and enters a "delicious pasta recipe" and "tips for boiling time" into the input form.

[0149] Input: Text data entered by the user (e.g., "Delicious pasta recipes," "Tips for boiling time").

[0150] Output: Text data of the expertise and experience entered in the input form.

[0151] Step 2:

[0152] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0153] Example of operation: A JavaScript script executed in the device's browser converts text data into JSON format and sends it to the server as a POST request using the fetch API.

[0154] Input: Text data of expertise and experience entered into the input form.

[0155] Output: JSON formatted data and HTTP request.

[0156] Step 3:

[0157] The server receives the HTTP request, analyzes the data, categorizes it, and stores it in a database.

[0158] How it works: The Node.js Express framework receives the POST request, and a Python script parses the data and categorizes it into categories such as "Recipe," "Cooking Instructions," and "Tips," before storing it in a MySQL database.

[0159] Input: JSON formatted data and HTTP request.

[0160] Output: The data classified by category is saved in a database.

[0161] Step 4:

[0162] The server retrieves the necessary data from the database and prepares it as a training dataset for building an AI model.

[0163] How it works: The server runs an SQL query to get data about "cuisine" and builds a training dataset with a Python script.

[0164] Input: Categorical data stored in a database.

[0165] Output: A dataset used to train an AI model.

[0166] Step 5:

[0167] The server preprocesses the data and trains the AI ​​model using machine learning and deep learning techniques.

[0168] Working example: Clean text data with Python's Pandas library and train a Transformer-based model using TensorFlow.

[0169] Input: Training dataset.

[0170] Output: A trained AI model.

[0171] Step 6:

[0172] The server evaluates the trained model on the validation dataset and deploys the passing model.

[0173] Example of operation: A Python script is used to calculate the model accuracy and F1 score, and the passing model is deployed to AWS SageMaker.

[0174] Input: Trained AI model, validation dataset.

[0175] Output: The deployed AI model.

[0176] Step 7:

[0177] Users enter their coaching profile, listing their areas of expertise and achievements.

[0178] Example of how it works: A user accesses a dedicated web form, enters their profile information, and clicks the submit button.

[0179] Input: User profile information (e.g., areas of expertise, achievements).

[0180] Output: The profile information is sent to the server and stored in a database.

[0181] Step 8:

[0182] A user visits the platform and searches for a specific category or coach.

[0183] Example of operation: A user enters "cooking" as a search keyword in a browser and presses the search button.

[0184] Input: Search keyword.

[0185] Output: Search results are returned from the server and displayed to the user.

[0186] Step 9:

[0187] The user selects the desired coach and sends a session request to the server.

[0188] Example of how it works: User selects appropriate coach from search results and clicks on Start Session button. A session request is sent to the server.

[0189] Input: Session request.

[0190] Output: The server calls the AI ​​model of the selected coach and the coaching session begins.

[0191] (Application example 1)

[0192] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0193] Conventional coaching systems have limited means for users to effectively utilize their expertise and experience, and suffer from insufficient quality and personalization of coaching content. Furthermore, the process for users to search for and properly match with a coach is cumbersome, often resulting in a long wait before a session can begin smoothly. Therefore, there is a need for efficient and effective generation and delivery of high-quality, personalized coaching content based on expert knowledge.

[0194] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0195] In this invention, the server includes data input means for a user to input their expertise and experience, communication means for a terminal to send the input data to the server, data management means for the server to organize and classify the received data and store it in a database, AI model training means for the server to train an AI model using the stored data, AI model providing means for deploying the trained AI model and making it available to users, registration means for a user to register as a coach, search means for a user who wants to be coached to search for and match with a coach, session initiation means for starting an AI coaching session based on the search results, and content delivery means for delivering coaching content generated based on the expertise. This makes it possible to efficiently generate and deliver high-quality, personalized coaching content based on a user's expertise.

[0196] The "data input means" is an interface for users to input their specialized knowledge and experience.

[0197] "Communication means" refers to the technical means by which the terminal transmits input data to the server.

[0198] "Data management means" is a system that organizes and classifies data received by the server and stores it in a database.

[0199] "AI model training means" means a program or algorithm that the server uses to train the AI ​​model using the stored data.

[0200] An "AI model providing means" is a system that has the function of deploying trained AI models and making them available to users.

[0201] The "registration means" is an interface for a user to register profile information as a coach.

[0202] The "search means" is a technical means by which a user who wants to be coached searches for a coach and is matched with them.

[0203] The "session initiation means" is a system that has the functionality to initiate an AI coaching session based on the search results.

[0204] "Content Delivery Vehicle" means a platform or technological means for delivering coaching content generated based on expert knowledge.

[0205] This invention provides a system in which users input their specialized knowledge and experience, and AI provides coaching based on that information.

[0206] composition

[0207] The system includes the following means:

[0208] 1. Data entry method

[0209] 2. Means of communication

[0210] 3. Data Management Measures

[0211] 4. AI model training methods

[0212] 5. AI model provision method

[0213] 6. Registration Method

[0214] 7. Search method

[0215] 8. Session Initiation Methods

[0216] 9. Content Delivery Methods

[0217] The specific hardware and software used

[0218] The system uses the following hardware and software:

[0219] Django Rest Framework: A web framework used to create API endpoints.

[0220] Transformers (Hugging Face): Uses a library that provides models for natural language processing.

[0221] Database (e.g., PostgreSQL): Use a database to store expert knowledge and model information.

[0222] Entering and Submitting Data

[0223] Users use the application's input form to enter their expertise and experience in text format. For example, a user with expertise in cooking may enter recipes, cooking procedures, and tips. The device converts this input data into JSON format and sends it to the server using an HTTP request.

[0224] Receiving and organizing data

[0225] The server analyzes the received data, classifies it by category, and stores it in a database. For example, data about cooking is classified into categories such as "recipes," "cooking steps," and "tips." The classified data is stored in a database through a data management means.

[0226] Training and serving AI models

[0227] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and trains the model using machine learning or deep learning techniques. For example, a Transformer-based model is used to create a conversational question-answering system. The trained model is evaluated and its performance is confirmed before it is deployed, allowing users to use the trained AI model.

[0228] Register and find a coach

[0229] Users register as coaches by entering their profile and areas of expertise. The registered information is stored in a database. When another user wants coaching, they can search the platform for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[0230] Starting a coaching session and delivering content

[0231] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and starts the coaching session. At the same time, coaching content generated based on the coach's expertise is delivered.

[0232] Specific examples

[0233] For example, if a user inputs a "basic Italian recipe," the AI ​​will generate and deliver tutorial videos such as "how to make spaghetti" and "how to make sauce."

[0234] Example prompt sentence:

[0235] User Input: Basic Italian recipe. How to make pasta with tomato sauce. Ingredients: Tomatoes, garlic, olive oil, salt, pepper. Steps: 1. Chop the tomatoes. 2. Sauté the garlic. 3. ...

[0236] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0237] Step 1:

[0238] User enters expertise

[0239] Users input their expertise and experience in text format using a smartphone app or a web browser input form. This input includes, for example, recipes, cooking procedures, cooking tips, etc. The input text is converted into JSON format and sent from the device to the server using a communication method.

[0240] Input: Text data of expertise and experience

[0241] Output: JSON format data

[0242] Step 2:

[0243] Transfer of input data

[0244] The device sends the JSON-formatted data entered by the user to the server as an HTTP request, which may also include the user's profile information.

[0245] Input: JSON format data, user profile information

[0246] Output: Data sent to the server

[0247] Step 3:

[0248] Receiving and organizing data

[0249] The server analyzes the received data, classifies it by category, and stores it in a database. For example, cooking data is classified into categories such as "recipes," "cooking steps," and "tips." The data is also structured through data management methods.

[0250] Input: Data sent to the server

[0251] Output: Structured data stored in a database

[0252] Step 4:

[0253] Training an AI model

[0254] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and then uses machine learning and deep learning techniques to train the AI ​​model. For example, it uses a Transformer-based model to create a conversational question-answering system.

[0255] Input: Structured data, training set

[0256] Output: A trained AI model

[0257] Step 5:

[0258] Evaluating and deploying AI models

[0259] The server evaluates the trained AI models and checks their performance. Successfully evaluated models are deployed and made available to users. This is done by making the models accessible through a model serving mechanism.

[0260] Input: A trained AI model

[0261] Output: Deployed AI model

[0262] Step 6:

[0263] Coach Registration

[0264] Users can register as coaches by entering their profile and areas of expertise. The registered information is stored in a database and can be used through search tools.

[0265] Input: Profile information, area of ​​expertise

[0266] Output: Coach information stored in a database

[0267] Step 7:

[0268] Explore Coaches

[0269] Users seeking coaching use the platform to search for specific categories and coaches. The device sends the search query to the server, which then filters and returns appropriate coaches.

[0270] Input: search query

[0271] Output: Filtered coach list

[0272] Step 8:

[0273] Starting a Session

[0274] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[0275] Input: Session request

[0276] Output: Coaching sessions started

[0277] Step 9:

[0278] Content Delivery

[0279] Based on the coaching sessions, expertly generated coaching content is delivered, such as cooking tutorial videos or Q&A session results.

[0280] Input: Coaching session data

[0281] Output: Delivered coaching content

[0282] The steps outlined here allow for efficient generation and delivery of high-quality coaching content based on user expertise.

[0283] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0284] This invention provides a system in which a user inputs their own expertise and experience, and an AI provides coaching based on that input, and further adjusts the content and tone of the coaching based on the user's emotions. This system includes: a data input means for the user to input their expertise and experience, a communication means for a terminal to send the input data to a server, a data management means for the server to organize and classify the data received and store it in a database, an AI model training means for training an AI model using the stored data, an AI model providing means for deploying the trained AI model and making it available to users, a registration means for a user to register as a coach, a search means for a user who wants to be coached to search for and match with a coach, a session initiation means for starting an AI coaching session based on the search results, and an emotion recognition means for analyzing emotions from the user's input data and voice data.

[0285] Steps for users to digitize their specialized knowledge

[0286] 1. Data Entry

[0287] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[0288] 2. Data Transmission

[0289] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[0290] 3. Data reception and organization

[0291] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[0292] Training and serving AI models

[0293] 1. Data collection

[0294] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[0295] 2. Training the AI ​​model

[0296] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[0297] 3. Evaluate and deploy the model

[0298] The server evaluates the trained AI model on a validation dataset to check its performance, and then deploys the passed model and makes it available to users.

[0299] Emotion Recognition and Applications

[0300] 1. Acquiring Emotion Data

[0301] The server collects user input data and voice data and passes the data to the emotion recognition means, for example, by collecting utterances and texts when the user interacts with the coach.

[0302] 2. Emotion Analysis

[0303] The server uses emotion recognition means to analyze the user's emotions (e.g., happiness, sadness, excitement, calmness) from the voice and text data. This process includes tone analysis of the voice and sentiment analysis of the text.

[0304] 3. Adjusting coaching content

[0305] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[0306] Providing coaching services

[0307] 1. Coach Registration

[0308] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[0309] 2. Coach search and matching

[0310] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which filters the appropriate coaches and returns the search results.

[0311] 3. Beginning a coaching session

[0312] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[0313] Examples:

[0314] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0315] 1. User A enters detailed cooking expertise (recipes, cooking tips, etc.).

[0316] 2. The device sends the entered information to the server, which organizes the data and stores it in a database.

[0317] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0318] 4. User B wants cooking coaching and searches on the platform.

[0319] 5. If User B finds a suitable coach, the device sends a session request to the server.

[0320] 6. The server starts the session and User B receives coaching from the AI.

[0321] 7. During coaching, the server analyzes User B's emotions and adjusts the content and tone of the coaching.

[0322] This system allows users to easily digitize their own expertise and provide high-quality coaching using AI. In addition, by combining it with emotion recognition functionality, highly individualized instruction that takes into account the user's emotions becomes possible.

[0323] The processing flow will be explained below.

[0324] Understood. Below, I will explain the specific process step by step.

[0325] Steps for users to digitize their specialized knowledge

[0326] Step 1: Data entry

[0327] Users input their expertise and experience through a browser or application.

[0328] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[0329] Step 2: Send data

[0330] The terminal converts the data entered by the user into JSON format.

[0331] The terminal sends the converted data to the server as an HTTP request.

[0332] Step 3: Analyze and store the data

[0333] The server receives the HTTP request and parses the JSON data.

[0334] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[0335] Training and serving AI models

[0336] Step 1: Collect data

[0337] The server retrieves data related to a particular category from the database.

[0338] The server prepares the acquired data as a dataset for training an AI model.

[0339] Step 2: Training the AI ​​model

[0340] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[0341] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[0342] Step 3: Evaluate and deploy the model

[0343] The server evaluates the trained AI model on a validation dataset to check its performance.

[0344] The server deploys the approved AI model and makes it accessible to users.

[0345] Emotion Recognition and Applications

[0346] Step 1: Obtaining emotion data

[0347] The server collects user input data and voice data and passes the data to the emotion recognition means.

[0348] The user inputs statements and text when interacting with the coach.

[0349] Step 2: Sentiment Analysis

[0350] The server uses emotion recognition means to analyze the user's emotions (e.g., joy, sadness, excitement, calmness) from the voice data and text data.

[0351] The server performs tone analysis of the voice and sentiment analysis of the text.

[0352] Step 3: Adjust your coaching

[0353] The server then adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data.

[0354] If the user is stressed, the server adjusts the model to provide guidance in a gentler tone.

[0355] Providing coaching services

[0356] Step 1: Register as a coach

[0357] The user fills out an input form about their coaching profile and areas of expertise.

[0358] The terminal transmits the input coach information to the server.

[0359] Step 2: Save your coach information

[0360] The server stores the coach information in a database.

[0361] The server prepares an appropriate AI model based on the stored coach information.

[0362] Step 3: Find a coach

[0363] Users who want to be coached access the platform and search for a specific category or coach.

[0364] The device sends a search query to the server.

[0365] Step 4: Providing matching results

[0366] The server filters suitable coaches from the database based on the search query.

[0367] The server sends the filtering results to the terminal and displays them to the user.

[0368] Step 5: Begin the coaching session

[0369] The user selects the desired coach.

[0370] The terminal sends a session request to the server.

[0371] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[0372] Example 2

[0373] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0374] Conventional coaching systems have had problems in effectively utilizing users' expertise and experience as data, and in providing highly personalized coaching that takes into account the user's emotional state. While there is a particular need for seamless processing from inputting expertise to conducting coaching sessions, many systems lack the ability to manage these processes in an integrated manner. Furthermore, there has been a lack of systems that can recognize users' emotions in real time and adjust the content and tone of coaching accordingly.

[0375] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0376] In this invention, the server includes: a data input means for a user to input their expertise and experience; a communication means for a terminal to send the input data to the server; a data management means for the server to analyze, classify, and store the data received; an AI model training means for the server to train an AI model using the stored data; an AI model provision means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user seeking coaching to search for and match with a coach; a session initiation means for starting an AI coaching session based on the search results; an emotion recognition means for the server to analyze emotions from the user's input data and voice data; and an adjustment means for adjusting the content and tone of coaching based on the analyzed emotion data. This makes it possible to effectively digitize a user's expertise and experience, recognize emotions, and provide highly personalized coaching.

[0377] "Data input means" refers to an interface or device that allows a user to input their own specialized knowledge and experience.

[0378] "Communication means" refers to the network functions and protocols that allow a terminal to send input data to a server.

[0379] "Data management means" refers to the functions and systems that allow the server to analyze and classify the data it receives and store it in a database.

[0380] "AI model training means" refers to the algorithms and methods used by the server to train the AI ​​model using the data stored on it.

[0381] "AI model provision means" refers to a mechanism for deploying trained AI models and making them available to users.

[0382] "Registration means" refers to a system or interface that allows a user to register by entering their coaching profile and areas of expertise.

[0383] "Search means" refers to a function or system that allows users who want to be coached to search for coaches and make appropriate matches.

[0384] "Session initiation means" refers to the function or process for initiating an AI coaching session based on the exploration results.

[0385] "Emotion recognition means" refers to the technology or algorithms that the server uses to analyze emotions from user input data and voice data.

[0386] "Adjustment measures" refer to mechanisms and functions for adjusting the content and tone of coaching based on analyzed emotional data.

[0387] This invention provides a system in which a user inputs their own expertise and experience, a generative AI model provides coaching based on that information, and the system also recognizes the user's emotions and adjusts the content and tone of the coaching. Specific embodiments of this system are described below.

[0388] Data entry and submission

[0389] First, a user enters their own expertise and experience using a browser or application input form. For example, if a user has expertise in cooking, they can enter detailed information such as recipes, cooking procedures, and tips.

[0390] The device then converts this input information into JSON format and sends it to the server as an HTTP request, which effectively transmits the data to the server.

[0391] Data organization and classification

[0392] The server analyzes the data received from the device, categorizes it, and stores it in a database. For example, cooking data is categorized into "recipes," "cooking steps," "tips," etc. This process organizes the data systematically, making subsequent processing easier.

[0393] Training and serving AI models

[0394] The server then retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. The algorithms used include natural language processing algorithms, machine learning, and deep learning. Specifically, a Transformer-based model can be used to create a conversational question-answering system.

[0395] The trained AI model is evaluated by the server to check its performance, and models that pass are deployed and made available to users.

[0396] Emotional awareness and coaching adjustment

[0397] During a coaching session, the server collects user input data and voice data and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[0398] Based on the analyzed emotional data, the server adjusts the content and tone of the coaching provided by the AI ​​model. For example, if the user is feeling stressed, the model can adjust its coaching to use a gentler tone.

[0399] Providing coaching services

[0400] Users complete the registration process by filling out a form describing their coaching profile and areas of expertise. This information is made publicly available to other users and stored in a database. When a user searches for a coach, their device sends a search query to the server, which then filters the results to find the appropriate coaches.

[0401] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model to initiate the AI ​​coaching session. During the session, the server analyzes the user's emotions and adjusts the content and tone of the coaching accordingly.

[0402] Examples of concrete examples and prompts

[0403] As a concrete example, the system usage procedure is as follows when User A wishes to receive cooking coaching. User A enters detailed cooking expertise (recipes, cooking tips, etc.), and the device sends the input information to the server, which organizes, categorizes, and stores the data. The server uses this data to train an AI model and deploys the trained model.

[0404] If User B wants cooking coaching and searches the platform, and finds a suitable coach, the device sends a session request to the server, which then starts the session. During the session, the server analyzes User B's emotions and adjusts the content and tone of the coaching accordingly.

[0405] An example of a prompt sentence is, "Please enter a cooking recipe. If you have any special dishes or cooking tips, please tell us in detail."

[0406] This system digitizes the user's expertise and experience, and is able to recognize emotions and provide highly individualized coaching.

[0407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0408] Step 1:

[0409] Users input their expertise and experience using a browser or application input form. The input information is entered into the text fields of the input form. For example, recipe information such as "boil pasta for 10 minutes" or "simmer the sauce slowly over low heat" can be entered.

[0410] Input: User expertise and experience (e.g., recipes, cooking instructions, tips)

[0411] Output: Text information entered in the input form

[0412] Step 2:

[0413] The terminal converts the information entered by the user into JSON format, which standardizes and structures the data, and then sends this JSON data to the server using an HTTP POST request.

[0414] Input: Text information entered by the user into an input form

[0415] Output: JSON format data sent to the server

[0416] Step 3:

[0417] The server parses the received JSON data and categorizes it using a data analysis algorithm to separate the information into categories such as "recipes," "cooking instructions," and "tips." The categorized data is then stored in a database.

[0418] Input: JSON format data sent from the terminal

[0419] Output: Information in the database sorted by category

[0420] Step 4:

[0421] The server collects the necessary data from the database and prepares a training set for the AI ​​model. It preprocesses and cleans the data using natural language processing algorithms. The collected data is then used to train the AI ​​model using a Transformer-based model.

[0422] Input: Categorical data collected from a database

[0423] Output: A trained AI model

[0424] Step 5:

[0425] The server evaluates the trained AI model and checks its performance. A validation dataset is used for evaluation, and the model's prediction accuracy, response time, etc. Models that meet the performance standards are deployed and made available to users.

[0426] Input: A trained AI model

[0427] Output: Deployed AI model

[0428] Step 6:

[0429] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[0430] Input: Profile and professional information entered by the user into the input form

[0431] Output: Coach profile information stored in a database

[0432] Step 7:

[0433] To search for a desired coach, a user accesses the platform and searches for a specific category or coach. The device sends this search query to the server, which then filters the appropriate coaches and returns the results.

[0434] Input: A search query entered by a user on the platform.

[0435] Output: A list of suitable coaches returned as search results

[0436] Step 8:

[0437] The user selects the desired coach, and the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[0438] Input: Information about the coach selected by the user

[0439] Output: AI coaching session started

[0440] Step 9:

[0441] The server collects user input data and voice data during the coaching session and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[0442] Input: User input and voice data collected during a coaching session

[0443] Output: Parsed emotion data

[0444] Step 10:

[0445] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[0446] Input: Parsed emotion data

[0447] Output: Tailored coaching content and tone

[0448] These steps allow users to effectively digitize their expertise and receive emotion-aware, personalized AI coaching.

[0449] (Application example 2)

[0450] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0451] Conventional coaching systems have had difficulty taking into account the user's emotions and state when providing coaching based on the user's specialized knowledge and experience. Furthermore, due to a lack of emotion recognition and personalized product recommendation functions, improving user satisfaction has been an issue. The present invention aims to solve these problems and provide a system that appropriately analyzes a user's emotions and provides coaching and product recommendations based on those analyses.

[0452] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: data input means for a user to input specialized knowledge and experience; communication means for a terminal to send the input data to the server; data management means for the server to organize, classify, and store the received data in a database; AI model training means for the server to train an AI model using the stored data; AI model provision means for deploying the trained AI model and making it available to users; registration means for a user to register as a coach; search means for a user seeking coaching to search for and match with a coach; session initiation means for starting an AI coaching session based on the search results; emotion recognition means for analyzing emotions from the user's facial expressions and voice data; tone adjustment means for adjusting the content and tone of coaching based on the emotion analysis results; and product recommendation means for recommending products based on the user's input data and emotion data. This enables personalized coaching and individualized product recommendations that take user emotions into consideration.

[0453] "Data input means" refers to interface devices or software that allow users to input their specialized knowledge and experience.

[0454] "Communication means" refers to the protocol and equipment used by the terminal to transmit input data to the server.

[0455] "Data management means" refers to software and functions for organizing and classifying data received by the server and storing it in a database.

[0456] "AI model training means" refers to the algorithms and frameworks that allow the server to train the AI ​​model using stored data.

[0457] "AI model provision means" refers to a system for deploying trained AI models and making them available to users.

[0458] "Registration means" refers to the function or form that allows a user to register as a coach.

[0459] "Search means" refers to a search system or algorithm that allows users seeking coaching to search for coaches and make appropriate matches.

[0460] "Session initiation means" refers to the process or command for initiating an AI coaching session based on the exploration results.

[0461] "Emotion recognition means" refers to algorithms or sensors for analyzing emotions from a user's facial expressions and voice data.

[0462] "Tone adjustment means" refers to the functions and logic for adjusting the content and tone of coaching based on the results of emotional analysis.

[0463] "Product recommendation means" refers to an algorithm or system for recommending products based on user input data and emotional data.

[0464] An embodiment of this invention is a system in which a user inputs their expertise and experience, and AI provides coaching based on that input. Furthermore, this system has an emotion recognition function, which allows it to adjust the content and tone of the coaching based on the user's emotions. The present invention has functions related to data input of the user's expertise, emotion recognition, and product recommendations, among others.

[0465] The server provides interface devices and software as a means for users to input their expertise and experience. This allows users to enter their own expertise and experience in detail through a browser or application input form. For example, if users input their cooking expertise, recipes, cooking tips, and other information can be converted into data.

[0466] The input data is converted to JSON format by the device using a communication method and sent to the server as an HTTP request. The server organizes the received data, categorizes it, and stores it in a database. Through this process, cooking-related data is classified into categories such as "recipes," "cooking steps," and "tips."

[0467] The server uses the stored data to train an AI model. It preprocesses the data using natural language processing algorithms and deep learning techniques, and trains a conversational AI using a Transformer-based model. Once trained, the AI ​​model is deployed for use by users using an AI model provisioning method.

[0468] Furthermore, when the user's facial expression or voice data is input, the emotion recognition means analyzes it and identifies the user's emotion (e.g., joy, sadness, excitement, etc.). Based on this data, the tone adjustment means adjusts the content and tone of the coaching. For example, if it is analyzed that the user is feeling stressed, the coaching will be given in a gentler tone.

[0469] Furthermore, the product recommendation unit has the function of recommending appropriate products based on the user's input data and emotional data. This allows the system to provide products that match the user's preferences and interests, improving the shopping experience in the virtual store. For example, a user who enjoys cooking could be recommended a "luxury knife set" or a "recipe book."

[0470] Examples:

[0471] Users use the app to input their expertise and preferences, and the AI ​​recommends items like "luxury knife sets" and "recipe books." The user can then start a coaching session and request advice on "how to cook Japanese food." The camera and microphone then recognize the user's emotion as "joy," and a brighter message is displayed.

[0472] Example prompt sentence:

[0473] User: Hello, I'd like some advice on how to cook Japanese food.

[0474] AI: I see, let's have fun learning! Can you tell us about the basics of Japanese cuisine that you already know?

[0475] This invention enables personalized coaching and individualized product recommendations that take into account the user's emotions, thereby realizing the provision of services that provide high levels of user satisfaction.

[0476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0477] Step 1:

[0478] The user inputs his / her specialized knowledge and experience using the data input means.

[0479] Input: A user enters their cooking expertise (e.g., recipes, cooking tips) into an input form.

[0480] Data processing: Convert the input information into JSON format.

[0481] Output: Generates data in JSON format.

[0482] Step 2:

[0483] The terminal transmits the user's input data to the server using a communication means.

[0484] Input: Data in JSON format.

[0485] Data calculation: Sends input data to the server as an HTTP request.

[0486] Output: Data transferred to the server.

[0487] Step 3:

[0488] The server organizes and classifies the received data using data management means and stores it in a database.

[0489] Input: JSON formatted data sent to the server.

[0490] Data processing: Analyze the data and classify it into categories (e.g., "recipes," "cooking instructions," "tips").

[0491] Output: The organized and classified data is stored in a database.

[0492] Step 4:

[0493] The server uses the stored data to train the AI ​​model using the AI ​​model training means.

[0494] Input: Expert knowledge data stored in a database.

[0495] Data Computing: Preprocessing data and training AI models using natural language processing algorithms and deep learning techniques.

[0496] Output: A trained AI model.

[0497] Step 5:

[0498] The server deploys the trained AI model using an AI model provisioning means, making it available to users.

[0499] Input: A trained AI model.

[0500] Data Computing: Deploying trained models and making them accessible to users.

[0501] Output: Available AI models.

[0502] Step 6:

[0503] To register as a coach, the user uses the registration means to input the necessary information.

[0504] Input: User profile information and areas of expertise.

[0505] Data processing: Registration information is sent to the server and stored in the database.

[0506] Output: Registered coach information.

[0507] Step 7:

[0508] A user who wants to be coached searches for a coach using a search means, and an appropriate coach is matched.

[0509] Input: Search query of the user you want to be coached.

[0510] Data calculations: Filtering suitable coaches from a database based on a search query.

[0511] Output: A list of coaches displayed as search results.

[0512] Step 8:

[0513] An AI coaching session is initiated based on the search results using a session initiation means.

[0514] Input: The user's session request.

[0515] Data calculation: Calls the AI ​​model of the selected coach based on the session request and starts the session.

[0516] Output: The AI ​​coaching session that was started.

[0517] Step 9:

[0518] The user's facial expressions and voice data are analyzed using emotion recognition means.

[0519] Input: User's facial expression or voice data.

[0520] Data Computation: Emotion recognition algorithms are used to analyze emotions (e.g., happiness, sadness, excitement).

[0521] Output: Parsed emotion data.

[0522] Step 10:

[0523] Based on the emotion analysis results, the coaching content and tone are adjusted using a tone adjustment means.

[0524] Input: Parsed emotion data.

[0525] Data arithmetic: Adjust the tone and content of coaching based on emotional data.

[0526] Output: Tailored coaching messages.

[0527] Step 11:

[0528] A product recommendation means is used to recommend products based on user input data and emotional data.

[0529] Input: User profile information, expertise data, sentiment data.

[0530] Data calculation: Using AI algorithms, products that match the user's preferences are selected.

[0531] Output: A list of recommended products.

[0532] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0533] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0534] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0535] [Second embodiment]

[0536] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0537] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0538] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0539] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0540] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0541] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0542] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0543] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0544] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0545] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0546] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0547] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0548] This invention provides a system in which a user inputs their own expertise and experience and an AI provides coaching based on that input. This system includes: a data input means for the user to input their expertise and experience; a communication means for a terminal to send the input data to a server; a data management means for the server to organize and classify the data received and store it in a database; an AI model training means for training an AI model using the stored data; an AI model providing means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user who wants to be coached to search for and match with a coach; and a session initiation means for starting an AI coaching session based on the search results.

[0549] Steps for users to digitize their specialized knowledge

[0550] 1. Data Entry

[0551] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[0552] 2. Data Transmission

[0553] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[0554] 3. Data reception and organization

[0555] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[0556] Training and serving AI models

[0557] 1. Data collection

[0558] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[0559] 2. Training the AI ​​model

[0560] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[0561] 3. Evaluate and deploy the model

[0562] The server evaluates the trained model on a validation dataset to check its performance, and then deploys the passed model, making it available to users.

[0563] Providing coaching services

[0564] 1. Coach Registration

[0565] Users enter their coaching profile, describing their areas of expertise and achievements, and this information is sent from the device to the server and stored in a database.

[0566] 2. Coach search and matching

[0567] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[0568] 3. Beginning a coaching session

[0569] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[0570] Examples:

[0571] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0572] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[0573] 2. The device sends this data to the server, which organizes it and stores it in a database.

[0574] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0575] 4. User B wants cooking coaching and searches on the platform.

[0576] 5. If User B finds a suitable coach, the device sends a session request to the server.

[0577] 6. The server starts the session and User B receives coaching from the AI.

[0578] This system allows users to easily digitize their own expertise and provide services as an AI coach based on that data. Users who want to be coached can easily find the right coach and receive high-quality coaching.

[0579] The processing flow will be explained below.

[0580] Understood. Below I will explain the process in concrete steps.

[0581] Steps for users to digitize their specialized knowledge

[0582] Step 1: Data entry

[0583] Users input their expertise and experience through a browser or application.

[0584] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[0585] Step 2: Send data

[0586] The terminal converts the data entered by the user into JSON format.

[0587] The terminal sends the converted data to the server as an HTTP request.

[0588] Step 3: Analyze and store the data

[0589] The server receives the HTTP request and parses the JSON data.

[0590] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[0591] Training and serving AI models

[0592] Step 1: Collect data

[0593] The server retrieves data related to a particular category from the database.

[0594] The server prepares the acquired data as a dataset for training an AI model.

[0595] Step 2: Training the AI ​​model

[0596] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[0597] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[0598] Step 3: Evaluate and deploy the model

[0599] The server evaluates the trained AI model on a validation dataset to check its performance.

[0600] The server deploys the approved AI model and makes it accessible to users.

[0601] Providing coaching services

[0602] Step 1: Register as a coach

[0603] The user fills out an input form about their coaching profile and areas of expertise.

[0604] The terminal transmits the input coach information to the server.

[0605] Step 2: Save your coach information

[0606] The server stores the coach information in a database.

[0607] The server prepares an appropriate AI model based on the stored coach information.

[0608] Step 3: Find a coach

[0609] Users who want to be coached access the platform and search for a specific category or coach.

[0610] The device sends a search query to the server.

[0611] Step 4: Providing matching results

[0612] The server filters suitable coaches from the database based on the search query.

[0613] The server sends the filtering results to the terminal and displays them to the user.

[0614] Step 5: Begin the coaching session

[0615] The user selects the desired coach.

[0616] The terminal sends a session request to the server.

[0617] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[0618] These are the specific processing steps of the program in this system. This allows users to easily digitize their own expertise and use it to provide AI coaching services. Users who want to be coached can easily find the right coach and receive high-quality coaching services.

[0619] Example 1

[0620] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] Conventional AI coaching systems have had difficulty quickly and accurately converting users' expertise and experience into data, and then training and deploying advanced AI models based on that data. Furthermore, the coach search and matching process was not smooth, resulting in a poor user experience.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0623] In this invention, the server includes a data management means, a data collection means, an AI model training means, and an AI model evaluation and provision means, which enables fast and accurate data classification and storage, effective AI model training and evaluation, and smooth coach search and matching.

[0624] "Data input means" refers to an interface that allows a user to input their own specialized knowledge and experience, and includes browsers, application input forms, and the like.

[0625] "Communication means" refers to a technology for transmitting data input from a terminal to a server, and includes HTTP requests based on the Internet Protocol.

[0626] "Data management means" refers to a system for analyzing and classifying data received by the server and storing it in a database, and includes analysis scripts and database management systems.

[0627] The "data collection means" is a system that allows the server to retrieve the necessary data from the database and prepare it as a training dataset for building an AI model.

[0628] An "AI model training means" is a system for training an AI model using machine learning or deep learning techniques with data that has been preprocessed by a server using a natural language processing algorithm.

[0629] The "AI model evaluation and provision means" is a system in which a server evaluates trained AI models and deploys approved models in a form that users can use.

[0630] The "registration means" is an interface that allows a user to input a profile as a coach and describe their area of ​​expertise and achievements.

[0631] "Search means" is a function that allows users who wish to be coached to access the platform and search for specific categories or coaches.

[0632] The "matching means" is a system that sends a search query to the server using a communication means based on the Internet Protocol, and the server filters suitable coaches.

[0633] The "session initiation means" is a function that allows the user to select a desired coach and start a coaching session.

[0634] This invention is a system in which users input their own expertise and experience, and AI provides coaching based on that. This system uses the following hardware and software:

[0635] First, users enter their expertise and experience using a form in a browser or dedicated application. The hardware used includes PCs, smartphones, tablets, etc. The software used includes any web browser (e.g., Google Chrome, Mozilla Firefox, etc.) or a dedicated application.

[0636] Next, the terminal converts the input data into JSON format and sends it to the server as an HTTP request. This communication method uses HTTP based on the Internet Protocol (TCP / IP). Specifically, a POST request is sent using the JavaScript fetch API.

[0637] The server analyzes the received data, categorizes it, and stores it in a database. This data analysis is performed using Python scripts, and database management systems such as MySQL or PostgreSQL are used for database management. For example, cooking data is categorized into categories such as "recipes," "cooking steps," and "tips."

[0638] The server then retrieves the necessary data from the database and prepares a training dataset for building an AI model. SQL queries and Python scripts are used to extract the data. The server then preprocesses the data using natural language processing algorithms and trains the model using machine learning and deep learning techniques. Libraries used include TensorFlow and PyTorch. For example, a Transformer-based model (such as BERT or GPT) is used to create a question-answering system.

[0639] The trained model is evaluated using a validation dataset. The server calculates the model's accuracy and F1 score, and deploys the model if it passes. Deployment is performed using cloud services such as AWS SageMaker or Azure ML, and the model is provided as an endpoint.

[0640] The system also provides an interface for users to enter their coaching profile, including their areas of expertise and achievements. This information is sent from the device to a server and stored in a database.

[0641] Users who want to be coached access the platform and search for a specific category or coach. This search is performed using a search engine such as Elasticsearch, and the user sends a search query from the device to the server. The server then filters the search results and returns the appropriate coaches.

[0642] Finally, once the user selects the desired coach, the device sends a session request to the server, which then calls the selected coach's AI model and starts the coaching session. This process uses technologies such as WebRTC and Socket.io for real-time communication.

[0643] Specific examples

[0644] Here's a real-world example:

[0645] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0646] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[0647] 2. The device converts this data into JSON format and sends it to the server.

[0648] 3. The server receives the data, analyzes and classifies it, and stores it in a database.

[0649] 4. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0650] 5. User B wants cooking coaching and searches on the platform.

[0651] 6. If User B finds a suitable coach, he sends a session request to the server.

[0652] 7. The server starts the session and User B receives coaching from the AI.

[0653] Prompt Sentence Examples

[0654] "Please explain the steps to train a Transformer-based AI model using cooking recipe data entered by User A."

[0655] "Please explain the process from when User B found the coach they wanted to coach to when they started the session."

[0656] This system allows users to effectively digitize their specialized knowledge and receive coaching based on high-quality AI models. Users who want to be coached can also easily find a suitable coach and receive high-quality coaching sessions.

[0657] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0658] Step 1:

[0659] The user enters their expertise and experience using a browser or application input form.

[0660] Example of operation: A user accesses a dedicated web application and enters a "delicious pasta recipe" and "tips for boiling time" into the input form.

[0661] Input: Text data entered by the user (e.g., "Delicious pasta recipes," "Tips for boiling time").

[0662] Output: Text data of the expertise and experience entered in the input form.

[0663] Step 2:

[0664] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0665] Example of operation: A JavaScript script executed in the device's browser converts text data into JSON format and sends it to the server as a POST request using the fetch API.

[0666] Input: Text data of expertise and experience entered into the input form.

[0667] Output: JSON formatted data and HTTP request.

[0668] Step 3:

[0669] The server receives the HTTP request, analyzes the data, categorizes it, and stores it in a database.

[0670] How it works: The Node.js Express framework receives the POST request, and a Python script parses the data and categorizes it into categories such as "Recipe," "Cooking Instructions," and "Tips," before storing it in a MySQL database.

[0671] Input: JSON formatted data and HTTP request.

[0672] Output: The data classified by category is saved in a database.

[0673] Step 4:

[0674] The server retrieves the necessary data from the database and prepares it as a training dataset for building an AI model.

[0675] How it works: The server runs an SQL query to get data about "cuisine" and builds a training dataset with a Python script.

[0676] Input: Categorical data stored in a database.

[0677] Output: A dataset used to train an AI model.

[0678] Step 5:

[0679] The server preprocesses the data and trains the AI ​​model using machine learning and deep learning techniques.

[0680] Working example: Clean text data with Python's Pandas library and train a Transformer-based model using TensorFlow.

[0681] Input: Training dataset.

[0682] Output: A trained AI model.

[0683] Step 6:

[0684] The server evaluates the trained model on the validation dataset and deploys the passing model.

[0685] Example of operation: A Python script is used to calculate the model accuracy and F1 score, and the passing model is deployed to AWS SageMaker.

[0686] Input: Trained AI model, validation dataset.

[0687] Output: The deployed AI model.

[0688] Step 7:

[0689] Users enter their coaching profile, listing their areas of expertise and achievements.

[0690] Example of how it works: A user accesses a dedicated web form, enters their profile information, and clicks the submit button.

[0691] Input: User profile information (e.g., areas of expertise, achievements).

[0692] Output: The profile information is sent to the server and stored in a database.

[0693] Step 8:

[0694] A user visits the platform and searches for a specific category or coach.

[0695] Example of operation: A user enters "cooking" as a search keyword in a browser and presses the search button.

[0696] Input: Search keyword.

[0697] Output: Search results are returned from the server and displayed to the user.

[0698] Step 9:

[0699] The user selects the desired coach and sends a session request to the server.

[0700] Example of how it works: User selects appropriate coach from search results and clicks on Start Session button. A session request is sent to the server.

[0701] Input: Session request.

[0702] Output: The server calls the AI ​​model of the selected coach and the coaching session begins.

[0703] (Application example 1)

[0704] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0705] Conventional coaching systems have limited means for users to effectively utilize their expertise and experience, and suffer from insufficient quality and personalization of coaching content. Furthermore, the process for users to search for and properly match with a coach is cumbersome, often resulting in a long wait before a session can begin smoothly. Therefore, there is a need for efficient and effective generation and delivery of high-quality, personalized coaching content based on expert knowledge.

[0706] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0707] In this invention, the server includes data input means for a user to input their expertise and experience, communication means for a terminal to send the input data to the server, data management means for the server to organize and classify the received data and store it in a database, AI model training means for the server to train an AI model using the stored data, AI model providing means for deploying the trained AI model and making it available to users, registration means for a user to register as a coach, search means for a user who wants to be coached to search for and match with a coach, session initiation means for starting an AI coaching session based on the search results, and content delivery means for delivering coaching content generated based on the expertise. This makes it possible to efficiently generate and deliver high-quality, personalized coaching content based on a user's expertise.

[0708] The "data input means" is an interface for users to input their specialized knowledge and experience.

[0709] "Communication means" refers to the technical means by which the terminal transmits input data to the server.

[0710] "Data management means" is a system that organizes and classifies data received by the server and stores it in a database.

[0711] "AI model training means" means a program or algorithm that the server uses to train the AI ​​model using the stored data.

[0712] An "AI model providing means" is a system that has the function of deploying trained AI models and making them available to users.

[0713] The "registration means" is an interface for a user to register profile information as a coach.

[0714] The "search means" is a technical means by which a user who wants to be coached searches for a coach and is matched with them.

[0715] The "session initiation means" is a system that has the functionality to initiate an AI coaching session based on the search results.

[0716] "Content Delivery Vehicle" means a platform or technological means for delivering coaching content generated based on expert knowledge.

[0717] This invention provides a system in which users input their specialized knowledge and experience, and AI provides coaching based on that information.

[0718] composition

[0719] The system includes the following means:

[0720] 1. Data entry method

[0721] 2. Means of communication

[0722] 3. Data Management Measures

[0723] 4. AI model training methods

[0724] 5. AI model provision method

[0725] 6. Registration Method

[0726] 7. Search method

[0727] 8. Session Initiation Methods

[0728] 9. Content Delivery Methods

[0729] The specific hardware and software used

[0730] The system uses the following hardware and software:

[0731] Django Rest Framework: A web framework used to create API endpoints.

[0732] Transformers (Hugging Face): Uses a library that provides models for natural language processing.

[0733] Database (e.g., PostgreSQL): Use a database to store expert knowledge and model information.

[0734] Entering and Submitting Data

[0735] Users use the application's input form to enter their expertise and experience in text format. For example, a user with expertise in cooking may enter recipes, cooking procedures, and tips. The device converts this input data into JSON format and sends it to the server using an HTTP request.

[0736] Receiving and organizing data

[0737] The server analyzes the received data, classifies it by category, and stores it in a database. For example, data about cooking is classified into categories such as "recipes," "cooking steps," and "tips." The classified data is stored in a database through a data management means.

[0738] Training and serving AI models

[0739] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and trains the model using machine learning or deep learning techniques. For example, a Transformer-based model is used to create a conversational question-answering system. The trained model is evaluated and its performance is confirmed before it is deployed, allowing users to use the trained AI model.

[0740] Register and find a coach

[0741] Users register as coaches by entering their profile and areas of expertise. The registered information is stored in a database. When another user wants coaching, they can search the platform for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[0742] Starting a coaching session and delivering content

[0743] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and starts the coaching session. At the same time, coaching content generated based on the coach's expertise is delivered.

[0744] Specific examples

[0745] For example, if a user inputs a "basic Italian recipe," the AI ​​will generate and deliver tutorial videos such as "how to make spaghetti" and "how to make sauce."

[0746] Example prompt sentence:

[0747] User Input: Basic Italian recipe. How to make pasta with tomato sauce. Ingredients: Tomatoes, garlic, olive oil, salt, pepper. Steps: 1. Chop the tomatoes. 2. Sauté the garlic. 3. ...

[0748] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0749] Step 1:

[0750] User enters expertise

[0751] Users input their expertise and experience in text format using a smartphone app or a web browser input form. This input includes, for example, recipes, cooking procedures, cooking tips, etc. The input text is converted into JSON format and sent from the device to the server using a communication method.

[0752] Input: Text data of expertise and experience

[0753] Output: JSON format data

[0754] Step 2:

[0755] Transfer of input data

[0756] The device sends the JSON-formatted data entered by the user to the server as an HTTP request, which may also include the user's profile information.

[0757] Input: JSON format data, user profile information

[0758] Output: Data sent to the server

[0759] Step 3:

[0760] Receiving and organizing data

[0761] The server analyzes the received data, classifies it by category, and stores it in a database. For example, cooking data is classified into categories such as "recipes," "cooking steps," and "tips." The data is also structured through data management methods.

[0762] Input: Data sent to the server

[0763] Output: Structured data stored in a database

[0764] Step 4:

[0765] Training an AI model

[0766] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and then uses machine learning and deep learning techniques to train the AI ​​model. For example, it uses a Transformer-based model to create a conversational question-answering system.

[0767] Input: Structured data, training set

[0768] Output: A trained AI model

[0769] Step 5:

[0770] Evaluating and deploying AI models

[0771] The server evaluates the trained AI models and checks their performance. Successfully evaluated models are deployed and made available to users. This is done by making the models accessible through a model serving mechanism.

[0772] Input: A trained AI model

[0773] Output: Deployed AI model

[0774] Step 6:

[0775] Coach Registration

[0776] Users can register as coaches by entering their profile and areas of expertise. The registered information is stored in a database and can be used through search tools.

[0777] Input: Profile information, area of ​​expertise

[0778] Output: Coach information stored in a database

[0779] Step 7:

[0780] Explore Coaches

[0781] Users seeking coaching use the platform to search for specific categories and coaches. The device sends the search query to the server, which then filters and returns appropriate coaches.

[0782] Input: search query

[0783] Output: Filtered coach list

[0784] Step 8:

[0785] Starting a Session

[0786] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[0787] Input: Session request

[0788] Output: Coaching sessions started

[0789] Step 9:

[0790] Content Delivery

[0791] Based on the coaching sessions, expertly generated coaching content is delivered, such as cooking tutorial videos or Q&A session results.

[0792] Input: Coaching session data

[0793] Output: Delivered coaching content

[0794] The steps outlined here allow for efficient generation and delivery of high-quality coaching content based on user expertise.

[0795] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0796] This invention provides a system in which a user inputs their own expertise and experience, and an AI provides coaching based on that input, and further adjusts the content and tone of the coaching based on the user's emotions. This system includes: a data input means for the user to input their expertise and experience, a communication means for a terminal to send the input data to a server, a data management means for the server to organize and classify the data received and store it in a database, an AI model training means for training an AI model using the stored data, an AI model providing means for deploying the trained AI model and making it available to users, a registration means for a user to register as a coach, a search means for a user who wants to be coached to search for and match with a coach, a session initiation means for starting an AI coaching session based on the search results, and an emotion recognition means for analyzing emotions from the user's input data and voice data.

[0797] Steps for users to digitize their specialized knowledge

[0798] 1. Data Entry

[0799] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[0800] 2. Data Transmission

[0801] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[0802] 3. Data reception and organization

[0803] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[0804] Training and serving AI models

[0805] 1. Data collection

[0806] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[0807] 2. Training the AI ​​model

[0808] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[0809] 3. Evaluate and deploy the model

[0810] The server evaluates the trained AI model on a validation dataset to check its performance, and then deploys the passed model and makes it available to users.

[0811] Emotion Recognition and Applications

[0812] 1. Acquiring Emotion Data

[0813] The server collects user input data and voice data and passes the data to the emotion recognition means, for example, by collecting utterances and texts when the user interacts with the coach.

[0814] 2. Emotion Analysis

[0815] The server uses emotion recognition means to analyze the user's emotions (e.g., happiness, sadness, excitement, calmness) from the voice and text data. This process includes tone analysis of the voice and sentiment analysis of the text.

[0816] 3. Adjusting coaching content

[0817] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[0818] Providing coaching services

[0819] 1. Coach Registration

[0820] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[0821] 2. Coach search and matching

[0822] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which filters the appropriate coaches and returns the search results.

[0823] 3. Beginning a coaching session

[0824] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[0825] Examples:

[0826] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[0827] 1. User A enters detailed cooking expertise (recipes, cooking tips, etc.).

[0828] 2. The device sends the entered information to the server, which organizes the data and stores it in a database.

[0829] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[0830] 4. User B wants cooking coaching and searches on the platform.

[0831] 5. If User B finds a suitable coach, the device sends a session request to the server.

[0832] 6. The server starts the session and User B receives coaching from the AI.

[0833] 7. During coaching, the server analyzes User B's emotions and adjusts the content and tone of the coaching.

[0834] This system allows users to easily digitize their own expertise and provide high-quality coaching using AI. In addition, by combining it with emotion recognition functionality, highly individualized instruction that takes into account the user's emotions becomes possible.

[0835] The processing flow will be explained below.

[0836] Understood. Below, I will explain the specific process step by step.

[0837] Steps for users to digitize their specialized knowledge

[0838] Step 1: Data entry

[0839] Users input their expertise and experience through a browser or application.

[0840] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[0841] Step 2: Send data

[0842] The terminal converts the data entered by the user into JSON format.

[0843] The terminal sends the converted data to the server as an HTTP request.

[0844] Step 3: Analyze and store the data

[0845] The server receives the HTTP request and parses the JSON data.

[0846] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[0847] Training and serving AI models

[0848] Step 1: Collect data

[0849] The server retrieves data related to a particular category from the database.

[0850] The server prepares the acquired data as a dataset for training an AI model.

[0851] Step 2: Training the AI ​​model

[0852] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[0853] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[0854] Step 3: Evaluate and deploy the model

[0855] The server evaluates the trained AI model on a validation dataset to check its performance.

[0856] The server deploys the approved AI model and makes it accessible to users.

[0857] Emotion Recognition and Applications

[0858] Step 1: Obtaining emotion data

[0859] The server collects user input data and voice data and passes the data to the emotion recognition means.

[0860] The user inputs statements and text when interacting with the coach.

[0861] Step 2: Sentiment Analysis

[0862] The server uses emotion recognition means to analyze the user's emotions (e.g., joy, sadness, excitement, calmness) from the voice data and text data.

[0863] The server performs tone analysis of the voice and sentiment analysis of the text.

[0864] Step 3: Adjust your coaching

[0865] The server then adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data.

[0866] If the user is stressed, the server adjusts the model to provide guidance in a gentler tone.

[0867] Providing coaching services

[0868] Step 1: Register as a coach

[0869] The user fills out an input form about their coaching profile and areas of expertise.

[0870] The terminal transmits the input coach information to the server.

[0871] Step 2: Save your coach information

[0872] The server stores the coach information in a database.

[0873] The server prepares an appropriate AI model based on the stored coach information.

[0874] Step 3: Find a coach

[0875] Users who want to be coached access the platform and search for a specific category or coach.

[0876] The device sends a search query to the server.

[0877] Step 4: Providing matching results

[0878] The server filters suitable coaches from the database based on the search query.

[0879] The server sends the filtering results to the terminal and displays them to the user.

[0880] Step 5: Begin the coaching session

[0881] The user selects the desired coach.

[0882] The terminal sends a session request to the server.

[0883] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[0884] Example 2

[0885] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0886] Conventional coaching systems have had problems in effectively utilizing users' expertise and experience as data, and in providing highly personalized coaching that takes into account the user's emotional state. While there is a particular need for seamless processing from inputting expertise to conducting coaching sessions, many systems lack the ability to manage these processes in an integrated manner. Furthermore, there has been a lack of systems that can recognize users' emotions in real time and adjust the content and tone of coaching accordingly.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0888] In this invention, the server includes: a data input means for a user to input their expertise and experience; a communication means for a terminal to send the input data to the server; a data management means for the server to analyze, classify, and store the data received; an AI model training means for the server to train an AI model using the stored data; an AI model provision means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user seeking coaching to search for and match with a coach; a session initiation means for starting an AI coaching session based on the search results; an emotion recognition means for the server to analyze emotions from the user's input data and voice data; and an adjustment means for adjusting the content and tone of coaching based on the analyzed emotion data. This makes it possible to effectively digitize a user's expertise and experience, recognize emotions, and provide highly personalized coaching.

[0889] "Data input means" refers to an interface or device that allows a user to input their own specialized knowledge and experience.

[0890] "Communication means" refers to the network functions and protocols that allow a terminal to send input data to a server.

[0891] "Data management means" refers to the functions and systems that allow the server to analyze and classify the data it receives and store it in a database.

[0892] "AI model training means" refers to the algorithms and methods used by the server to train the AI ​​model using the data stored on it.

[0893] "AI model provision means" refers to a mechanism for deploying trained AI models and making them available to users.

[0894] "Registration means" refers to a system or interface that allows a user to register by entering their coaching profile and areas of expertise.

[0895] "Search means" refers to a function or system that allows users who want to be coached to search for coaches and make appropriate matches.

[0896] "Session initiation means" refers to the function or process for initiating an AI coaching session based on the exploration results.

[0897] "Emotion recognition means" refers to the technology or algorithms that the server uses to analyze emotions from user input data and voice data.

[0898] "Adjustment measures" refer to mechanisms and functions for adjusting the content and tone of coaching based on analyzed emotional data.

[0899] This invention provides a system in which a user inputs their own expertise and experience, a generative AI model provides coaching based on that information, and the system also recognizes the user's emotions and adjusts the content and tone of the coaching. Specific embodiments of this system are described below.

[0900] Data entry and submission

[0901] First, a user enters their own expertise and experience using a browser or application input form. For example, if a user has expertise in cooking, they can enter detailed information such as recipes, cooking procedures, and tips.

[0902] The device then converts this input information into JSON format and sends it to the server as an HTTP request, which effectively transmits the data to the server.

[0903] Data organization and classification

[0904] The server analyzes the data received from the device, categorizes it, and stores it in a database. For example, cooking data is categorized into "recipes," "cooking steps," "tips," etc. This process organizes the data systematically, making subsequent processing easier.

[0905] Training and serving AI models

[0906] The server then retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. The algorithms used include natural language processing algorithms, machine learning, and deep learning. Specifically, a Transformer-based model can be used to create a conversational question-answering system.

[0907] The trained AI model is evaluated by the server to check its performance, and models that pass are deployed and made available to users.

[0908] Emotional awareness and coaching adjustment

[0909] During a coaching session, the server collects user input data and voice data and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[0910] Based on the analyzed emotional data, the server adjusts the content and tone of the coaching provided by the AI ​​model. For example, if the user is feeling stressed, the model can adjust its coaching to use a gentler tone.

[0911] Providing coaching services

[0912] Users complete the registration process by filling out a form describing their coaching profile and areas of expertise. This information is made publicly available to other users and stored in a database. When a user searches for a coach, their device sends a search query to the server, which then filters the results to find the appropriate coaches.

[0913] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model to initiate the AI ​​coaching session. During the session, the server analyzes the user's emotions and adjusts the content and tone of the coaching accordingly.

[0914] Examples of concrete examples and prompts

[0915] As a concrete example, the system usage procedure is as follows when User A wishes to receive cooking coaching. User A enters detailed cooking expertise (recipes, cooking tips, etc.), and the device sends the input information to the server, which organizes, categorizes, and stores the data. The server uses this data to train an AI model and deploys the trained model.

[0916] If User B wants cooking coaching and searches the platform, and finds a suitable coach, the device sends a session request to the server, which then starts the session. During the session, the server analyzes User B's emotions and adjusts the content and tone of the coaching accordingly.

[0917] An example of a prompt sentence is, "Please enter a cooking recipe. If you have any special dishes or cooking tips, please tell us in detail."

[0918] This system digitizes the user's expertise and experience, and is able to recognize emotions and provide highly individualized coaching.

[0919] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0920] Step 1:

[0921] Users input their expertise and experience using a browser or application input form. The input information is entered into the text fields of the input form. For example, recipe information such as "boil pasta for 10 minutes" or "simmer the sauce slowly over low heat" can be entered.

[0922] Input: User expertise and experience (e.g., recipes, cooking instructions, tips)

[0923] Output: Text information entered in the input form

[0924] Step 2:

[0925] The terminal converts the information entered by the user into JSON format, which standardizes and structures the data, and then sends this JSON data to the server using an HTTP POST request.

[0926] Input: Text information entered by the user into an input form

[0927] Output: JSON format data sent to the server

[0928] Step 3:

[0929] The server parses the received JSON data and categorizes it using a data analysis algorithm to separate the information into categories such as "recipes," "cooking instructions," and "tips." The categorized data is then stored in a database.

[0930] Input: JSON format data sent from the terminal

[0931] Output: Information in the database sorted by category

[0932] Step 4:

[0933] The server collects the necessary data from the database and prepares a training set for the AI ​​model. It preprocesses and cleans the data using natural language processing algorithms. The collected data is then used to train the AI ​​model using a Transformer-based model.

[0934] Input: Categorical data collected from a database

[0935] Output: A trained AI model

[0936] Step 5:

[0937] The server evaluates the trained AI model and checks its performance. A validation dataset is used for evaluation, and the model's prediction accuracy, response time, etc. Models that meet the performance standards are deployed and made available to users.

[0938] Input: A trained AI model

[0939] Output: Deployed AI model

[0940] Step 6:

[0941] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[0942] Input: Profile and professional information entered by the user into the input form

[0943] Output: Coach profile information stored in a database

[0944] Step 7:

[0945] To search for a desired coach, a user accesses the platform and searches for a specific category or coach. The device sends this search query to the server, which then filters the appropriate coaches and returns the results.

[0946] Input: A search query entered by a user on the platform.

[0947] Output: A list of suitable coaches returned as search results

[0948] Step 8:

[0949] The user selects the desired coach, and the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[0950] Input: Information about the coach selected by the user

[0951] Output: AI coaching session started

[0952] Step 9:

[0953] The server collects user input data and voice data during the coaching session and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[0954] Input: User input and voice data collected during a coaching session

[0955] Output: Parsed emotion data

[0956] Step 10:

[0957] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[0958] Input: Parsed emotion data

[0959] Output: Tailored coaching content and tone

[0960] These steps allow users to effectively digitize their expertise and receive emotion-aware, personalized AI coaching.

[0961] (Application example 2)

[0962] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0963] Conventional coaching systems have had difficulty taking into account the user's emotions and state when providing coaching based on the user's specialized knowledge and experience. Furthermore, due to a lack of emotion recognition and personalized product recommendation functions, improving user satisfaction has been an issue. The present invention aims to solve these problems and provide a system that appropriately analyzes a user's emotions and provides coaching and product recommendations based on those analyses.

[0964] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: data input means for a user to input specialized knowledge and experience; communication means for a terminal to send the input data to the server; data management means for the server to organize, classify, and store the received data in a database; AI model training means for the server to train an AI model using the stored data; AI model provision means for deploying the trained AI model and making it available to users; registration means for a user to register as a coach; search means for a user seeking coaching to search for and match with a coach; session initiation means for starting an AI coaching session based on the search results; emotion recognition means for analyzing emotions from the user's facial expressions and voice data; tone adjustment means for adjusting the content and tone of coaching based on the emotion analysis results; and product recommendation means for recommending products based on the user's input data and emotion data. This enables personalized coaching and individualized product recommendations that take user emotions into consideration.

[0965] "Data input means" refers to interface devices or software that allow users to input their specialized knowledge and experience.

[0966] "Communication means" refers to the protocol and equipment used by the terminal to transmit input data to the server.

[0967] "Data management means" refers to software and functions for organizing and classifying data received by the server and storing it in a database.

[0968] "AI model training means" refers to the algorithms and frameworks that allow the server to train the AI ​​model using stored data.

[0969] "AI model provision means" refers to a system for deploying trained AI models and making them available to users.

[0970] "Registration means" refers to the function or form that allows a user to register as a coach.

[0971] "Search means" refers to a search system or algorithm that allows users seeking coaching to search for coaches and make appropriate matches.

[0972] "Session initiation means" refers to the process or command for initiating an AI coaching session based on the exploration results.

[0973] "Emotion recognition means" refers to algorithms or sensors for analyzing emotions from a user's facial expressions and voice data.

[0974] "Tone adjustment means" refers to the functions and logic for adjusting the content and tone of coaching based on the results of emotional analysis.

[0975] "Product recommendation means" refers to an algorithm or system for recommending products based on user input data and emotional data.

[0976] An embodiment of this invention is a system in which a user inputs their expertise and experience, and AI provides coaching based on that input. Furthermore, this system has an emotion recognition function, which allows it to adjust the content and tone of the coaching based on the user's emotions. The present invention has functions related to data input of the user's expertise, emotion recognition, and product recommendations, among others.

[0977] The server provides interface devices and software as a means for users to input their expertise and experience. This allows users to enter their own expertise and experience in detail through a browser or application input form. For example, if users input their cooking expertise, recipes, cooking tips, and other information can be converted into data.

[0978] The input data is converted to JSON format by the device using a communication method and sent to the server as an HTTP request. The server organizes the received data, categorizes it, and stores it in a database. Through this process, cooking-related data is classified into categories such as "recipes," "cooking steps," and "tips."

[0979] The server uses the stored data to train an AI model. It preprocesses the data using natural language processing algorithms and deep learning techniques, and trains a conversational AI using a Transformer-based model. Once trained, the AI ​​model is deployed for use by users using an AI model provisioning method.

[0980] Furthermore, when the user's facial expression or voice data is input, the emotion recognition means analyzes it and identifies the user's emotion (e.g., joy, sadness, excitement, etc.). Based on this data, the tone adjustment means adjusts the content and tone of the coaching. For example, if it is analyzed that the user is feeling stressed, the coaching will be given in a gentler tone.

[0981] Furthermore, the product recommendation unit has the function of recommending appropriate products based on the user's input data and emotional data. This allows the system to provide products that match the user's preferences and interests, improving the shopping experience in the virtual store. For example, a user who enjoys cooking could be recommended a "luxury knife set" or a "recipe book."

[0982] Examples:

[0983] Users use the app to input their expertise and preferences, and the AI ​​recommends items like "luxury knife sets" and "recipe books." The user can then start a coaching session and request advice on "how to cook Japanese food." The camera and microphone then recognize the user's emotion as "joy," and a brighter message is displayed.

[0984] Example prompt sentence:

[0985] User: Hello, I'd like some advice on how to cook Japanese food.

[0986] AI: I see, let's have fun learning! Can you tell us about the basics of Japanese cuisine that you already know?

[0987] This invention enables personalized coaching and individualized product recommendations that take into account the user's emotions, thereby realizing the provision of services that provide high levels of user satisfaction.

[0988] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0989] Step 1:

[0990] The user inputs his / her specialized knowledge and experience using the data input means.

[0991] Input: A user enters their cooking expertise (e.g., recipes, cooking tips) into an input form.

[0992] Data processing: Convert the input information into JSON format.

[0993] Output: Generates data in JSON format.

[0994] Step 2:

[0995] The terminal transmits the user's input data to the server using a communication means.

[0996] Input: Data in JSON format.

[0997] Data calculation: Sends input data to the server as an HTTP request.

[0998] Output: Data transferred to the server.

[0999] Step 3:

[1000] The server organizes and classifies the received data using data management means and stores it in a database.

[1001] Input: JSON formatted data sent to the server.

[1002] Data processing: Analyze the data and classify it into categories (e.g., "recipes," "cooking instructions," "tips").

[1003] Output: The organized and classified data is stored in a database.

[1004] Step 4:

[1005] The server uses the stored data to train the AI ​​model using the AI ​​model training means.

[1006] Input: Expert knowledge data stored in a database.

[1007] Data Computing: Preprocessing data and training AI models using natural language processing algorithms and deep learning techniques.

[1008] Output: A trained AI model.

[1009] Step 5:

[1010] The server deploys the trained AI model using an AI model provisioning means, making it available to users.

[1011] Input: A trained AI model.

[1012] Data Computing: Deploying trained models and making them accessible to users.

[1013] Output: Available AI models.

[1014] Step 6:

[1015] To register as a coach, the user uses the registration means to input the necessary information.

[1016] Input: User profile information and areas of expertise.

[1017] Data processing: Registration information is sent to the server and stored in the database.

[1018] Output: Registered coach information.

[1019] Step 7:

[1020] A user who wants to be coached searches for a coach using a search means, and an appropriate coach is matched.

[1021] Input: Search query of the user you want to be coached.

[1022] Data calculations: Filtering suitable coaches from a database based on a search query.

[1023] Output: A list of coaches displayed as search results.

[1024] Step 8:

[1025] An AI coaching session is initiated based on the search results using a session initiation means.

[1026] Input: The user's session request.

[1027] Data calculation: Calls the AI ​​model of the selected coach based on the session request and starts the session.

[1028] Output: The AI ​​coaching session that was started.

[1029] Step 9:

[1030] The user's facial expressions and voice data are analyzed using emotion recognition means.

[1031] Input: User's facial expression or voice data.

[1032] Data Computation: Emotion recognition algorithms are used to analyze emotions (e.g., happiness, sadness, excitement).

[1033] Output: Parsed emotion data.

[1034] Step 10:

[1035] Based on the emotion analysis results, the coaching content and tone are adjusted using a tone adjustment means.

[1036] Input: Parsed emotion data.

[1037] Data arithmetic: Adjust the tone and content of coaching based on emotional data.

[1038] Output: Tailored coaching messages.

[1039] Step 11:

[1040] A product recommendation means is used to recommend products based on user input data and emotional data.

[1041] Input: User profile information, expertise data, sentiment data.

[1042] Data calculation: Using AI algorithms, products that match the user's preferences are selected.

[1043] Output: A list of recommended products.

[1044] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1045] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1046] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1047] [Third embodiment]

[1048] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1049] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1050] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1051] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1052] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1053] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1054] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1055] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1056] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1057] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1058] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1059] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1060] This invention provides a system in which a user inputs their own expertise and experience and an AI provides coaching based on that input. This system includes: a data input means for the user to input their expertise and experience; a communication means for a terminal to send the input data to a server; a data management means for the server to organize and classify the data received and store it in a database; an AI model training means for training an AI model using the stored data; an AI model providing means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user who wants to be coached to search for and match with a coach; and a session initiation means for starting an AI coaching session based on the search results.

[1061] Steps for users to digitize their specialized knowledge

[1062] 1. Data Entry

[1063] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[1064] 2. Data Transmission

[1065] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[1066] 3. Data reception and organization

[1067] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[1068] Training and serving AI models

[1069] 1. Data collection

[1070] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[1071] 2. Training the AI ​​model

[1072] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[1073] 3. Evaluate and deploy the model

[1074] The server evaluates the trained model on a validation dataset to check its performance, and then deploys the passed model, making it available to users.

[1075] Providing coaching services

[1076] 1. Coach Registration

[1077] Users enter their coaching profile, describing their areas of expertise and achievements, and this information is sent from the device to the server and stored in a database.

[1078] 2. Coach search and matching

[1079] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[1080] 3. Beginning a coaching session

[1081] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[1082] Examples:

[1083] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1084] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[1085] 2. The device sends this data to the server, which organizes it and stores it in a database.

[1086] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1087] 4. User B wants cooking coaching and searches on the platform.

[1088] 5. If User B finds a suitable coach, the device sends a session request to the server.

[1089] 6. The server starts the session and User B receives coaching from the AI.

[1090] This system allows users to easily digitize their own expertise and provide services as an AI coach based on that data. Users who want to be coached can easily find the right coach and receive high-quality coaching.

[1091] The processing flow will be explained below.

[1092] Understood. Below I will explain the process in concrete steps.

[1093] Steps for users to digitize their specialized knowledge

[1094] Step 1: Data entry

[1095] Users input their expertise and experience through a browser or application.

[1096] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[1097] Step 2: Send data

[1098] The terminal converts the data entered by the user into JSON format.

[1099] The terminal sends the converted data to the server as an HTTP request.

[1100] Step 3: Analyze and store the data

[1101] The server receives the HTTP request and parses the JSON data.

[1102] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[1103] Training and serving AI models

[1104] Step 1: Collect data

[1105] The server retrieves data related to a particular category from the database.

[1106] The server prepares the acquired data as a dataset for training an AI model.

[1107] Step 2: Training the AI ​​model

[1108] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[1109] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[1110] Step 3: Evaluate and deploy the model

[1111] The server evaluates the trained AI model on a validation dataset to check its performance.

[1112] The server deploys the approved AI model and makes it accessible to users.

[1113] Providing coaching services

[1114] Step 1: Register as a coach

[1115] The user fills out an input form about their coaching profile and areas of expertise.

[1116] The terminal transmits the input coach information to the server.

[1117] Step 2: Save your coach information

[1118] The server stores the coach information in a database.

[1119] The server prepares an appropriate AI model based on the stored coach information.

[1120] Step 3: Find a coach

[1121] Users who want to be coached access the platform and search for a specific category or coach.

[1122] The device sends a search query to the server.

[1123] Step 4: Providing matching results

[1124] The server filters suitable coaches from the database based on the search query.

[1125] The server sends the filtering results to the terminal and displays them to the user.

[1126] Step 5: Begin the coaching session

[1127] The user selects the desired coach.

[1128] The terminal sends a session request to the server.

[1129] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[1130] These are the specific processing steps of the program in this system. This allows users to easily digitize their own expertise and use it to provide AI coaching services. Users who want to be coached can easily find the right coach and receive high-quality coaching services.

[1131] Example 1

[1132] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1133] Conventional AI coaching systems have had difficulty quickly and accurately converting users' expertise and experience into data, and then training and deploying advanced AI models based on that data. Furthermore, the coach search and matching process was not smooth, resulting in a poor user experience.

[1134] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1135] In this invention, the server includes a data management means, a data collection means, an AI model training means, and an AI model evaluation and provision means, which enables fast and accurate data classification and storage, effective AI model training and evaluation, and smooth coach search and matching.

[1136] "Data input means" refers to an interface that allows a user to input their own specialized knowledge and experience, and includes browsers, application input forms, and the like.

[1137] "Communication means" refers to a technology for transmitting data input from a terminal to a server, and includes HTTP requests based on the Internet Protocol.

[1138] "Data management means" refers to a system for analyzing and classifying data received by the server and storing it in a database, and includes analysis scripts and database management systems.

[1139] The "data collection means" is a system that allows the server to retrieve the necessary data from the database and prepare it as a training dataset for building an AI model.

[1140] An "AI model training means" is a system for training an AI model using machine learning or deep learning techniques with data that has been preprocessed by a server using a natural language processing algorithm.

[1141] The "AI model evaluation and provision means" is a system in which a server evaluates trained AI models and deploys approved models in a form that users can use.

[1142] The "registration means" is an interface that allows a user to input a profile as a coach and describe their area of ​​expertise and achievements.

[1143] "Search means" is a function that allows users who wish to be coached to access the platform and search for specific categories or coaches.

[1144] The "matching means" is a system that sends a search query to the server using a communication means based on the Internet Protocol, and the server filters suitable coaches.

[1145] The "session initiation means" is a function that allows the user to select a desired coach and start a coaching session.

[1146] This invention is a system in which users input their own expertise and experience, and AI provides coaching based on that. This system uses the following hardware and software:

[1147] First, users enter their expertise and experience using a form in a browser or dedicated application. The hardware used includes PCs, smartphones, tablets, etc. The software used includes any web browser (e.g., Google Chrome, Mozilla Firefox, etc.) or a dedicated application.

[1148] Next, the terminal converts the input data into JSON format and sends it to the server as an HTTP request. This communication method uses HTTP based on the Internet Protocol (TCP / IP). Specifically, a POST request is sent using the JavaScript fetch API.

[1149] The server analyzes the received data, categorizes it, and stores it in a database. This data analysis is performed using Python scripts, and database management systems such as MySQL or PostgreSQL are used for database management. For example, cooking data is categorized into categories such as "recipes," "cooking steps," and "tips."

[1150] The server then retrieves the necessary data from the database and prepares a training dataset for building an AI model. SQL queries and Python scripts are used to extract the data. The server then preprocesses the data using natural language processing algorithms and trains the model using machine learning and deep learning techniques. Libraries used include TensorFlow and PyTorch. For example, a Transformer-based model (such as BERT or GPT) is used to create a question-answering system.

[1151] The trained model is evaluated using a validation dataset. The server calculates the model's accuracy and F1 score, and deploys the model if it passes. Deployment is performed using cloud services such as AWS SageMaker or Azure ML, and the model is provided as an endpoint.

[1152] The system also provides an interface for users to enter their coaching profile, including their areas of expertise and achievements. This information is sent from the device to a server and stored in a database.

[1153] Users who want to be coached access the platform and search for a specific category or coach. This search is performed using a search engine such as Elasticsearch, and the user sends a search query from the device to the server. The server then filters the search results and returns the appropriate coaches.

[1154] Finally, once the user selects the desired coach, the device sends a session request to the server, which then calls the selected coach's AI model and starts the coaching session. This process uses technologies such as WebRTC and Socket.io for real-time communication.

[1155] Specific examples

[1156] Here's a real-world example:

[1157] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1158] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[1159] 2. The device converts this data into JSON format and sends it to the server.

[1160] 3. The server receives the data, analyzes and classifies it, and stores it in a database.

[1161] 4. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1162] 5. User B wants cooking coaching and searches on the platform.

[1163] 6. If User B finds a suitable coach, he sends a session request to the server.

[1164] 7. The server starts the session and User B receives coaching from the AI.

[1165] Prompt Sentence Examples

[1166] "Please explain the steps to train a Transformer-based AI model using cooking recipe data entered by User A."

[1167] "Please explain the process from when User B found the coach they wanted to coach to when they started the session."

[1168] This system allows users to effectively digitize their specialized knowledge and receive coaching based on high-quality AI models. Users who want to be coached can also easily find a suitable coach and receive high-quality coaching sessions.

[1169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] The user enters their expertise and experience using a browser or application input form.

[1172] Example of operation: A user accesses a dedicated web application and enters a "delicious pasta recipe" and "tips for boiling time" into the input form.

[1173] Input: Text data entered by the user (e.g., "Delicious pasta recipes," "Tips for boiling time").

[1174] Output: Text data of the expertise and experience entered in the input form.

[1175] Step 2:

[1176] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1177] Example of operation: A JavaScript script executed in the device's browser converts text data into JSON format and sends it to the server as a POST request using the fetch API.

[1178] Input: Text data of expertise and experience entered into the input form.

[1179] Output: JSON formatted data and HTTP request.

[1180] Step 3:

[1181] The server receives the HTTP request, analyzes the data, categorizes it, and stores it in a database.

[1182] How it works: The Node.js Express framework receives the POST request, and a Python script parses the data and categorizes it into categories such as "Recipe," "Cooking Instructions," and "Tips," before storing it in a MySQL database.

[1183] Input: JSON formatted data and HTTP request.

[1184] Output: The data classified by category is saved in a database.

[1185] Step 4:

[1186] The server retrieves the necessary data from the database and prepares it as a training dataset for building an AI model.

[1187] How it works: The server runs an SQL query to get data about "cuisine" and builds a training dataset with a Python script.

[1188] Input: Categorical data stored in a database.

[1189] Output: A dataset used to train an AI model.

[1190] Step 5:

[1191] The server preprocesses the data and trains the AI ​​model using machine learning and deep learning techniques.

[1192] Working example: Clean text data with Python's Pandas library and train a Transformer-based model using TensorFlow.

[1193] Input: Training dataset.

[1194] Output: A trained AI model.

[1195] Step 6:

[1196] The server evaluates the trained model on the validation dataset and deploys the passing model.

[1197] Example of operation: A Python script is used to calculate the model accuracy and F1 score, and the passing model is deployed to AWS SageMaker.

[1198] Input: Trained AI model, validation dataset.

[1199] Output: The deployed AI model.

[1200] Step 7:

[1201] Users enter their coaching profile, listing their areas of expertise and achievements.

[1202] Example of how it works: A user accesses a dedicated web form, enters their profile information, and clicks the submit button.

[1203] Input: User profile information (e.g., areas of expertise, achievements).

[1204] Output: The profile information is sent to the server and stored in a database.

[1205] Step 8:

[1206] A user visits the platform and searches for a specific category or coach.

[1207] Example of operation: A user enters "cooking" as a search keyword in a browser and presses the search button.

[1208] Input: Search keyword.

[1209] Output: Search results are returned from the server and displayed to the user.

[1210] Step 9:

[1211] The user selects the desired coach and sends a session request to the server.

[1212] Example of how it works: User selects appropriate coach from search results and clicks on Start Session button. A session request is sent to the server.

[1213] Input: Session request.

[1214] Output: The server calls the AI ​​model of the selected coach and the coaching session begins.

[1215] (Application example 1)

[1216] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1217] Conventional coaching systems have limited means for users to effectively utilize their expertise and experience, and suffer from insufficient quality and personalization of coaching content. Furthermore, the process for users to search for and properly match with a coach is cumbersome, often resulting in a long wait before a session can begin smoothly. Therefore, there is a need for efficient and effective generation and delivery of high-quality, personalized coaching content based on expert knowledge.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1219] In this invention, the server includes data input means for a user to input their expertise and experience, communication means for a terminal to send the input data to the server, data management means for the server to organize and classify the received data and store it in a database, AI model training means for the server to train an AI model using the stored data, AI model providing means for deploying the trained AI model and making it available to users, registration means for a user to register as a coach, search means for a user who wants to be coached to search for and match with a coach, session initiation means for starting an AI coaching session based on the search results, and content delivery means for delivering coaching content generated based on the expertise. This makes it possible to efficiently generate and deliver high-quality, personalized coaching content based on a user's expertise.

[1220] The "data input means" is an interface for users to input their specialized knowledge and experience.

[1221] "Communication means" refers to the technical means by which the terminal transmits input data to the server.

[1222] "Data management means" is a system that organizes and classifies data received by the server and stores it in a database.

[1223] "AI model training means" means a program or algorithm that the server uses to train the AI ​​model using the stored data.

[1224] An "AI model providing means" is a system that has the function of deploying trained AI models and making them available to users.

[1225] The "registration means" is an interface for a user to register profile information as a coach.

[1226] The "search means" is a technical means by which a user who wants to be coached searches for a coach and is matched with them.

[1227] The "session initiation means" is a system that has the functionality to initiate an AI coaching session based on the search results.

[1228] "Content Delivery Vehicle" means a platform or technological means for delivering coaching content generated based on expert knowledge.

[1229] This invention provides a system in which users input their specialized knowledge and experience, and AI provides coaching based on that information.

[1230] composition

[1231] The system includes the following means:

[1232] 1. Data entry method

[1233] 2. Means of communication

[1234] 3. Data Management Measures

[1235] 4. AI model training methods

[1236] 5. AI model provision method

[1237] 6. Registration Method

[1238] 7. Search method

[1239] 8. Session Initiation Methods

[1240] 9. Content Delivery Methods

[1241] The specific hardware and software used

[1242] The system uses the following hardware and software:

[1243] Django Rest Framework: A web framework used to create API endpoints.

[1244] Transformers (Hugging Face): Uses a library that provides models for natural language processing.

[1245] Database (e.g., PostgreSQL): Use a database to store expert knowledge and model information.

[1246] Entering and Submitting Data

[1247] Users use the application's input form to enter their expertise and experience in text format. For example, a user with expertise in cooking may enter recipes, cooking procedures, and tips. The device converts this input data into JSON format and sends it to the server using an HTTP request.

[1248] Receiving and organizing data

[1249] The server analyzes the received data, classifies it by category, and stores it in a database. For example, data about cooking is classified into categories such as "recipes," "cooking steps," and "tips." The classified data is stored in a database through a data management means.

[1250] Training and serving AI models

[1251] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and trains the model using machine learning or deep learning techniques. For example, a Transformer-based model is used to create a conversational question-answering system. The trained model is evaluated and its performance is confirmed before it is deployed, allowing users to use the trained AI model.

[1252] Register and find a coach

[1253] Users register as coaches by entering their profile and areas of expertise. The registered information is stored in a database. When another user wants coaching, they can search the platform for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[1254] Starting a coaching session and delivering content

[1255] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and starts the coaching session. At the same time, coaching content generated based on the coach's expertise is delivered.

[1256] Specific examples

[1257] For example, if a user inputs a "basic Italian recipe," the AI ​​will generate and deliver tutorial videos such as "how to make spaghetti" and "how to make sauce."

[1258] Example prompt sentence:

[1259] User Input: Basic Italian recipe. How to make pasta with tomato sauce. Ingredients: Tomatoes, garlic, olive oil, salt, pepper. Steps: 1. Chop the tomatoes. 2. Sauté the garlic. 3. ...

[1260] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1261] Step 1:

[1262] User enters expertise

[1263] Users input their expertise and experience in text format using a smartphone app or a web browser input form. This input includes, for example, recipes, cooking procedures, cooking tips, etc. The input text is converted into JSON format and sent from the device to the server using a communication method.

[1264] Input: Text data of expertise and experience

[1265] Output: JSON format data

[1266] Step 2:

[1267] Transfer of input data

[1268] The device sends the JSON-formatted data entered by the user to the server as an HTTP request, which may also include the user's profile information.

[1269] Input: JSON format data, user profile information

[1270] Output: Data sent to the server

[1271] Step 3:

[1272] Receiving and organizing data

[1273] The server analyzes the received data, classifies it by category, and stores it in a database. For example, cooking data is classified into categories such as "recipes," "cooking steps," and "tips." The data is also structured through data management methods.

[1274] Input: Data sent to the server

[1275] Output: Structured data stored in a database

[1276] Step 4:

[1277] Training an AI model

[1278] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and then uses machine learning and deep learning techniques to train the AI ​​model. For example, it uses a Transformer-based model to create a conversational question-answering system.

[1279] Input: Structured data, training set

[1280] Output: A trained AI model

[1281] Step 5:

[1282] Evaluating and deploying AI models

[1283] The server evaluates the trained AI models and checks their performance. Successfully evaluated models are deployed and made available to users. This is done by making the models accessible through a model serving mechanism.

[1284] Input: A trained AI model

[1285] Output: Deployed AI model

[1286] Step 6:

[1287] Coach Registration

[1288] Users can register as coaches by entering their profile and areas of expertise. The registered information is stored in a database and can be used through search tools.

[1289] Input: Profile information, area of ​​expertise

[1290] Output: Coach information stored in a database

[1291] Step 7:

[1292] Explore Coaches

[1293] Users seeking coaching use the platform to search for specific categories and coaches. The device sends the search query to the server, which then filters and returns appropriate coaches.

[1294] Input: search query

[1295] Output: Filtered coach list

[1296] Step 8:

[1297] Starting a Session

[1298] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[1299] Input: Session request

[1300] Output: Coaching sessions started

[1301] Step 9:

[1302] Content Delivery

[1303] Based on the coaching sessions, expertly generated coaching content is delivered, such as cooking tutorial videos or Q&A session results.

[1304] Input: Coaching session data

[1305] Output: Delivered coaching content

[1306] The steps outlined here allow for efficient generation and delivery of high-quality coaching content based on user expertise.

[1307] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1308] This invention provides a system in which a user inputs their own expertise and experience, and an AI provides coaching based on that input, and further adjusts the content and tone of the coaching based on the user's emotions. This system includes: a data input means for the user to input their expertise and experience, a communication means for a terminal to send the input data to a server, a data management means for the server to organize and classify the data received and store it in a database, an AI model training means for training an AI model using the stored data, an AI model providing means for deploying the trained AI model and making it available to users, a registration means for a user to register as a coach, a search means for a user who wants to be coached to search for and match with a coach, a session initiation means for starting an AI coaching session based on the search results, and an emotion recognition means for analyzing emotions from the user's input data and voice data.

[1309] Steps for users to digitize their specialized knowledge

[1310] 1. Data Entry

[1311] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[1312] 2. Data Transmission

[1313] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[1314] 3. Data reception and organization

[1315] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[1316] Training and serving AI models

[1317] 1. Data collection

[1318] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[1319] 2. Training the AI ​​model

[1320] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[1321] 3. Evaluate and deploy the model

[1322] The server evaluates the trained AI model on a validation dataset to check its performance, and then deploys the passed model and makes it available to users.

[1323] Emotion Recognition and Applications

[1324] 1. Acquiring Emotion Data

[1325] The server collects user input data and voice data and passes the data to the emotion recognition means, for example, by collecting utterances and texts when the user interacts with the coach.

[1326] 2. Emotion Analysis

[1327] The server uses emotion recognition means to analyze the user's emotions (e.g., happiness, sadness, excitement, calmness) from the voice and text data. This process includes tone analysis of the voice and sentiment analysis of the text.

[1328] 3. Adjusting coaching content

[1329] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[1330] Providing coaching services

[1331] 1. Coach Registration

[1332] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[1333] 2. Coach search and matching

[1334] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which filters the appropriate coaches and returns the search results.

[1335] 3. Beginning a coaching session

[1336] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[1337] Examples:

[1338] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1339] 1. User A enters detailed cooking expertise (recipes, cooking tips, etc.).

[1340] 2. The device sends the entered information to the server, which organizes the data and stores it in a database.

[1341] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1342] 4. User B wants cooking coaching and searches on the platform.

[1343] 5. If User B finds a suitable coach, the device sends a session request to the server.

[1344] 6. The server starts the session and User B receives coaching from the AI.

[1345] 7. During coaching, the server analyzes User B's emotions and adjusts the content and tone of the coaching.

[1346] This system allows users to easily digitize their own expertise and provide high-quality coaching using AI. In addition, by combining it with emotion recognition functionality, highly individualized instruction that takes into account the user's emotions becomes possible.

[1347] The processing flow will be explained below.

[1348] Understood. Below, I will explain the specific process step by step.

[1349] Steps for users to digitize their specialized knowledge

[1350] Step 1: Data entry

[1351] Users input their expertise and experience through a browser or application.

[1352] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[1353] Step 2: Send data

[1354] The terminal converts the data entered by the user into JSON format.

[1355] The terminal sends the converted data to the server as an HTTP request.

[1356] Step 3: Analyze and store the data

[1357] The server receives the HTTP request and parses the JSON data.

[1358] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[1359] Training and serving AI models

[1360] Step 1: Collect data

[1361] The server retrieves data related to a particular category from the database.

[1362] The server prepares the acquired data as a dataset for training an AI model.

[1363] Step 2: Training the AI ​​model

[1364] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[1365] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[1366] Step 3: Evaluate and deploy the model

[1367] The server evaluates the trained AI model on a validation dataset to check its performance.

[1368] The server deploys the approved AI model and makes it accessible to users.

[1369] Emotion Recognition and Applications

[1370] Step 1: Obtaining emotion data

[1371] The server collects user input data and voice data and passes the data to the emotion recognition means.

[1372] The user inputs statements and text when interacting with the coach.

[1373] Step 2: Sentiment Analysis

[1374] The server uses emotion recognition means to analyze the user's emotions (e.g., joy, sadness, excitement, calmness) from the voice data and text data.

[1375] The server performs tone analysis of the voice and sentiment analysis of the text.

[1376] Step 3: Adjust your coaching

[1377] The server then adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data.

[1378] If the user is stressed, the server adjusts the model to provide guidance in a gentler tone.

[1379] Providing coaching services

[1380] Step 1: Register as a coach

[1381] The user fills out an input form about their coaching profile and areas of expertise.

[1382] The terminal transmits the input coach information to the server.

[1383] Step 2: Save your coach information

[1384] The server stores the coach information in a database.

[1385] The server prepares an appropriate AI model based on the stored coach information.

[1386] Step 3: Find a coach

[1387] Users who want to be coached access the platform and search for a specific category or coach.

[1388] The device sends a search query to the server.

[1389] Step 4: Providing matching results

[1390] The server filters suitable coaches from the database based on the search query.

[1391] The server sends the filtering results to the terminal and displays them to the user.

[1392] Step 5: Begin the coaching session

[1393] The user selects the desired coach.

[1394] The terminal sends a session request to the server.

[1395] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[1396] Example 2

[1397] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1398] Conventional coaching systems have had problems in effectively utilizing users' expertise and experience as data, and in providing highly personalized coaching that takes into account the user's emotional state. While there is a particular need for seamless processing from inputting expertise to conducting coaching sessions, many systems lack the ability to manage these processes in an integrated manner. Furthermore, there has been a lack of systems that can recognize users' emotions in real time and adjust the content and tone of coaching accordingly.

[1399] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1400] In this invention, the server includes: a data input means for a user to input their expertise and experience; a communication means for a terminal to send the input data to the server; a data management means for the server to analyze, classify, and store the data received; an AI model training means for the server to train an AI model using the stored data; an AI model provision means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user seeking coaching to search for and match with a coach; a session initiation means for starting an AI coaching session based on the search results; an emotion recognition means for the server to analyze emotions from the user's input data and voice data; and an adjustment means for adjusting the content and tone of coaching based on the analyzed emotion data. This makes it possible to effectively digitize a user's expertise and experience, recognize emotions, and provide highly personalized coaching.

[1401] "Data input means" refers to an interface or device that allows a user to input their own specialized knowledge and experience.

[1402] "Communication means" refers to the network functions and protocols that allow a terminal to send input data to a server.

[1403] "Data management means" refers to the functions and systems that allow the server to analyze and classify the data it receives and store it in a database.

[1404] "AI model training means" refers to the algorithms and methods used by the server to train the AI ​​model using the data stored on it.

[1405] "AI model provision means" refers to a mechanism for deploying trained AI models and making them available to users.

[1406] "Registration means" refers to a system or interface that allows a user to register by entering their coaching profile and areas of expertise.

[1407] "Search means" refers to a function or system that allows users who want to be coached to search for coaches and make appropriate matches.

[1408] "Session initiation means" refers to the function or process for initiating an AI coaching session based on the exploration results.

[1409] "Emotion recognition means" refers to the technology or algorithms that the server uses to analyze emotions from user input data and voice data.

[1410] "Adjustment measures" refer to mechanisms and functions for adjusting the content and tone of coaching based on analyzed emotional data.

[1411] This invention provides a system in which a user inputs their own expertise and experience, a generative AI model provides coaching based on that information, and the system also recognizes the user's emotions and adjusts the content and tone of the coaching. Specific embodiments of this system are described below.

[1412] Data entry and submission

[1413] First, a user enters their own expertise and experience using a browser or application input form. For example, if a user has expertise in cooking, they can enter detailed information such as recipes, cooking procedures, and tips.

[1414] The device then converts this input information into JSON format and sends it to the server as an HTTP request, which effectively transmits the data to the server.

[1415] Data organization and classification

[1416] The server analyzes the data received from the device, categorizes it, and stores it in a database. For example, cooking data is categorized into "recipes," "cooking steps," "tips," etc. This process organizes the data systematically, making subsequent processing easier.

[1417] Training and serving AI models

[1418] The server then retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. The algorithms used include natural language processing algorithms, machine learning, and deep learning. Specifically, a Transformer-based model can be used to create a conversational question-answering system.

[1419] The trained AI model is evaluated by the server to check its performance, and models that pass are deployed and made available to users.

[1420] Emotional awareness and coaching adjustment

[1421] During a coaching session, the server collects user input data and voice data and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[1422] Based on the analyzed emotional data, the server adjusts the content and tone of the coaching provided by the AI ​​model. For example, if the user is feeling stressed, the model can adjust its coaching to use a gentler tone.

[1423] Providing coaching services

[1424] Users complete the registration process by filling out a form describing their coaching profile and areas of expertise. This information is made publicly available to other users and stored in a database. When a user searches for a coach, their device sends a search query to the server, which then filters the results to find the appropriate coaches.

[1425] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model to initiate the AI ​​coaching session. During the session, the server analyzes the user's emotions and adjusts the content and tone of the coaching accordingly.

[1426] Examples of concrete examples and prompts

[1427] As a concrete example, the system usage procedure is as follows when User A wishes to receive cooking coaching. User A enters detailed cooking expertise (recipes, cooking tips, etc.), and the device sends the input information to the server, which organizes, categorizes, and stores the data. The server uses this data to train an AI model and deploys the trained model.

[1428] If User B wants cooking coaching and searches the platform, and finds a suitable coach, the device sends a session request to the server, which then starts the session. During the session, the server analyzes User B's emotions and adjusts the content and tone of the coaching accordingly.

[1429] An example of a prompt sentence is, "Please enter a cooking recipe. If you have any special dishes or cooking tips, please tell us in detail."

[1430] This system digitizes the user's expertise and experience, and is able to recognize emotions and provide highly individualized coaching.

[1431] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1432] Step 1:

[1433] Users input their expertise and experience using a browser or application input form. The input information is entered into the text fields of the input form. For example, recipe information such as "boil pasta for 10 minutes" or "simmer the sauce slowly over low heat" can be entered.

[1434] Input: User expertise and experience (e.g., recipes, cooking instructions, tips)

[1435] Output: Text information entered in the input form

[1436] Step 2:

[1437] The terminal converts the information entered by the user into JSON format, which standardizes and structures the data, and then sends this JSON data to the server using an HTTP POST request.

[1438] Input: Text information entered by the user into an input form

[1439] Output: JSON format data sent to the server

[1440] Step 3:

[1441] The server parses the received JSON data and categorizes it using a data analysis algorithm to separate the information into categories such as "recipes," "cooking instructions," and "tips." The categorized data is then stored in a database.

[1442] Input: JSON format data sent from the terminal

[1443] Output: Information in the database sorted by category

[1444] Step 4:

[1445] The server collects the necessary data from the database and prepares a training set for the AI ​​model. It preprocesses and cleans the data using natural language processing algorithms. The collected data is then used to train the AI ​​model using a Transformer-based model.

[1446] Input: Categorical data collected from a database

[1447] Output: A trained AI model

[1448] Step 5:

[1449] The server evaluates the trained AI model and checks its performance. A validation dataset is used for evaluation, and the model's prediction accuracy, response time, etc. Models that meet the performance standards are deployed and made available to users.

[1450] Input: A trained AI model

[1451] Output: Deployed AI model

[1452] Step 6:

[1453] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[1454] Input: Profile and professional information entered by the user into the input form

[1455] Output: Coach profile information stored in a database

[1456] Step 7:

[1457] To search for a desired coach, a user accesses the platform and searches for a specific category or coach. The device sends this search query to the server, which then filters the appropriate coaches and returns the results.

[1458] Input: A search query entered by a user on the platform.

[1459] Output: A list of suitable coaches returned as search results

[1460] Step 8:

[1461] The user selects the desired coach, and the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[1462] Input: Information about the coach selected by the user

[1463] Output: AI coaching session started

[1464] Step 9:

[1465] The server collects user input data and voice data during the coaching session and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[1466] Input: User input and voice data collected during a coaching session

[1467] Output: Parsed emotion data

[1468] Step 10:

[1469] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[1470] Input: Parsed emotion data

[1471] Output: Tailored coaching content and tone

[1472] These steps allow users to effectively digitize their expertise and receive emotion-aware, personalized AI coaching.

[1473] (Application example 2)

[1474] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1475] Conventional coaching systems have had difficulty taking into account the user's emotions and state when providing coaching based on the user's specialized knowledge and experience. Furthermore, due to a lack of emotion recognition and personalized product recommendation functions, improving user satisfaction has been an issue. The present invention aims to solve these problems and provide a system that appropriately analyzes a user's emotions and provides coaching and product recommendations based on those analyses.

[1476] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: data input means for a user to input specialized knowledge and experience; communication means for a terminal to send the input data to the server; data management means for the server to organize, classify, and store the received data in a database; AI model training means for the server to train an AI model using the stored data; AI model provision means for deploying the trained AI model and making it available to users; registration means for a user to register as a coach; search means for a user seeking coaching to search for and match with a coach; session initiation means for starting an AI coaching session based on the search results; emotion recognition means for analyzing emotions from the user's facial expressions and voice data; tone adjustment means for adjusting the content and tone of coaching based on the emotion analysis results; and product recommendation means for recommending products based on the user's input data and emotion data. This enables personalized coaching and individualized product recommendations that take user emotions into consideration.

[1477] "Data input means" refers to interface devices or software that allow users to input their specialized knowledge and experience.

[1478] "Communication means" refers to the protocol and equipment used by the terminal to transmit input data to the server.

[1479] "Data management means" refers to software and functions for organizing and classifying data received by the server and storing it in a database.

[1480] "AI model training means" refers to the algorithms and frameworks that allow the server to train the AI ​​model using stored data.

[1481] "AI model provision means" refers to a system for deploying trained AI models and making them available to users.

[1482] "Registration means" refers to the function or form that allows a user to register as a coach.

[1483] "Search means" refers to a search system or algorithm that allows users seeking coaching to search for coaches and make appropriate matches.

[1484] "Session initiation means" refers to the process or command for initiating an AI coaching session based on the exploration results.

[1485] "Emotion recognition means" refers to algorithms or sensors for analyzing emotions from a user's facial expressions and voice data.

[1486] "Tone adjustment means" refers to the functions and logic for adjusting the content and tone of coaching based on the results of emotional analysis.

[1487] "Product recommendation means" refers to an algorithm or system for recommending products based on user input data and emotional data.

[1488] An embodiment of this invention is a system in which a user inputs their expertise and experience, and AI provides coaching based on that input. Furthermore, this system has an emotion recognition function, which allows it to adjust the content and tone of the coaching based on the user's emotions. The present invention has functions related to data input of the user's expertise, emotion recognition, and product recommendations, among others.

[1489] The server provides interface devices and software as a means for users to input their expertise and experience. This allows users to enter their own expertise and experience in detail through a browser or application input form. For example, if users input their cooking expertise, recipes, cooking tips, and other information can be converted into data.

[1490] The input data is converted to JSON format by the device using a communication method and sent to the server as an HTTP request. The server organizes the received data, categorizes it, and stores it in a database. Through this process, cooking-related data is classified into categories such as "recipes," "cooking steps," and "tips."

[1491] The server uses the stored data to train an AI model. It preprocesses the data using natural language processing algorithms and deep learning techniques, and trains a conversational AI using a Transformer-based model. Once trained, the AI ​​model is deployed for use by users using an AI model provisioning method.

[1492] Furthermore, when the user's facial expression or voice data is input, the emotion recognition means analyzes it and identifies the user's emotion (e.g., joy, sadness, excitement, etc.). Based on this data, the tone adjustment means adjusts the content and tone of the coaching. For example, if it is analyzed that the user is feeling stressed, the coaching will be given in a gentler tone.

[1493] Furthermore, the product recommendation unit has the function of recommending appropriate products based on the user's input data and emotional data. This allows the system to provide products that match the user's preferences and interests, improving the shopping experience in the virtual store. For example, a user who enjoys cooking could be recommended a "luxury knife set" or a "recipe book."

[1494] Examples:

[1495] Users use the app to input their expertise and preferences, and the AI ​​recommends items like "luxury knife sets" and "recipe books." The user can then start a coaching session and request advice on "how to cook Japanese food." The camera and microphone then recognize the user's emotion as "joy," and a brighter message is displayed.

[1496] Example prompt sentence:

[1497] User: Hello, I'd like some advice on how to cook Japanese food.

[1498] AI: I see, let's have fun learning! Can you tell us about the basics of Japanese cuisine that you already know?

[1499] This invention enables personalized coaching and individualized product recommendations that take into account the user's emotions, thereby realizing the provision of services that provide high levels of user satisfaction.

[1500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1501] Step 1:

[1502] The user inputs his / her specialized knowledge and experience using the data input means.

[1503] Input: A user enters their cooking expertise (e.g., recipes, cooking tips) into an input form.

[1504] Data processing: Convert the input information into JSON format.

[1505] Output: Generates data in JSON format.

[1506] Step 2:

[1507] The terminal transmits the user's input data to the server using a communication means.

[1508] Input: Data in JSON format.

[1509] Data calculation: Sends input data to the server as an HTTP request.

[1510] Output: Data transferred to the server.

[1511] Step 3:

[1512] The server organizes and classifies the received data using data management means and stores it in a database.

[1513] Input: JSON formatted data sent to the server.

[1514] Data processing: Analyze the data and classify it into categories (e.g., "recipes," "cooking instructions," "tips").

[1515] Output: The organized and classified data is stored in a database.

[1516] Step 4:

[1517] The server uses the stored data to train the AI ​​model using the AI ​​model training means.

[1518] Input: Expert knowledge data stored in a database.

[1519] Data Computing: Preprocessing data and training AI models using natural language processing algorithms and deep learning techniques.

[1520] Output: A trained AI model.

[1521] Step 5:

[1522] The server deploys the trained AI model using an AI model provisioning means, making it available to users.

[1523] Input: A trained AI model.

[1524] Data Computing: Deploying trained models and making them accessible to users.

[1525] Output: Available AI models.

[1526] Step 6:

[1527] To register as a coach, the user uses the registration means to input the necessary information.

[1528] Input: User profile information and areas of expertise.

[1529] Data processing: Registration information is sent to the server and stored in the database.

[1530] Output: Registered coach information.

[1531] Step 7:

[1532] A user who wants to be coached searches for a coach using a search means, and an appropriate coach is matched.

[1533] Input: Search query of the user you want to be coached.

[1534] Data calculations: Filtering suitable coaches from a database based on a search query.

[1535] Output: A list of coaches displayed as search results.

[1536] Step 8:

[1537] An AI coaching session is initiated based on the search results using a session initiation means.

[1538] Input: The user's session request.

[1539] Data calculation: Calls the AI ​​model of the selected coach based on the session request and starts the session.

[1540] Output: The AI ​​coaching session that was started.

[1541] Step 9:

[1542] The user's facial expressions and voice data are analyzed using emotion recognition means.

[1543] Input: User's facial expression or voice data.

[1544] Data Computation: Emotion recognition algorithms are used to analyze emotions (e.g., happiness, sadness, excitement).

[1545] Output: Parsed emotion data.

[1546] Step 10:

[1547] Based on the emotion analysis results, the coaching content and tone are adjusted using a tone adjustment means.

[1548] Input: Parsed emotion data.

[1549] Data arithmetic: Adjust the tone and content of coaching based on emotional data.

[1550] Output: Tailored coaching messages.

[1551] Step 11:

[1552] A product recommendation means is used to recommend products based on user input data and emotional data.

[1553] Input: User profile information, expertise data, sentiment data.

[1554] Data calculation: Using AI algorithms, products that match the user's preferences are selected.

[1555] Output: A list of recommended products.

[1556] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1557] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1558] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1559] [Fourth embodiment]

[1560] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1561] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1562] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1563] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1564] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1565] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1566] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1567] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1568] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1569] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1570] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1571] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1572] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1573] This invention provides a system in which a user inputs their own expertise and experience and an AI provides coaching based on that input. This system includes: a data input means for the user to input their expertise and experience; a communication means for a terminal to send the input data to a server; a data management means for the server to organize and classify the data received and store it in a database; an AI model training means for training an AI model using the stored data; an AI model providing means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user who wants to be coached to search for and match with a coach; and a session initiation means for starting an AI coaching session based on the search results.

[1574] Steps for users to digitize their specialized knowledge

[1575] 1. Data Entry

[1576] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[1577] 2. Data Transmission

[1578] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[1579] 3. Data reception and organization

[1580] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[1581] Training and serving AI models

[1582] 1. Data collection

[1583] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[1584] 2. Training the AI ​​model

[1585] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[1586] 3. Evaluate and deploy the model

[1587] The server evaluates the trained model on a validation dataset to check its performance, and then deploys the passed model, making it available to users.

[1588] Providing coaching services

[1589] 1. Coach Registration

[1590] Users enter their coaching profile, describing their areas of expertise and achievements, and this information is sent from the device to the server and stored in a database.

[1591] 2. Coach search and matching

[1592] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[1593] 3. Beginning a coaching session

[1594] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[1595] Examples:

[1596] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1597] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[1598] 2. The device sends this data to the server, which organizes it and stores it in a database.

[1599] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1600] 4. User B wants cooking coaching and searches on the platform.

[1601] 5. If User B finds a suitable coach, the device sends a session request to the server.

[1602] 6. The server starts the session and User B receives coaching from the AI.

[1603] This system allows users to easily digitize their own expertise and provide services as an AI coach based on that data. Users who want to be coached can easily find the right coach and receive high-quality coaching.

[1604] The processing flow will be explained below.

[1605] Understood. Below I will explain the process in concrete steps.

[1606] Steps for users to digitize their specialized knowledge

[1607] Step 1: Data entry

[1608] Users input their expertise and experience through a browser or application.

[1609] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[1610] Step 2: Send data

[1611] The terminal converts the data entered by the user into JSON format.

[1612] The terminal sends the converted data to the server as an HTTP request.

[1613] Step 3: Analyze and store the data

[1614] The server receives the HTTP request and parses the JSON data.

[1615] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[1616] Training and serving AI models

[1617] Step 1: Collect data

[1618] The server retrieves data related to a particular category from the database.

[1619] The server prepares the acquired data as a dataset for training an AI model.

[1620] Step 2: Training the AI ​​model

[1621] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[1622] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[1623] Step 3: Evaluate and deploy the model

[1624] The server evaluates the trained AI model on a validation dataset to check its performance.

[1625] The server deploys the approved AI model and makes it accessible to users.

[1626] Providing coaching services

[1627] Step 1: Register as a coach

[1628] The user fills out an input form about their coaching profile and areas of expertise.

[1629] The terminal transmits the input coach information to the server.

[1630] Step 2: Save your coach information

[1631] The server stores the coach information in a database.

[1632] The server prepares an appropriate AI model based on the stored coach information.

[1633] Step 3: Find a coach

[1634] Users who want to be coached access the platform and search for a specific category or coach.

[1635] The device sends a search query to the server.

[1636] Step 4: Providing matching results

[1637] The server filters suitable coaches from the database based on the search query.

[1638] The server sends the filtering results to the terminal and displays them to the user.

[1639] Step 5: Begin the coaching session

[1640] The user selects the desired coach.

[1641] The terminal sends a session request to the server.

[1642] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[1643] These are the specific processing steps of the program in this system. This allows users to easily digitize their own expertise and use it to provide AI coaching services. Users who want to be coached can easily find the right coach and receive high-quality coaching services.

[1644] Example 1

[1645] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1646] Conventional AI coaching systems have had difficulty quickly and accurately converting users' expertise and experience into data, and then training and deploying advanced AI models based on that data. Furthermore, the coach search and matching process was not smooth, resulting in a poor user experience.

[1647] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1648] In this invention, the server includes a data management means, a data collection means, an AI model training means, and an AI model evaluation and provision means, which enables fast and accurate data classification and storage, effective AI model training and evaluation, and smooth coach search and matching.

[1649] "Data input means" refers to an interface that allows a user to input their own specialized knowledge and experience, and includes browsers, application input forms, and the like.

[1650] "Communication means" refers to a technology for transmitting data input from a terminal to a server, and includes HTTP requests based on the Internet Protocol.

[1651] "Data management means" refers to a system for analyzing and classifying data received by the server and storing it in a database, and includes analysis scripts and database management systems.

[1652] The "data collection means" is a system that allows the server to retrieve the necessary data from the database and prepare it as a training dataset for building an AI model.

[1653] An "AI model training means" is a system for training an AI model using machine learning or deep learning techniques with data that has been preprocessed by a server using a natural language processing algorithm.

[1654] The "AI model evaluation and provision means" is a system in which a server evaluates trained AI models and deploys approved models in a form that users can use.

[1655] The "registration means" is an interface that allows a user to input a profile as a coach and describe their area of ​​expertise and achievements.

[1656] "Search means" is a function that allows users who wish to be coached to access the platform and search for specific categories or coaches.

[1657] The "matching means" is a system that sends a search query to the server using a communication means based on the Internet Protocol, and the server filters suitable coaches.

[1658] The "session initiation means" is a function that allows the user to select a desired coach and start a coaching session.

[1659] This invention is a system in which users input their own expertise and experience, and AI provides coaching based on that. This system uses the following hardware and software:

[1660] First, users enter their expertise and experience using a form in a browser or dedicated application. The hardware used includes PCs, smartphones, tablets, etc. The software used includes any web browser (e.g., Google Chrome, Mozilla Firefox, etc.) or a dedicated application.

[1661] Next, the terminal converts the input data into JSON format and sends it to the server as an HTTP request. This communication method uses HTTP based on the Internet Protocol (TCP / IP). Specifically, a POST request is sent using the JavaScript fetch API.

[1662] The server analyzes the received data, categorizes it, and stores it in a database. This data analysis is performed using Python scripts, and database management systems such as MySQL or PostgreSQL are used for database management. For example, cooking data is categorized into categories such as "recipes," "cooking steps," and "tips."

[1663] The server then retrieves the necessary data from the database and prepares a training dataset for building an AI model. SQL queries and Python scripts are used to extract the data. The server then preprocesses the data using natural language processing algorithms and trains the model using machine learning and deep learning techniques. Libraries used include TensorFlow and PyTorch. For example, a Transformer-based model (such as BERT or GPT) is used to create a question-answering system.

[1664] The trained model is evaluated using a validation dataset. The server calculates the model's accuracy and F1 score, and deploys the model if it passes. Deployment is performed using cloud services such as AWS SageMaker or Azure ML, and the model is provided as an endpoint.

[1665] The system also provides an interface for users to enter their coaching profile, including their areas of expertise and achievements. This information is sent from the device to a server and stored in a database.

[1666] Users who want to be coached access the platform and search for a specific category or coach. This search is performed using a search engine such as Elasticsearch, and the user sends a search query from the device to the server. The server then filters the search results and returns the appropriate coaches.

[1667] Finally, once the user selects the desired coach, the device sends a session request to the server, which then calls the selected coach's AI model and starts the coaching session. This process uses technologies such as WebRTC and Socket.io for real-time communication.

[1668] Specific examples

[1669] Here's a real-world example:

[1670] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1671] 1. User A enters his / her cooking expertise (recipes, cooking tips, etc.) into the input form.

[1672] 2. The device converts this data into JSON format and sends it to the server.

[1673] 3. The server receives the data, analyzes and classifies it, and stores it in a database.

[1674] 4. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1675] 5. User B wants cooking coaching and searches on the platform.

[1676] 6. If User B finds a suitable coach, he sends a session request to the server.

[1677] 7. The server starts the session and User B receives coaching from the AI.

[1678] Prompt Sentence Examples

[1679] "Please explain the steps to train a Transformer-based AI model using cooking recipe data entered by User A."

[1680] "Please explain the process from when User B found the coach they wanted to coach to when they started the session."

[1681] This system allows users to effectively digitize their specialized knowledge and receive coaching based on high-quality AI models. Users who want to be coached can also easily find a suitable coach and receive high-quality coaching sessions.

[1682] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1683] Step 1:

[1684] The user enters their expertise and experience using a browser or application input form.

[1685] Example of operation: A user accesses a dedicated web application and enters a "delicious pasta recipe" and "tips for boiling time" into the input form.

[1686] Input: Text data entered by the user (e.g., "Delicious pasta recipes," "Tips for boiling time").

[1687] Output: Text data of the expertise and experience entered in the input form.

[1688] Step 2:

[1689] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1690] Example of operation: A JavaScript script executed in the device's browser converts text data into JSON format and sends it to the server as a POST request using the fetch API.

[1691] Input: Text data of expertise and experience entered into the input form.

[1692] Output: JSON formatted data and HTTP request.

[1693] Step 3:

[1694] The server receives the HTTP request, analyzes the data, categorizes it, and stores it in a database.

[1695] How it works: The Node.js Express framework receives the POST request, and a Python script parses the data and categorizes it into categories such as "Recipe," "Cooking Instructions," and "Tips," before storing it in a MySQL database.

[1696] Input: JSON formatted data and HTTP request.

[1697] Output: The data classified by category is saved in a database.

[1698] Step 4:

[1699] The server retrieves the necessary data from the database and prepares it as a training dataset for building an AI model.

[1700] How it works: The server runs an SQL query to get data about "cuisine" and builds a training dataset with a Python script.

[1701] Input: Categorical data stored in a database.

[1702] Output: A dataset used to train an AI model.

[1703] Step 5:

[1704] The server preprocesses the data and trains the AI ​​model using machine learning and deep learning techniques.

[1705] Working example: Clean text data with Python's Pandas library and train a Transformer-based model using TensorFlow.

[1706] Input: Training dataset.

[1707] Output: A trained AI model.

[1708] Step 6:

[1709] The server evaluates the trained model on the validation dataset and deploys the passing model.

[1710] Example of operation: A Python script is used to calculate the model accuracy and F1 score, and the passing model is deployed to AWS SageMaker.

[1711] Input: Trained AI model, validation dataset.

[1712] Output: The deployed AI model.

[1713] Step 7:

[1714] Users enter their coaching profile, listing their areas of expertise and achievements.

[1715] Example of how it works: A user accesses a dedicated web form, enters their profile information, and clicks the submit button.

[1716] Input: User profile information (e.g., areas of expertise, achievements).

[1717] Output: The profile information is sent to the server and stored in a database.

[1718] Step 8:

[1719] A user visits the platform and searches for a specific category or coach.

[1720] Example of operation: A user enters "cooking" as a search keyword in a browser and presses the search button.

[1721] Input: Search keyword.

[1722] Output: Search results are returned from the server and displayed to the user.

[1723] Step 9:

[1724] The user selects the desired coach and sends a session request to the server.

[1725] Example of how it works: User selects appropriate coach from search results and clicks on Start Session button. A session request is sent to the server.

[1726] Input: Session request.

[1727] Output: The server calls the AI ​​model of the selected coach and the coaching session begins.

[1728] (Application example 1)

[1729] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1730] Conventional coaching systems have limited means for users to effectively utilize their expertise and experience, and suffer from insufficient quality and personalization of coaching content. Furthermore, the process for users to search for and properly match with a coach is cumbersome, often resulting in a long wait before a session can begin smoothly. Therefore, there is a need for efficient and effective generation and delivery of high-quality, personalized coaching content based on expert knowledge.

[1731] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1732] In this invention, the server includes data input means for a user to input their expertise and experience, communication means for a terminal to send the input data to the server, data management means for the server to organize and classify the received data and store it in a database, AI model training means for the server to train an AI model using the stored data, AI model providing means for deploying the trained AI model and making it available to users, registration means for a user to register as a coach, search means for a user who wants to be coached to search for and match with a coach, session initiation means for starting an AI coaching session based on the search results, and content delivery means for delivering coaching content generated based on the expertise. This makes it possible to efficiently generate and deliver high-quality, personalized coaching content based on a user's expertise.

[1733] The "data input means" is an interface for users to input their specialized knowledge and experience.

[1734] "Communication means" refers to the technical means by which the terminal transmits input data to the server.

[1735] "Data management means" is a system that organizes and classifies data received by the server and stores it in a database.

[1736] "AI model training means" means a program or algorithm that the server uses to train the AI ​​model using the stored data.

[1737] An "AI model providing means" is a system that has the function of deploying trained AI models and making them available to users.

[1738] The "registration means" is an interface for a user to register profile information as a coach.

[1739] The "search means" is a technical means by which a user who wants to be coached searches for a coach and is matched with them.

[1740] The "session initiation means" is a system that has the functionality to initiate an AI coaching session based on the search results.

[1741] "Content Delivery Vehicle" means a platform or technological means for delivering coaching content generated based on expert knowledge.

[1742] This invention provides a system in which users input their specialized knowledge and experience, and AI provides coaching based on that information.

[1743] composition

[1744] The system includes the following means:

[1745] 1. Data entry method

[1746] 2. Means of communication

[1747] 3. Data Management Measures

[1748] 4. AI model training methods

[1749] 5. AI model provision method

[1750] 6. Registration Method

[1751] 7. Search method

[1752] 8. Session Initiation Methods

[1753] 9. Content Delivery Methods

[1754] The specific hardware and software used

[1755] The system uses the following hardware and software:

[1756] Django Rest Framework: A web framework used to create API endpoints.

[1757] Transformers (Hugging Face): Uses a library that provides models for natural language processing.

[1758] Database (e.g., PostgreSQL): Use a database to store expert knowledge and model information.

[1759] Entering and Submitting Data

[1760] Users use the application's input form to enter their expertise and experience in text format. For example, a user with expertise in cooking may enter recipes, cooking procedures, and tips. The device converts this input data into JSON format and sends it to the server using an HTTP request.

[1761] Receiving and organizing data

[1762] The server analyzes the received data, classifies it by category, and stores it in a database. For example, data about cooking is classified into categories such as "recipes," "cooking steps," and "tips." The classified data is stored in a database through a data management means.

[1763] Training and serving AI models

[1764] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and trains the model using machine learning or deep learning techniques. For example, a Transformer-based model is used to create a conversational question-answering system. The trained model is evaluated and its performance is confirmed before it is deployed, allowing users to use the trained AI model.

[1765] Register and find a coach

[1766] Users register as coaches by entering their profile and areas of expertise. The registered information is stored in a database. When another user wants coaching, they can search the platform for a specific category or coach. The device sends the search query to the server, which then filters the appropriate coaches.

[1767] Starting a coaching session and delivering content

[1768] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and starts the coaching session. At the same time, coaching content generated based on the coach's expertise is delivered.

[1769] Specific examples

[1770] For example, if a user inputs a "basic Italian recipe," the AI ​​will generate and deliver tutorial videos such as "how to make spaghetti" and "how to make sauce."

[1771] Example prompt sentence:

[1772] User Input: Basic Italian recipe. How to make pasta with tomato sauce. Ingredients: Tomatoes, garlic, olive oil, salt, pepper. Steps: 1. Chop the tomatoes. 2. Sauté the garlic. 3. ...

[1773] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1774] Step 1:

[1775] User enters expertise

[1776] Users input their expertise and experience in text format using a smartphone app or a web browser input form. This input includes, for example, recipes, cooking procedures, cooking tips, etc. The input text is converted into JSON format and sent from the device to the server using a communication method.

[1777] Input: Text data of expertise and experience

[1778] Output: JSON format data

[1779] Step 2:

[1780] Transfer of input data

[1781] The device sends the JSON-formatted data entered by the user to the server as an HTTP request, which may also include the user's profile information.

[1782] Input: JSON format data, user profile information

[1783] Output: Data sent to the server

[1784] Step 3:

[1785] Receiving and organizing data

[1786] The server analyzes the received data, classifies it by category, and stores it in a database. For example, cooking data is classified into categories such as "recipes," "cooking steps," and "tips." The data is also structured through data management methods.

[1787] Input: Data sent to the server

[1788] Output: Structured data stored in a database

[1789] Step 4:

[1790] Training an AI model

[1791] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. It preprocesses the data using natural language processing algorithms and then uses machine learning and deep learning techniques to train the AI ​​model. For example, it uses a Transformer-based model to create a conversational question-answering system.

[1792] Input: Structured data, training set

[1793] Output: A trained AI model

[1794] Step 5:

[1795] Evaluating and deploying AI models

[1796] The server evaluates the trained AI models and checks their performance. Successfully evaluated models are deployed and made available to users. This is done by making the models accessible through a model serving mechanism.

[1797] Input: A trained AI model

[1798] Output: Deployed AI model

[1799] Step 6:

[1800] Coach Registration

[1801] Users can register as coaches by entering their profile and areas of expertise. The registered information is stored in a database and can be used through search tools.

[1802] Input: Profile information, area of ​​expertise

[1803] Output: Coach information stored in a database

[1804] Step 7:

[1805] Explore Coaches

[1806] Users seeking coaching use the platform to search for specific categories and coaches. The device sends the search query to the server, which then filters and returns appropriate coaches.

[1807] Input: search query

[1808] Output: Filtered coach list

[1809] Step 8:

[1810] Starting a Session

[1811] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model and begins the coaching session.

[1812] Input: Session request

[1813] Output: Coaching sessions started

[1814] Step 9:

[1815] Content Delivery

[1816] Based on the coaching sessions, expertly generated coaching content is delivered, such as cooking tutorial videos or Q&A session results.

[1817] Input: Coaching session data

[1818] Output: Delivered coaching content

[1819] The steps outlined here allow for efficient generation and delivery of high-quality coaching content based on user expertise.

[1820] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1821] This invention provides a system in which a user inputs their own expertise and experience, and an AI provides coaching based on that input, and further adjusts the content and tone of the coaching based on the user's emotions. This system includes: a data input means for the user to input their expertise and experience, a communication means for a terminal to send the input data to a server, a data management means for the server to organize and classify the data received and store it in a database, an AI model training means for training an AI model using the stored data, an AI model providing means for deploying the trained AI model and making it available to users, a registration means for a user to register as a coach, a search means for a user who wants to be coached to search for and match with a coach, a session initiation means for starting an AI coaching session based on the search results, and an emotion recognition means for analyzing emotions from the user's input data and voice data.

[1822] Steps for users to digitize their specialized knowledge

[1823] 1. Data Entry

[1824] Users use input forms in browsers or applications to enter their expertise and experience. For example, if a user has knowledge about cooking, they will enter detailed recipes, cooking steps, tips, etc.

[1825] 2. Data Transmission

[1826] The device converts the information entered by the user into JSON format and sends it to the server as an HTTP request. This process ensures that the data arrives structured.

[1827] 3. Data reception and organization

[1828] The server analyzes the received data, categorizes it, and stores it in a database. For example, cooking data can be categorized into "recipes," "cooking steps," "tips," etc.

[1829] Training and serving AI models

[1830] 1. Data collection

[1831] The server retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. For example, it aggregates cooking-related data to build a training dataset.

[1832] 2. Training the AI ​​model

[1833] The server preprocesses the data using natural language processing algorithms and trains models using machine learning and deep learning techniques, such as using a Transformer-based model to create a conversational question-answering system.

[1834] 3. Evaluate and deploy the model

[1835] The server evaluates the trained AI model on a validation dataset to check its performance, and then deploys the passed model and makes it available to users.

[1836] Emotion Recognition and Applications

[1837] 1. Acquiring Emotion Data

[1838] The server collects user input data and voice data and passes the data to the emotion recognition means, for example, by collecting utterances and texts when the user interacts with the coach.

[1839] 2. Emotion Analysis

[1840] The server uses emotion recognition means to analyze the user's emotions (e.g., happiness, sadness, excitement, calmness) from the voice and text data. This process includes tone analysis of the voice and sentiment analysis of the text.

[1841] 3. Adjusting coaching content

[1842] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[1843] Providing coaching services

[1844] 1. Coach Registration

[1845] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[1846] 2. Coach search and matching

[1847] Users who want to be coached access the platform and search for a specific category or coach. The device sends the search query to the server, which filters the appropriate coaches and returns the search results.

[1848] 3. Beginning a coaching session

[1849] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[1850] Examples:

[1851] If user A wants to receive cooking coaching, he or she will use the system using the following procedure.

[1852] 1. User A enters detailed cooking expertise (recipes, cooking tips, etc.).

[1853] 2. The device sends the entered information to the server, which organizes the data and stores it in a database.

[1854] 3. The server trains the AI ​​model using the cooking data and deploys the trained model.

[1855] 4. User B wants cooking coaching and searches on the platform.

[1856] 5. If User B finds a suitable coach, the device sends a session request to the server.

[1857] 6. The server starts the session and User B receives coaching from the AI.

[1858] 7. During coaching, the server analyzes User B's emotions and adjusts the content and tone of the coaching.

[1859] This system allows users to easily digitize their own expertise and provide high-quality coaching using AI. In addition, by combining it with emotion recognition functionality, highly individualized instruction that takes into account the user's emotions becomes possible.

[1860] The processing flow will be explained below.

[1861] Understood. Below, I will explain the specific process step by step.

[1862] Steps for users to digitize their specialized knowledge

[1863] Step 1: Data entry

[1864] Users input their expertise and experience through a browser or application.

[1865] The user fills in the input form with details such as "recipe," "cooking procedure," and "tips."

[1866] Step 2: Send data

[1867] The terminal converts the data entered by the user into JSON format.

[1868] The terminal sends the converted data to the server as an HTTP request.

[1869] Step 3: Analyze and store the data

[1870] The server receives the HTTP request and parses the JSON data.

[1871] The server categorizes the parsed data into categories (e.g., "recipes," "cooking instructions," "tips") and stores them in a database.

[1872] Training and serving AI models

[1873] Step 1: Collect data

[1874] The server retrieves data related to a particular category from the database.

[1875] The server prepares the acquired data as a dataset for training an AI model.

[1876] Step 2: Training the AI ​​model

[1877] The server uses natural language processing (NLP) algorithms to perform preprocessing such as tokenization and normalization on the collected data.

[1878] The server uses the preprocessed data to train an AI model using machine learning or deep learning techniques (e.g., a Transformer model).

[1879] Step 3: Evaluate and deploy the model

[1880] The server evaluates the trained AI model on a validation dataset to check its performance.

[1881] The server deploys the approved AI model and makes it accessible to users.

[1882] Emotion Recognition and Applications

[1883] Step 1: Obtaining emotion data

[1884] The server collects user input data and voice data and passes the data to the emotion recognition means.

[1885] The user inputs statements and text when interacting with the coach.

[1886] Step 2: Sentiment Analysis

[1887] The server uses emotion recognition means to analyze the user's emotions (e.g., joy, sadness, excitement, calmness) from the voice data and text data.

[1888] The server performs tone analysis of the voice and sentiment analysis of the text.

[1889] Step 3: Adjust your coaching

[1890] The server then adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data.

[1891] If the user is stressed, the server adjusts the model to provide guidance in a gentler tone.

[1892] Providing coaching services

[1893] Step 1: Register as a coach

[1894] The user fills out an input form about their coaching profile and areas of expertise.

[1895] The terminal transmits the input coach information to the server.

[1896] Step 2: Save your coach information

[1897] The server stores the coach information in a database.

[1898] The server prepares an appropriate AI model based on the stored coach information.

[1899] Step 3: Find a coach

[1900] Users who want to be coached access the platform and search for a specific category or coach.

[1901] The device sends a search query to the server.

[1902] Step 4: Providing matching results

[1903] The server filters suitable coaches from the database based on the search query.

[1904] The server sends the filtering results to the terminal and displays them to the user.

[1905] Step 5: Begin the coaching session

[1906] The user selects the desired coach.

[1907] The terminal sends a session request to the server.

[1908] The server will call the AI ​​model of the selected coach and start the AI ​​coaching session.

[1909] Example 2

[1910] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1911] Conventional coaching systems have had problems in effectively utilizing users' expertise and experience as data, and in providing highly personalized coaching that takes into account the user's emotional state. While there is a particular need for seamless processing from inputting expertise to conducting coaching sessions, many systems lack the ability to manage these processes in an integrated manner. Furthermore, there has been a lack of systems that can recognize users' emotions in real time and adjust the content and tone of coaching accordingly.

[1912] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1913] In this invention, the server includes: a data input means for a user to input their expertise and experience; a communication means for a terminal to send the input data to the server; a data management means for the server to analyze, classify, and store the data received; an AI model training means for the server to train an AI model using the stored data; an AI model provision means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; a search means for a user seeking coaching to search for and match with a coach; a session initiation means for starting an AI coaching session based on the search results; an emotion recognition means for the server to analyze emotions from the user's input data and voice data; and an adjustment means for adjusting the content and tone of coaching based on the analyzed emotion data. This makes it possible to effectively digitize a user's expertise and experience, recognize emotions, and provide highly personalized coaching.

[1914] "Data input means" refers to an interface or device that allows a user to input their own specialized knowledge and experience.

[1915] "Communication means" refers to the network functions and protocols that allow a terminal to send input data to a server.

[1916] "Data management means" refers to the functions and systems that allow the server to analyze and classify the data it receives and store it in a database.

[1917] "AI model training means" refers to the algorithms and methods used by the server to train the AI ​​model using the data stored on it.

[1918] "AI model provision means" refers to a mechanism for deploying trained AI models and making them available to users.

[1919] "Registration means" refers to a system or interface that allows a user to register by entering their coaching profile and areas of expertise.

[1920] "Search means" refers to a function or system that allows users who want to be coached to search for coaches and make appropriate matches.

[1921] "Session initiation means" refers to the function or process for initiating an AI coaching session based on the exploration results.

[1922] "Emotion recognition means" refers to the technology or algorithms that the server uses to analyze emotions from user input data and voice data.

[1923] "Adjustment measures" refer to mechanisms and functions for adjusting the content and tone of coaching based on analyzed emotional data.

[1924] This invention provides a system in which a user inputs their own expertise and experience, a generative AI model provides coaching based on that information, and the system also recognizes the user's emotions and adjusts the content and tone of the coaching. Specific embodiments of this system are described below.

[1925] Data entry and submission

[1926] First, a user enters their own expertise and experience using a browser or application input form. For example, if a user has expertise in cooking, they can enter detailed information such as recipes, cooking procedures, and tips.

[1927] The device then converts this input information into JSON format and sends it to the server as an HTTP request, which effectively transmits the data to the server.

[1928] Data organization and classification

[1929] The server analyzes the data received from the device, categorizes it, and stores it in a database. For example, cooking data is categorized into "recipes," "cooking steps," "tips," etc. This process organizes the data systematically, making subsequent processing easier.

[1930] Training and serving AI models

[1931] The server then retrieves the necessary data from the database and prepares it as a training set for the AI ​​model. The algorithms used include natural language processing algorithms, machine learning, and deep learning. Specifically, a Transformer-based model can be used to create a conversational question-answering system.

[1932] The trained AI model is evaluated by the server to check its performance, and models that pass are deployed and made available to users.

[1933] Emotional awareness and coaching adjustment

[1934] During a coaching session, the server collects user input data and voice data and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[1935] Based on the analyzed emotional data, the server adjusts the content and tone of the coaching provided by the AI ​​model. For example, if the user is feeling stressed, the model can adjust its coaching to use a gentler tone.

[1936] Providing coaching services

[1937] Users complete the registration process by filling out a form describing their coaching profile and areas of expertise. This information is made publicly available to other users and stored in a database. When a user searches for a coach, their device sends a search query to the server, which then filters the results to find the appropriate coaches.

[1938] Once the user selects the desired coach, the device sends a session request to the server, which then invokes the selected coach's AI model to initiate the AI ​​coaching session. During the session, the server analyzes the user's emotions and adjusts the content and tone of the coaching accordingly.

[1939] Examples of concrete examples and prompts

[1940] As a concrete example, the system usage procedure is as follows when User A wishes to receive cooking coaching. User A enters detailed cooking expertise (recipes, cooking tips, etc.), and the device sends the input information to the server, which organizes, categorizes, and stores the data. The server uses this data to train an AI model and deploys the trained model.

[1941] If User B wants cooking coaching and searches the platform, and finds a suitable coach, the device sends a session request to the server, which then starts the session. During the session, the server analyzes User B's emotions and adjusts the content and tone of the coaching accordingly.

[1942] An example of a prompt sentence is, "Please enter a cooking recipe. If you have any special dishes or cooking tips, please tell us in detail."

[1943] This system digitizes the user's expertise and experience, and is able to recognize emotions and provide highly individualized coaching.

[1944] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1945] Step 1:

[1946] Users input their expertise and experience using a browser or application input form. The input information is entered into the text fields of the input form. For example, recipe information such as "boil pasta for 10 minutes" or "simmer the sauce slowly over low heat" can be entered.

[1947] Input: User expertise and experience (e.g., recipes, cooking instructions, tips)

[1948] Output: Text information entered in the input form

[1949] Step 2:

[1950] The terminal converts the information entered by the user into JSON format, which standardizes and structures the data, and then sends this JSON data to the server using an HTTP POST request.

[1951] Input: Text information entered by the user into an input form

[1952] Output: JSON format data sent to the server

[1953] Step 3:

[1954] The server parses the received JSON data and categorizes it using a data analysis algorithm to separate the information into categories such as "recipes," "cooking instructions," and "tips." The categorized data is then stored in a database.

[1955] Input: JSON format data sent from the terminal

[1956] Output: Information in the database sorted by category

[1957] Step 4:

[1958] The server collects the necessary data from the database and prepares a training set for the AI ​​model. It preprocesses and cleans the data using natural language processing algorithms. The collected data is then used to train the AI ​​model using a Transformer-based model.

[1959] Input: Categorical data collected from a database

[1960] Output: A trained AI model

[1961] Step 5:

[1962] The server evaluates the trained AI model and checks its performance. A validation dataset is used for evaluation, and the model's prediction accuracy, response time, etc. Models that meet the performance standards are deployed and made available to users.

[1963] Input: A trained AI model

[1964] Output: Deployed AI model

[1965] Step 6:

[1966] Users complete the registration form by filling out their coaching profile and areas of expertise. This information is sent from the device to the server and stored in a database.

[1967] Input: Profile and professional information entered by the user into the input form

[1968] Output: Coach profile information stored in a database

[1969] Step 7:

[1970] To search for a desired coach, a user accesses the platform and searches for a specific category or coach. The device sends this search query to the server, which then filters the appropriate coaches and returns the results.

[1971] Input: A search query entered by a user on the platform.

[1972] Output: A list of suitable coaches returned as search results

[1973] Step 8:

[1974] The user selects the desired coach, and the device sends a session request to the server, which then invokes the AI ​​model of the selected coach and begins the AI ​​coaching session.

[1975] Input: Information about the coach selected by the user

[1976] Output: AI coaching session started

[1977] Step 9:

[1978] The server collects user input data and voice data during the coaching session and passes them to the emotion recognition means, which performs tone analysis of the voice data and emotion analysis of the text data to analyze the user's emotional state.

[1979] Input: User input and voice data collected during a coaching session

[1980] Output: Parsed emotion data

[1981] Step 10:

[1982] The server adjusts the content and tone of the coaching provided by the AI ​​model based on the analyzed emotional data. For example, if the user is feeling stressed, the model adjusts the coaching to use a gentler tone.

[1983] Input: Parsed emotion data

[1984] Output: Tailored coaching content and tone

[1985] These steps allow users to effectively digitize their expertise and receive emotion-aware, personalized AI coaching.

[1986] (Application example 2)

[1987] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1988] Conventional coaching systems have had difficulty taking into account the user's emotions and state when providing coaching based on the user's specialized knowledge and experience. Furthermore, due to a lack of emotion recognition and personalized product recommendation functions, improving user satisfaction has been an issue. The present invention aims to solve these problems and provide a system that appropriately analyzes a user's emotions and provides coaching and product recommendations based on those analyses.

[1989] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: data input means for a user to input specialized knowledge and experience; communication means for a terminal to send the input data to the server; data management means for the server to organize, classify, and store the received data in a database; AI model training means for the server to train an AI model using the stored data; AI model provision means for deploying the trained AI model and making it available to users; registration means for a user to register as a coach; search means for a user seeking coaching to search for and match with a coach; session initiation means for starting an AI coaching session based on the search results; emotion recognition means for analyzing emotions from the user's facial expressions and voice data; tone adjustment means for adjusting the content and tone of coaching based on the emotion analysis results; and product recommendation means for recommending products based on the user's input data and emotion data. This enables personalized coaching and individualized product recommendations that take user emotions into consideration.

[1990] "Data input means" refers to interface devices or software that allow users to input their specialized knowledge and experience.

[1991] "Communication means" refers to the protocol and equipment used by the terminal to transmit input data to the server.

[1992] "Data management means" refers to software and functions for organizing and classifying data received by the server and storing it in a database.

[1993] "AI model training means" refers to the algorithms and frameworks that allow the server to train the AI ​​model using stored data.

[1994] "AI model provision means" refers to a system for deploying trained AI models and making them available to users.

[1995] "Registration means" refers to the function or form that allows a user to register as a coach.

[1996] "Search means" refers to a search system or algorithm that allows users seeking coaching to search for coaches and make appropriate matches.

[1997] "Session initiation means" refers to the process or command for initiating an AI coaching session based on the exploration results.

[1998] "Emotion recognition means" refers to algorithms or sensors for analyzing emotions from a user's facial expressions and voice data.

[1999] "Tone adjustment means" refers to the functions and logic for adjusting the content and tone of coaching based on the results of emotional analysis.

[2000] "Product recommendation means" refers to an algorithm or system for recommending products based on user input data and emotional data.

[2001] An embodiment of this invention is a system in which a user inputs their expertise and experience, and AI provides coaching based on that input. Furthermore, this system has an emotion recognition function, which allows it to adjust the content and tone of the coaching based on the user's emotions. The present invention has functions related to data input of the user's expertise, emotion recognition, and product recommendations, among others.

[2002] The server provides interface devices and software as a means for users to input their expertise and experience. This allows users to enter their own expertise and experience in detail through a browser or application input form. For example, if users input their cooking expertise, recipes, cooking tips, and other information can be converted into data.

[2003] The input data is converted to JSON format by the device using a communication method and sent to the server as an HTTP request. The server organizes the received data, categorizes it, and stores it in a database. Through this process, cooking-related data is classified into categories such as "recipes," "cooking steps," and "tips."

[2004] The server uses the stored data to train an AI model. It preprocesses the data using natural language processing algorithms and deep learning techniques, and trains a conversational AI using a Transformer-based model. Once trained, the AI ​​model is deployed for use by users using an AI model provisioning method.

[2005] Furthermore, when the user's facial expression or voice data is input, the emotion recognition means analyzes it and identifies the user's emotion (e.g., joy, sadness, excitement, etc.). Based on this data, the tone adjustment means adjusts the content and tone of the coaching. For example, if it is analyzed that the user is feeling stressed, the coaching will be given in a gentler tone.

[2006] Furthermore, the product recommendation unit has the function of recommending appropriate products based on the user's input data and emotional data. This allows the system to provide products that match the user's preferences and interests, improving the shopping experience in the virtual store. For example, a user who enjoys cooking could be recommended a "luxury knife set" or a "recipe book."

[2007] Examples:

[2008] Users use the app to input their expertise and preferences, and the AI ​​recommends items like "luxury knife sets" and "recipe books." The user can then start a coaching session and request advice on "how to cook Japanese food." The camera and microphone then recognize the user's emotion as "joy," and a brighter message is displayed.

[2009] Example prompt sentence:

[2010] User: Hello, I'd like some advice on how to cook Japanese food.

[2011] AI: I see, let's have fun learning! Can you tell us about the basics of Japanese cuisine that you already know?

[2012] This invention enables personalized coaching and individualized product recommendations that take into account the user's emotions, thereby realizing the provision of services that provide high levels of user satisfaction.

[2013] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2014] Step 1:

[2015] The user inputs his / her specialized knowledge and experience using the data input means.

[2016] Input: A user enters their cooking expertise (e.g., recipes, cooking tips) into an input form.

[2017] Data processing: Convert the input information into JSON format.

[2018] Output: Generates data in JSON format.

[2019] Step 2:

[2020] The terminal transmits the user's input data to the server using a communication means.

[2021] Input: Data in JSON format.

[2022] Data calculation: Sends input data to the server as an HTTP request.

[2023] Output: Data transferred to the server.

[2024] Step 3:

[2025] The server organizes and classifies the received data using data management means and stores it in a database.

[2026] Input: JSON formatted data sent to the server.

[2027] Data processing: Analyze the data and classify it into categories (e.g., "recipes," "cooking instructions," "tips").

[2028] Output: The organized and classified data is stored in a database.

[2029] Step 4:

[2030] The server uses the stored data to train the AI ​​model using the AI ​​model training means.

[2031] Input: Expert knowledge data stored in a database.

[2032] Data Computing: Preprocessing data and training AI models using natural language processing algorithms and deep learning techniques.

[2033] Output: A trained AI model.

[2034] Step 5:

[2035] The server deploys the trained AI model using an AI model provisioning means, making it available to users.

[2036] Input: A trained AI model.

[2037] Data Computing: Deploying trained models and making them accessible to users.

[2038] Output: Available AI models.

[2039] Step 6:

[2040] To register as a coach, the user uses the registration means to input the necessary information.

[2041] Input: User profile information and areas of expertise.

[2042] Data processing: Registration information is sent to the server and stored in the database.

[2043] Output: Registered coach information.

[2044] Step 7:

[2045] A user who wants to be coached searches for a coach using a search means, and an appropriate coach is matched.

[2046] Input: Search query of the user you want to be coached.

[2047] Data calculations: Filtering suitable coaches from a database based on a search query.

[2048] Output: A list of coaches displayed as search results.

[2049] Step 8:

[2050] An AI coaching session is initiated based on the search results using a session initiation means.

[2051] Input: The user's session request.

[2052] Data calculation: Calls the AI ​​model of the selected coach based on the session request and starts the session.

[2053] Output: The AI ​​coaching session that was started.

[2054] Step 9:

[2055] The user's facial expressions and voice data are analyzed using emotion recognition means.

[2056] Input: User's facial expression or voice data.

[2057] Data Computation: Emotion recognition algorithms are used to analyze emotions (e.g., happiness, sadness, excitement).

[2058] Output: Parsed emotion data.

[2059] Step 10:

[2060] Based on the emotion analysis results, the coaching content and tone are adjusted using a tone adjustment means.

[2061] Input: Parsed emotion data.

[2062] Data arithmetic: Adjust the tone and content of coaching based on emotional data.

[2063] Output: Tailored coaching messages.

[2064] Step 11:

[2065] A product recommendation means is used to recommend products based on user input data and emotional data.

[2066] Input: User profile information, expertise data, sentiment data.

[2067] Data calculation: Using AI algorithms, products that match the user's preferences are selected.

[2068] Output: A list of recommended products.

[2069] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2070] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2071] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2072] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2073] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2074] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2075] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2076] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2077] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2078] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2079] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2080] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2081] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2082] 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.

[2083] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2084] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2085] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2086] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2087] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2088] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2089] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2090] The following is further disclosed regarding the above embodiment.

[2091] Understood. Below are the draft claims:

[2092] (Claim 1)

[2093] data entry means for a user to enter expertise and experience;

[2094] a communication means for transmitting input data from the terminal to a server;

[2095] A data management means for organizing and classifying the data received by the server and storing it in a database;

[2096] an AI model training means for training an AI model using the data stored in the server;

[2097] An AI model provisioning means for deploying trained AI models and making them available to users;

[2098] a registration means for a user to register as a coach;

[2099] A search means for a user who wants to be coached to search for a coach and be matched with the coach;

[2100] a session initiation means for initiating an AI coaching session based on the search results;

[2101] A system including:

[2102] (Claim 2)

[2103] 2. The system of claim 1, wherein the data entered by the user is converted into JSON format and sent as an HTTP request.

[2104] (Claim 3)

[2105] The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning and deep learning techniques.

[2106] "Example 1"

[2107] (Claim 1)

[2108] data entry means for a user to enter expertise and experience;

[2109] a communication means for transmitting input data from the terminal to a server;

[2110] A data management means for analyzing and classifying the data received by the server and storing the data in a database;

[2111] a data collection means for the server to retrieve the stored data and prepare it as a training dataset for building an AI model;

[2112] an AI model training means for training an AI model using machine learning or deep learning techniques using data preprocessed by the server using a natural language processing algorithm;

[2113] An AI model evaluation and provision means for the server to evaluate the trained AI model and deploy a passed model;

[2114] a registration means for users to enter their coaching profile and list their areas of expertise and achievements;

[2115] A search mechanism that allows users seeking coaching to access the platform and search for specific categories or coaches;

[2116] a matching means for transmitting a search query to a server using a communication means based on an Internet protocol, and for the server to filter suitable coaches;

[2117] a session initiation means for allowing a user to select a desired coach and start a coaching session;

[2118] A system including:

[2119] (Claim 2)

[2120] 2. The system of claim 1, wherein the data entered by the user is converted into JSON format and sent as an HTTP request.

[2121] (Claim 3)

[2122] The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning and deep learning techniques.

[2123] "Application Example 1"

[2124] (Claim 1)

[2125] data entry means for a user to enter expertise and experience;

[2126] a communication means for transmitting input data from the terminal to a server;

[2127] A data management means for organizing and classifying the data received by the server and storing it in a database;

[2128] an AI model training means for training an AI model using the data stored in the server;

[2129] An AI model provisioning means for deploying trained AI models and making them available to users;

[2130] a registration means for a user to register as a coach;

[2131] A search means for a user who wants to be coached to search for a coach and be matched with the coach;

[2132] a session initiation means for initiating an AI coaching session based on the search results;

[2133] a content delivery means for delivering coaching content generated based on specialized knowledge;

[2134] A system including:

[2135] (Claim 2)

[2136] 2. The system of claim 1, wherein the data entered by the user is converted into JSON format and sent as an HTTP request.

[2137] (Claim 3)

[2138] The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning and deep learning techniques.

[2139] "Example 2: Combining Emotion Engines"

[2140] (Claim 1)

[2141] data entry means for a user to enter expertise and experience;

[2142] a communication means for transmitting input data from the terminal to a server;

[2143] A data management means for analyzing, classifying and storing the data received by the server;

[2144] an AI model training means for training an AI model using the data stored in the server;

[2145] An AI model provisioning means for deploying trained AI models and making them available to users;

[2146] a registration means for a user to register as a coach;

[2147] A search means for a user who wants to be coached to search for a coach and be matched with the coach;

[2148] a session initiation means for initiating an AI coaching session based on the search results;

[2149] An emotion recognition means for the server to analyze emotions from user input data and voice data;

[2150] an adjustment method to adjust the content and tone of coaching based on the analyzed emotional data;

[2151] A system including:

[2152] (Claim 2)

[2153] 2. The system of claim 1, wherein the data entered by the user is converted into JSON format and sent as an HTTP request.

[2154] (Claim 3)

[2155] The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning and deep learning techniques.

[2156] "Application example 2 when combining emotion engines"

[2157] (Claim 1)

[2158] data entry means for a user to enter expertise and experience;

[2159] a communication means for transmitting input data from the terminal to a server;

[2160] A data management means for organizing and classifying the data received by the server and storing it in a database;

[2161] an AI model training means for training an AI model using the data stored in the server;

[2162] An AI model provisioning means for deploying trained AI models and making them available to users;

[2163] a registration means for a user to register as a coach;

[2164] A search means for a user who wants to be coached to search for a coach and be matched with the coach;

[2165] a session initiation means for initiating an AI coaching session based on the search results;

[2166] emotion recognition means for analyzing emotions from facial expressions and voice data of a user;

[2167] a tone adjustment means for adjusting the content and tone of coaching based on the emotion analysis results;

[2168] a product recommendation means for recommending products based on user input data and emotion data;

[2169] A system including:

[2170] (Claim 2)

[2171] 2. The system of claim 1, wherein the data entered by the user is converted into JSON format and sent as an HTTP request.

[2172] (Claim 3)

[2173] The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning and deep learning techniques. [Explanation of symbols]

[2174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. data entry means for a user to enter expertise and experience; a communication means for transmitting input data from the terminal to the server; A data management means for organizing and classifying the data received by the server and storing it in a database; an AI model training means for training an AI model using the data stored in the server; An AI model provisioning means for deploying the trained AI model and making it available to users; a registration means for a user to register as a coach; A search means for a user who wants to be coached to search for a coach and be matched with them; a session initiation means for initiating an AI coaching session based on the search results; A system including:

2. 2. The system according to claim 1, wherein data entered by a user is converted into JSON format and transmitted as an HTTP request.

3. The system of claim 1, wherein the server preprocesses the data using natural language processing algorithms and trains the AI ​​model using machine learning or deep learning techniques.

Images