System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a user request; means for obtaining user information from a database; means for automatically generating a training plan using a generation AI; and means for transmitting the generated training plan to a user device.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] Due to a shortage of trainers with sports science expertise and a shortage of trainers at fitness gyms and sports teams, it is difficult to provide timely and appropriate training and nutritional advice to a large number of users. When one trainer tries to handle multiple members, the response to each user becomes slow or the quality of the support decreases, which is an issue. In addition, hiring individual trainers increases costs and places a burden on users. [Means for solving the problem]

[0005] The present invention is a system that includes a means for accepting user requests, a means for acquiring user information from a database, a means for automatically generating a training plan using a generation AI, and a means for sending the generated training plan to a user terminal. Furthermore, by adding a means for automatically generating nutritional advice using the generation AI and a means for receiving user progress information and automatically generating feedback using the generation AI, it becomes possible to provide users with personalized, high-quality training plans and nutritional advice. This system can efficiently provide professional advice on training and nutrition to a large number of users, simultaneously solving problems of cost and quality.

[0006] "User" means an individual or entity that uses the system and requests training plans and nutrition advice.

[0007] A "request" is a user's request to the system for a particular service (e.g., generating a training plan or providing nutritional advice).

[0008] "Database" means a system for storing and managing user information, training plans, nutritional data, and the like.

[0009] "Generative AI" refers to programs or models that use artificial intelligence to analyze data and perform specific tasks, in this case to automatically generate training plans or nutritional advice.

[0010] A "training plan" is a specific exercise program and schedule customized to meet a user's fitness goals.

[0011] "Nutrition Advice" refers to dietary and nutritional guidance and advice tailored to a user's health status and goals.

[0012] "User terminal" refers to a device (e.g., smartphone, tablet, PC, etc.) used by a user to access the system.

[0013] "Feedback" refers to evaluations and instructions for improvement provided by the system based on the user's progress. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a method for utilizing generative AI models to realize a system that provides sports science knowledge. Below, we will explain the important components of the system and their specific operations.

[0036] User Registration

[0037] 1. User Device:

[0038] The user installs the app and enters the required information on the new registration screen, including their name, email address, and password.

[0039] When the registration button is clicked, the form data is sent to the server in JSON format.

[0040] 2. Server:

[0041] The server receives the request and performs validation of the information entered, for example checking that the email address is formatted correctly or that the password is strong.

[0042] If validation is successful, the user information is saved in the database, a success response is sent back to the user's device, and a message indicating successful registration is displayed to the user.

[0043] Providing training plans

[0044] 1. User Device:

[0045] The user clicks the request a training plan button within the app.

[0046] The request is sent to the server in JSON format.

[0047] 2. Server:

[0048] The server receives the request and retrieves the profile information of the user from the database.

[0049] Based on the acquired user information, a generative AI model (e.g., ChatGPT) is asked to generate a training plan.

[0050] The generation AI generates a customized training plan, which the server then sends back to the user's device.

[0051] 3. User Device:

[0052] The user terminal displays the received training plan information on the screen, providing details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[0053] Providing nutritional advice

[0054] 1. User Device:

[0055] The user clicks the "Request Nutritional Advice" button.

[0056] The request is sent to the server in JSON format.

[0057] 2. Server:

[0058] The server receives the request and retrieves the nutrition-related information for the user from the database.

[0059] Based on the acquired user information and request content, the generative AI model is asked to generate nutritional advice.

[0060] The generation AI generates customized nutrition advice, and the server sends the advice back to the user's device.

[0061] 3. User Device:

[0062] The user terminal displays the received nutrition advice information on the screen and provides specific advice such as "eat a high-protein meal for breakfast."

[0063] Progress management and feedback

[0064] 1. User Device:

[0065] Users enter their exercise and diet progress information into the app.

[0066] 2. Server:

[0067] The server stores the progress data in a database and generates feedback using a generative AI model.

[0068] The generated feedback is sent to the user's device, providing the user with progress-based evaluations and suggestions for improvement.

[0069] Specific examples

[0070] Example 1: Retrieving a training plan

[0071] 1. User Device:

[0072] User A clicks the button to request a training plan.

[0073] The request is sent to the server in JSON format.

[0074] 2. Server:

[0075] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[0076] The training plan received from the generation AI is sent back to the user's device.

[0077] 3. User Device:

[0078] User A checks the received training plan on the screen and exercises based on the plan.

[0079] Example 2: Getting nutrition advice

[0080] 1. User Device:

[0081] User B clicks the button to request nutrition advice.

[0082] The request is sent to the server in JSON format.

[0083] 2. Server:

[0084] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[0085] The nutritional advice received from the generating AI is sent back to the user's device.

[0086] 3. User Device:

[0087] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[0088] As described above, this system uses generative AI to provide personalized training plans and nutritional advice based on user requests, thereby realizing efficient and high-quality services for a large number of users.

[0089] The processing flow will be explained below.

[0090] Handling user registration

[0091] Step 1:

[0092] User device: The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[0093] Step 2:

[0094] User device: When the registration button is clicked, the form data is sent to the server in JSON format.

[0095] Step 3:

[0096] Server: Receives the request and validates the entered information, specifically checking the format of the email address and the strength of the password.

[0097] Step 4:

[0098] Server: If validation is successful, save the user information to the database.

[0099] Step 5:

[0100] Server: Sends a success response to the user terminal, and the user terminal displays a message indicating successful registration.

[0101] Providing training plans

[0102] Step 1:

[0103] User device: The user clicks the training plan request button within the app.

[0104] Step 2:

[0105] User terminal: The request is sent to the server in JSON format.

[0106] Step 3:

[0107] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[0108] Step 4:

[0109] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[0110] Step 5:

[0111] Server: Returns the training plan received from the generation AI to the user device.

[0112] Step 6:

[0113] User device: Displays the received training plan information on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[0114] Providing nutritional advice

[0115] Step 1:

[0116] User terminal: The user clicks on the "Request nutrition advice" button.

[0117] Step 2:

[0118] User terminal: The request is sent to the server in JSON format.

[0119] Step 3:

[0120] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[0121] Step 4:

[0122] Server: Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice. The generative AI model takes into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[0123] Step 5:

[0124] Server: Returns the nutrition advice received from the generation AI to the user's device.

[0125] Step 6:

[0126] User device: The received nutrition advice information is displayed on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[0127] Progress management and feedback

[0128] Step 1:

[0129] User device: The user enters exercise and diet progress information into the app.

[0130] Step 2:

[0131] Server: Receives progress data and stores it in a database.

[0132] Step 3:

[0133] Server: Based on the progress data, the server requests the generative AI model to generate feedback. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[0134] Step 4:

[0135] Server: Returns the feedback received from the generation AI to the user device.

[0136] Step 5:

[0137] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[0138] Through the above processing flow, the system can provide users with personalized training plans and nutritional advice, and can also provide progress management and feedback functions, realizing an efficient and high-quality service.

[0139] Example 1

[0140] 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."

[0141] Traditional methods have not made it easy for users to quickly and efficiently obtain personalized training plans and nutritional advice. It has also been difficult to monitor users' progress in real time and provide appropriate feedback. Therefore, there has been a need for a system that can help users achieve their health and fitness goals.

[0142] 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.

[0143] In this invention, the server includes: means for transmitting form data in JSON format to the server when a user enters necessary information on a new registration screen and clicks the registration button; means for the server to receive the request, validate the entered information, and, if successful, store the user information in a database and return a success response to the user terminal; means for transmitting a request in JSON format to the server when the user terminal clicks a training plan request button; means for the server to receive the request, retrieve the user's profile information from the database, and request the generation AI model to generate a training plan; and means for returning the generated training plan to the user terminal and displaying the training plan received by the user terminal on the screen. This allows users to quickly and efficiently obtain personalized training plans and nutritional advice, and also enables progress management in real time.

[0144] A "user terminal" is an electronic device used by a user to input information and communicate with the system.

[0145] A "server" is a centralized computer system that receives requests from user devices, validates information, and interacts with databases.

[0146] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in an organized text format.

[0147] A "database" is a system that stores information in a structured format and allows it to be searched and updated later.

[0148] A "generative AI model" is an algorithm or software that uses artificial intelligence technology to generate information, such as a model that automatically generates training plans or nutritional advice.

[0149] "Validation" is the process of checking whether the entered information is in the correct format or meets certain conditions.

[0150] "Feedback" is information, including evaluations and suggestions for improvement, that the system provides based on the user's progress.

[0151] "Profile information" is information about the attributes and status of each user, including, for example, age, height, weight, and fitness level.

[0152] A "training plan" is an exercise program created by a generative AI model to achieve a user's fitness goals.

[0153] "Nutrition advice" refers to advice and suggestions about a user's diet, which are customized and generated by a generative AI model.

[0154] The present invention is a system that uses generative AI models to provide users with sports science-based training plans and nutrition advice. Specific embodiments of the present invention are described in detail below.

[0155] User Registration

[0156] First, in order for a user to use the system, they must register using their device. The user installs the app and enters information such as their name, email address, and password on the registration screen. Once the user has completed the entry and clicked the registration button, the entered information is sent to the server in JSON format.

[0157] The server receives the request sent from the user terminal and validates the input information. For example, it checks whether the email address format is correct and whether the password is strong. If validation is successful, the user information is saved in the database and a response indicating successful registration is sent back to the user terminal. The user terminal receives this response and displays a message indicating successful registration on its screen.

[0158] Providing training plans

[0159] To request a training plan, a user clicks on the training plan request button in the app. This request is sent to the server in JSON format. After receiving the request, the server retrieves the user's profile information from the database.

[0160] Next, a prompt is generated and sent to the generative AI model (e.g., ChatGPT). The prompt includes information such as the user's age, height, weight, and fitness level. Based on the generated prompt, the generative AI model generates a customized training plan. The server receives the generated training plan and sends it to the user's device. The user's device receives this information and displays details such as "chest training" on Mondays and "aerobic exercise" on Tuesdays.

[0161] Providing nutritional advice

[0162] When a user requests nutrition advice, they click the "Request Nutrition Advice" button in the app. The request is sent to the server in JSON format. After receiving the request, the server retrieves the user's nutrition-related information from the database.

[0163] Based on the acquired nutritional information, the server sends prompts to the generative AI model, asking it to generate customized nutritional advice. The generated nutritional advice is sent to the user's device via the server, and the user's device displays this information on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[0164] Progress management and feedback

[0165] Users enter their exercise and diet progress information into the app. The server receives and stores this progress information and requests the generative AI model to generate feedback. The generated feedback is sent from the server to the user's device, and the user is given an evaluation and suggestions for improvement based on their progress.

[0166] Examples of concrete examples and prompts

[0167] Example 1: Obtaining a training plan

[0168] When User A clicks the button to request a training plan, the request is sent in JSON format to the server. The server obtains the user's profile information and asks the generation AI to generate a training plan. The generated training plan is sent back to the user's device, and User A checks the received plan and performs the exercise.

[0169] Example 2: Getting nutrition advice

[0170] When User B clicks the button to request nutrition advice, the request is sent in JSON format to the server. The server obtains the user's nutrition-related information and asks the AI ​​to generate advice. The generated nutrition advice is sent back to the user's device, where User B can review the advice and plan their meals.

[0171] Prompt Sentence Examples

[0172] "Generate a training plan. Your profile information is as follows: age 30, height 175cm, weight 70kg, and fitness level intermediate."

[0173] "Generate nutrition advice. User's nutritional information is: vegan, goal weight 65kg, current weight 70kg."

[0174] As described above, the present invention uses generative AI models to provide users with personalized training plans and nutritional advice, and provides progress management and feedback, thereby achieving efficient and high-quality services.

[0175] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0176] Step 1: Enter user registration information

[0177] User device:

[0178] Input: User information such as name, email address, and password.

[0179] How it works: The user installs the app and enters the required information on the new registration screen.

[0180] Output: When the registration button is clicked, the entered information is sent to the server as JSON format data.

[0181] Step 2: Information validation and storage

[0182] server:

[0183] Input: JSON format user information sent from the user device.

[0184] What it does: The server receives the request, checks that the email address is valid and the password is strong, and if validation is successful, stores the user information in the database.

[0185] Output: Generates a response indicating successful registration and sends it to the user's device. If any information is inaccurate, generates and returns an error message.

[0186] Step 3: Viewing registration results

[0187] User device:

[0188] Input: Registration success or error message sent by the server.

[0189] Operation: The user terminal displays the received message on the screen.

[0190] Output: Registration success message or error message.

[0191] Step 4: Submit a training plan request

[0192] User device:

[0193] Enter: Click on Training Plan Request.

[0194] What happens: A user clicks the in-app training plan request button.

[0195] Output: The request is sent to the server as JSON data.

[0196] Step 5: Obtain user information

[0197] server:

[0198] Input: Training plan request sent from user device.

[0199] How it works: The server receives the request and retrieves the user's profile information (age, height, weight, fitness level, etc.) from the database.

[0200] Output: The retrieved profile information.

[0201] Step 6: Prompt generation and AI requests

[0202] server:

[0203] Input: User profile information.

[0204] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate a training plan.

[0205] Output: The generated training plan.

[0206] Step 7: Submit your training plan

[0207] server:

[0208] Input: The training plan received from the generative AI model.

[0209] Operation: The server transmits the generated training plan to the user terminal.

[0210] Output: The training plan sent to the user device.

[0211] Step 8: View your training plan

[0212] User device:

[0213] Input: The training plan sent by the server.

[0214] How it works: The user device displays the received training plan on the screen, providing details such as "chest workout" on Monday and "cardio" on Tuesday.

[0215] Output: Training plan displayed on the screen.

[0216] Step 9: Submit a nutrition advice request

[0217] User device:

[0218] Enter: Click on Request Nutritional Advice.

[0219] What happens: A user clicks the "Request Nutrition Advice" button in the app.

[0220] Output: The request is sent to the server as JSON data.

[0221] Step 10: Obtaining user nutrition information

[0222] server:

[0223] Input: A nutrition advice request sent from a user device.

[0224] How it works: The server receives the request and retrieves the user's nutrition-related information (such as dietary preferences and allergy information) from the database.

[0225] Output: Retrieved nutrition-related information.

[0226] Step 11: Prompt generation and AI request (nutritional advice)

[0227] server:

[0228] Input: User nutrition related information.

[0229] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate nutritional advice.

[0230] Output: The generated nutrition advice.

[0231] Step 12: Send nutrition advice

[0232] server:

[0233] Input: Nutrition advice received from a generative AI model.

[0234] Operation: The server transmits the generated nutrition advice to the user terminal.

[0235] Output: Nutrition advice sent to the user device.

[0236] Step 13: View nutrition advice

[0237] User device:

[0238] Input: Nutrition advice sent from the server.

[0239] Operation: The user device displays the received nutrition advice on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[0240] Output: Nutrition advice displayed on the screen.

[0241] Step 14: Enter progress information

[0242] User device:

[0243] Input: Exercise and diet progress information.

[0244] How it works: Users enter exercise and diet progress information into the app.

[0245] Output: The entered progress information is sent to the server in JSON format.

[0246] Step 15: Save progress information and request AI

[0247] server:

[0248] Input: Progress information sent from the user's device.

[0249] How it works: The server stores progress information in a database and asks the generative AI model to generate feedback based on the stored progress data.

[0250] Output: The generated feedback.

[0251] Step 16: Send feedback

[0252] server:

[0253] Input: Feedback received from the generative AI model.

[0254] Operation: The server sends the generated feedback to the user terminal.

[0255] Output: Feedback sent to the user device.

[0256] Step 17: Viewing feedback

[0257] User device:

[0258] Input: Feedback sent by the server.

[0259] How it works: The user device displays the received feedback on its screen, providing the user with a rating and suggestions for improvement based on their progress.

[0260] Output: Feedback displayed on the screen.

[0261] (Application example 1)

[0262] 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."

[0263] In today's advanced information society, various security threats exist on a daily basis, requiring rapid and appropriate responses to these threats. At the same time, there is a growing demand for personalized training plans and nutritional advice that utilize knowledge of sports science. However, there is a lack of mechanisms to efficiently provide these to individual users. Furthermore, it is difficult to utilize wearable devices such as smart glasses to perform real-time situation analysis and present appropriate defensive measures. Given this background, there is a need for a system that can provide personalized training plans and nutritional advice while also effectively providing security support through devices such as smart glasses.

[0264] 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.

[0265] In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the situation based on data acquired from sensors, and means for providing defensive measures according to the situation using the generation AI. This makes it possible to provide the user with a personalized training plan and nutritional advice, while also providing real-time security support through the wearable device.

[0266] "User" refers to an individual or corporation that uses this system, and whose information is registered in the database.

[0267] The "means for accepting a request" is an interface for receiving a request from a user in an input format and transmitting it to a server.

[0268] A "database" is a system for storing user information and related data, and for searching and retrieving them as needed.

[0269] "User information" refers to various data required by the system, such as a user's personal information, profile data, and activity history.

[0270] "Generative AI" is a technology that uses machine learning models trained on large datasets to generate training plans, nutritional advice, and situational defensive strategies based on user requests.

[0271] A "training plan" is an exercise program automatically created by the generation AI based on the user's health condition and goals.

[0272] "Nutrition advice" refers to dietary suggestions provided by the generative AI based on the user's diet and health status.

[0273] A "user terminal" is a device (e.g., a smartphone, smart glasses, head-mounted display, etc.) that a user uses to access the system.

[0274] A "sensor" is a device for detecting environmental information and user activity, and includes a camera, microphone, GPS, etc.

[0275] "Situation analysis" is the process of assessing the current environment and the user's situation based on data obtained from sensors.

[0276] "Defensive measures" are guidelines and countermeasures provided by the generative AI based on situational analysis to ensure the user's safety.

[0277] "Progress information" is data related to training plans and nutrition advice, such as records of exercise and meals a user has completed.

[0278] "Feedback" refers to evaluations and suggestions for improvement provided by the generating AI based on the user's progress information.

[0279] The present invention is a system that utilizes generative AI models to provide users with personalized training plans, nutritional advice, and security support. The specific operation of the system is described below.

[0280] 1. User Registration

[0281] User device:

[0282] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The form data is sent to the server in JSON format.

[0283] server:

[0284] The server receives the request, validates the entered information, and if successful, stores the user information in a database and returns a message to the user terminal indicating successful registration.

[0285] 2. Providing training plans

[0286] User device:

[0287] The user clicks the training plan request button and the request is sent to the server in JSON format.

[0288] server:

[0289] The server receives the request, retrieves the user's profile information from the database, and requests the generation AI to generate a training plan. The generated training plan is then sent back to the user's device.

[0290] User device:

[0291] The user displays the received training plan on the screen and performs exercise based on the plan's contents.

[0292] 3. Providing nutritional advice

[0293] User device:

[0294] The user clicks the request nutrition advice button and the request is sent in JSON format to the server.

[0295] server:

[0296] The server receives the request, retrieves the user's nutrition-related information from the database, and requests the AI ​​to generate advice. The generated nutrition advice is then sent back to the user's device.

[0297] User device:

[0298] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[0299] 4. Security Support

[0300] User device (smart glasses):

[0301] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings and send the data in JSON format to a server.

[0302] server:

[0303] The server receives and analyzes the data sent from the sensors and performs situation analysis. Based on the analysis results, the generative AI provides appropriate defensive measures.

[0304] User device:

[0305] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[0306] 5. Progress Management and Feedback

[0307] User device:

[0308] Users enter their exercise and diet progress information into the app.

[0309] server:

[0310] The server stores the progress data in a database, and the AI ​​generates feedback based on the progress. The generated feedback is sent to the user's device and displayed on the screen.

[0311] Hardware and Software Use

[0312] Hardware:

[0313] Smart glasses (e.g., Google Glass, Microsoft HoloLens)

[0314] Built-in sensors (camera, microphone, GPS)

[0315] software:

[0316] Web server (e.g. Python Flask, Django)

[0317] Database (e.g. MySQL, PostgreSQL)

[0318] Generative AI models (e.g. ChatGPT)

[0319] Specific examples

[0320] Get your training plan

[0321] 1. User Device:

[0322] User A clicks the button to request a training plan, and the request is sent to the server in JSON format.

[0323] 2. Server:

[0324] The server acquires the user's profile information and requests the AI ​​to generate a training plan. The AI ​​then returns the training plan to the user's device.

[0325] 3. User Device:

[0326] User A checks the received training plan on the screen and exercises based on the plan.

[0327] Prompt Sentence Examples

[0328] 1. Training plan generation prompt:

[0329] Current Situation: User A is looking to improve his muscle strength.

[0330] Q: Create a training plan for the week.

[0331] 2. Nutrition advice generation prompts:

[0332] Current Situation: User B is trying to lose weight.

[0333] Q: What is your daily meal plan?

[0334] 3. Situation Analysis Prompt:

[0335] Current situation: Unknown people are approaching you.

[0336] Information: It's 8pm and the location is on a deserted street.

[0337] Question: How can I stay safe?

[0338] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0339] Step 1:

[0340] User Registration

[0341] User device:

[0342] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The input data (name, email address, and password) is sent to the server in JSON format.

[0343] server:

[0344] The server receives the request and validates the input data. If validation is successful, the user information is saved in the database. A success response (registration successful message) is sent back to the user device.

[0345] Step 2:

[0346] Providing training plans

[0347] User device:

[0348] The user clicks the training plan request button, and the request (user ID and desired content data) is sent to the server in JSON format.

[0349] server:

[0350] The server receives the request and retrieves the user's profile information from the database. Based on the retrieved information, it asks the generation AI to generate a training plan. The generation AI generates the training plan and returns the data to the server. The server then returns the generated training plan data to the user's device.

[0351] User device:

[0352] The user displays the received training plan on the screen and performs exercise based on the plan.

[0353] Step 3:

[0354] Providing nutritional advice

[0355] User device:

[0356] The user clicks the request button for nutrition advice, and the request (user ID and desired content data) is sent to the server in JSON format.

[0357] server:

[0358] The server receives the request and retrieves the user's nutrition-related information from the database. Based on the retrieved information, it asks the generation AI to generate nutrition advice. The generation AI generates the nutrition advice and returns the data to the server. The server then returns the generated nutrition advice data to the user's device.

[0359] User device:

[0360] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[0361] Step 4:

[0362] Security Assistance

[0363] User device (smart glasses):

[0364] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings, and the collected data (environmental information, location information, etc.) is sent to the server in JSON format.

[0365] server:

[0366] The server receives data sent from the sensors and analyzes the situation. It processes the data (normalizes location information, analyzes audio data, analyzes image data, etc.) and passes the analysis results to the generation AI. The generation AI generates defensive measures according to the situation and returns the data to the server. The server then returns the generated defensive measures data to the user device.

[0367] User device:

[0368] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[0369] Step 5:

[0370] Progress management and feedback

[0371] User device:

[0372] Users input their exercise and diet progress information into the app. The input data (exercise status, diet details, etc.) is sent to the server in JSON format.

[0373] server:

[0374] The server stores the progress data in a database and requests the generation AI to generate feedback based on the progress information. The generation AI generates the feedback and returns the data to the server. The server then sends the generated feedback data back to the user's device.

[0375] User device:

[0376] Users can check the feedback they receive on screen and use it to guide their next actions.

[0377] 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.

[0378] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[0379] User Registration

[0380] 1. User Device

[0381] The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[0382] When you click the register button, the form data is sent to the server in JSON format.

[0383] 2. Server

[0384] The server receives the request and performs validation of the information entered, such as checking the format of the email address and the strength of the password.

[0385] If validation is successful, save the user information to the database.

[0386] 3. Server

[0387] A success response is sent to the user terminal, and the user terminal displays a message indicating successful registration.

[0388] Providing training plans

[0389] 1. User Device

[0390] The user clicks the request a training plan button within the app.

[0391] The request is sent to the server in JSON format.

[0392] 2. Server

[0393] The server receives the request and retrieves the profile information of the user from the database.

[0394] Based on the acquired user information, the generative AI model is asked to generate a training plan, which takes into account the user's age, gender, exercise experience, etc. to generate a customized plan.

[0395] 3. Server

[0396] The training plan received from the generation AI is sent back to the user's device.

[0397] 4. User Device

[0398] The received training plan information is displayed on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[0399] Providing nutritional advice

[0400] 1. User Device

[0401] The user clicks the "Request Nutritional Advice" button.

[0402] The request is sent to the server in JSON format.

[0403] 2. Server

[0404] The server receives the request and retrieves the nutrition-related information for the user from the database.

[0405] Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice, taking into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[0406] 3. Server

[0407] The nutritional advice received from the generating AI is sent back to the user's device.

[0408] 4. User Device

[0409] The received nutrition advice information is displayed on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[0410] Progress management and feedback

[0411] 1. User Device

[0412] Users enter their exercise and diet progress information into the app.

[0413] 2. Server

[0414] Receives progress data and stores it in a database.

[0415] 3. Server

[0416] Based on the progress data, the generative AI model is asked to generate feedback, which evaluates the user's progress and provides suggestions for improvement and next steps.

[0417] 4. Server

[0418] The feedback received from the generation AI is sent back to the user's device.

[0419] 5. User Device

[0420] The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[0421] Incorporating an emotion engine

[0422] 1. User Device

[0423] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[0424] 2. Server

[0425] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[0426] 3. Server

[0427] Based on the analysis results from the emotion engine, the generative AI model can further personalize training plans and nutrition advice, for example suggesting relaxation exercises if the user is under stress.

[0428] 4. Server

[0429] The generated training plan and nutrition advice are sent to the user's terminal, allowing the user to obtain appropriate information at the appropriate time.

[0430] Specific examples

[0431] Example 1: Retrieving a training plan

[0432] 1. User Device

[0433] User A clicks the button to request a training plan.

[0434] The request is sent to the server in JSON format.

[0435] 2. Server

[0436] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[0437] The training plan received from the generation AI is sent back to the user's device.

[0438] 3. User Device

[0439] User A checks the received training plan on the screen and exercises based on the plan.

[0440] Example 2: Getting nutrition advice

[0441] 1. User Device

[0442] User B clicks the button to request nutrition advice.

[0443] The request is sent to the server in JSON format.

[0444] 2. Server

[0445] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[0446] The nutritional advice received from the generating AI is sent back to the user's device.

[0447] 3. User Device

[0448] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[0449] Example 3: Using the Emotion Engine

[0450] 1. User Device

[0451] User C inputs his emotional state.

[0452] The data is sent to the server through the emotion engine.

[0453] 2. Server

[0454] The emotion engine analyzes the emotion data and provides the results to the generative AI.

[0455] Generative AI takes emotional state into account to generate training plans and nutritional advice.

[0456] 3. User Device

[0457] User C reviews the personalized training plan and nutrition advice he or she receives on the screen and acts accordingly.

[0458] As described above, by incorporating an emotion engine, this system provides more personalized training plans and nutritional advice that reflect the user's emotional state, enabling users to effectively manage their fitness and nutritional needs while taking their emotional state into account.

[0459] The processing flow will be explained below.

[0460] Providing training plans incorporating an emotion engine (example)

[0461] Step 1:

[0462] User device: The user clicks the training plan request button within the app.

[0463] Step 2:

[0464] User terminal: The request is sent to the server in JSON format.

[0465] Step 3:

[0466] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[0467] sql

[0468] SELECT FROM users WHERE user_id = 'user_a_id';

[0469] Step 4:

[0470] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[0471] Step 5:

[0472] Server: Temporarily stores the training plan received from the generation AI.

[0473] Step 6:

[0474] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[0475] json

[0476] {

[0477] "action": "get_emotion",

[0478] "user_id": "user_a_id"

[0479] }

[0480] Step 7:

[0481] Server: Receives the user's emotional state from the emotion engine.

[0482] Step 8:

[0483] Emotion Engine: Analyzes emotional data and makes appropriate adjustments to the training plan if the user is feeling stressed.

[0484] Step 9:

[0485] Server: Sends the adjusted training plan to the user device.

[0486] Step 10:

[0487] User terminal: Displays the received training plan information on the screen.

[0488] Providing nutrition advice using an emotion engine (example)

[0489] Step 1:

[0490] User terminal: The user clicks on the "Request nutrition advice" button.

[0491] Step 2:

[0492] User terminal: The request is sent to the server in JSON format.

[0493] Step 3:

[0494] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[0495] sql

[0496] SELECT FROM users WHERE user_id = 'user_b_id';

[0497] Step 4:

[0498] Server: Based on the acquired user information and request, the generative AI model is asked to generate nutrition advice. The generative AI model takes into account the user's health status and goals.

[0499] Step 5:

[0500] Server: Temporarily stores nutrition advice received from the generation AI.

[0501] Step 6:

[0502] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[0503] json

[0504] {

[0505] "action": "get_emotion",

[0506] "user_id": "user_b_id"

[0507] }

[0508] Step 7:

[0509] Server: Receives the user's emotional state from the emotion engine.

[0510] Step 8:

[0511] Emotion engine: Analyzes emotional data and makes appropriate adjustments to nutrition advice if the user is feeling stressed.

[0512] Step 9:

[0513] Server: Sends tailored nutrition advice to the user terminal.

[0514] Step 10:

[0515] User terminal: Displays the received nutrition advice information on the screen.

[0516] Progress management and feedback using emotion engine (example)

[0517] Step 1:

[0518] User device: The user enters exercise and diet progress information into the app.

[0519] Step 2:

[0520] Server: Receives progress data and stores it in a database.

[0521] sql

[0522] INSERT INTO progress (user_id, exercise_data, nutrition_data) VALUES ('user_c_id', 'exercise_data', 'nutrition_data');

[0523] Step 3:

[0524] Server: Requests the generative AI model to generate feedback based on the progress data. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[0525] Step 4:

[0526] Server: Temporarily stores feedback received from the generation AI.

[0527] Step 5:

[0528] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[0529] json

[0530] {

[0531] "action": "get_emotion",

[0532] "user_id": "user_c_id"

[0533] }

[0534] Step 6:

[0535] Server: Receives the user's emotional state from the emotion engine.

[0536] Step 7:

[0537] Emotion engine: Analyzes emotional data and provides encouraging and motivational feedback if the user is feeling down.

[0538] Step 8:

[0539] Server: Sends the adjusted feedback to the user device.

[0540] Step 9:

[0541] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[0542] By incorporating an emotion engine, the system can achieve further personalization that takes into account the user's emotional state, providing training plans, nutritional advice, progress management, and feedback.

[0543] Example 2

[0544] 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."

[0545] Conventional training planning and nutrition advice systems provide uniform plans and advice without considering the user's individual emotional state, making it difficult to obtain optimal feedback for the user. It is also difficult to provide prompt, personalized feedback based on the user's progress.

[0546] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generative AI model, means for transmitting the generated training plan to a user terminal, means including an emotion engine for collecting and analyzing the user's emotional state, and means for generating a training plan taking the user's emotional state into consideration using the generative AI model. This makes it possible to provide an optimal training plan and nutritional advice taking the user's emotional state and individual progress information into consideration.

[0547] "Means for accepting user requests" refers to an interface that allows users to make requests to the system for training plans, nutritional advice, etc.

[0548] "Means for obtaining user information from a database" refers to a function for searching and extracting data about users stored in a database within the system.

[0549] "Means for automatically generating training plans using generative AI models" refers to a process that uses artificial intelligence to automatically create personalized training plans based on a user's profile information.

[0550] The "means for transmitting the generated training plan to the user terminal" refers to a function for transmitting the generated training plan to the user's device via a network.

[0551] "Means including an emotion engine that collects and analyzes the user's emotional state" refers to a system that collects and analyzes user's emotional data using text, voice, images, etc.

[0552] "Means for generating a training plan that takes into account a user's emotional state using a generative AI model" refers to a process that uses artificial intelligence to create an individualized training plan that reflects a user's emotional state.

[0553] "Means for automatically generating nutritional advice" refers to a system that uses generative AI to automatically create nutritional advice, taking into account the user's health condition and goals.

[0554] "Means of receiving user progress information and automatically generating feedback using a generation AI" refers to the function of receiving exercise and diet progress data entered by the user and having the generation AI create personalized feedback based on that data.

[0555] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[0556] System configuration

[0557] This system consists of the following main components:

[0558] User terminal

[0559] server

[0560] Database

[0561] Generative AI Models

[0562] Emotion Engine

[0563] User Registration

[0564] 1. User Device

[0565] The user installs the application on their smartphone or computer, opens the new registration screen, enters the required information such as name, email address, and password, and clicks the register button. The entered information is sent to the server in JSON format.

[0566] 2. Server

[0567] The server receives a request from the user's device. It checks the format of the email address and the strength of the password, and if validation is successful, it saves the user information in the database. It then sends a response indicating successful registration to the user's device.

[0568] 3. User Device

[0569] A registration success message will be displayed on the user's device.

[0570] Providing training plans

[0571] 1. User Device

[0572] The user clicks the Request a Training Plan button in the application, and the request is sent to the server in JSON format.

[0573] 2. Server

[0574] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[0575] 3. Server

[0576] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[0577] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[0578] 4. Server

[0579] The training plan received from the generation AI is sent back to the user's device.

[0580] 5. User Device

[0581] The user terminal displays the received training plan, which may include details such as "chest training" on Monday and "cardio" on Tuesday.

[0582] Providing nutritional advice

[0583] 1. User Device

[0584] The user clicks the "Request Nutrition Advice" button, and the request is sent to the server in JSON format.

[0585] 2. Server

[0586] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[0587] 3. Server

[0588] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[0589] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[0590] 4. Server

[0591] The nutritional advice received from the generating AI is sent back to the user's device.

[0592] 5. User Device

[0593] The received nutrition advice is displayed on the user's device. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[0594] Progress management and feedback

[0595] 1. User Device

[0596] Users enter exercise and diet progress information within the app.

[0597] 2. Server

[0598] Receives progress data and stores it in a database.

[0599] 3. Server

[0600] Based on the progress data, the generative AI model is asked to generate feedback, for example, a prompt sentence like this:

[0601] "Consider the user's recent exercise and food logs and suggest next steps."

[0602] 4. Server

[0603] The feedback received from the generation AI is sent back to the user's device.

[0604] 5. User Device

[0605] The received feedback is displayed on the user's device, and the user can make adjustments for further improvement.

[0606] Incorporating an emotion engine

[0607] 1. User Device

[0608] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[0609] 2. Server

[0610] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[0611] 3. Server

[0612] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[0613] "The user is under stress, please suggest some relaxation exercises."

[0614] 4. Server

[0615] The generated training plan and nutrition advice are sent to the user terminal.

[0616] 5. User Device

[0617] Users can obtain appropriate information at the right time on their devices and take action.

[0618] This concludes the concrete implementation of a sports science knowledge provision system using a generative AI model, which enables users to receive optimal fitness and nutritional management that takes into account their individual emotional state and progress information.

[0619] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] Enter and submit user registration information

[0622] Specific actions

[0623] Users install the application on their smartphone or computer and open the new registration screen.

[0624] Fill in the form with the required information, such as your name, email address, and password.

[0625] Click the Register button.

[0626] input

[0627] Information entered by the user, such as name, email address, and password.

[0628] output

[0629] Registration information sent to the server in JSON format.

[0630] Step 2:

[0631] Validation of user information by the server

[0632] Specific actions

[0633] The server receives the user information sent from the terminal.

[0634] Check the format of the email address (e.g., check the format such as example@example.com) and the strength of the password (e.g., check that it is at least 8 characters long, including uppercase and lowercase letters, numbers, and special characters).

[0635] input

[0636] User information sent from the device in JSON format.

[0637] output

[0638] The result of validation: success or failure.

[0639] Step 3:

[0640] Server saves user information and sends response

[0641] Specific actions

[0642] If validation is successful, the server saves the user information in the database.

[0643] A response indicating that the user registration was successful is generated and sent to the terminal.

[0644] input

[0645] User information that has passed validation.

[0646] output

[0647] A response indicating successful registration.

[0648] Step 4:

[0649] Displaying a successful registration message for users

[0650] Specific actions

[0651] The user terminal receives the success response from the server and displays a registration success message on the screen.

[0652] input

[0653] A successful registration response received from the server.

[0654] output

[0655] A successful registration message will be displayed on the device screen.

[0656] Step 5:

[0657] Submit a Training Plan Request

[0658] Specific actions

[0659] The user clicks the request training plan button within the application.

[0660] The request is sent to the server in JSON format.

[0661] input

[0662] User training plan request.

[0663] output

[0664] The request data sent to the server in JSON format.

[0665] Step 6:

[0666] Server retrieval of user profile

[0667] Specific actions

[0668] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[0669] input

[0670] Training plan request received by the server.

[0671] User profile information in the database.

[0672] output

[0673] The user profile information retrieved.

[0674] Step 7:

[0675] Request to generate a training plan

[0676] Specific actions

[0677] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[0678] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[0679] input

[0680] The retrieved user profile information.

[0681] The generated prompt statement.

[0682] output

[0683] A prompt is used to request a generative AI model to generate a training plan.

[0684] Step 8:

[0685] Return and view your training plan

[0686] Specific actions

[0687] The server returns the training plan received from the generation AI to the user's device.

[0688] The user device displays the received training plan on its screen, which may include details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[0689] input

[0690] The training plan received from the generative AI.

[0691] output

[0692] Training plan displayed on device.

[0693] Step 9:

[0694] Submit a Nutrition Advice Request

[0695] Specific actions

[0696] The user clicks the "Request Nutritional Advice" button.

[0697] The request is sent to the server in JSON format.

[0698] input

[0699] User nutrition advice requests.

[0700] output

[0701] The request data sent to the server in JSON format.

[0702] Step 10:

[0703] Obtaining nutritional information

[0704] Specific actions

[0705] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[0706] input

[0707] A nutrition advice request received by the server.

[0708] Nutrition-related information in the database.

[0709] output

[0710] Nutrition-related information obtained.

[0711] Step 11:

[0712] Request for nutrition advice generation

[0713] Specific actions

[0714] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[0715] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[0716] input

[0717] Nutrition-related information obtained.

[0718] The generated prompt statement.

[0719] output

[0720] A prompt is used to request a generative AI model to generate nutrition advice.

[0721] Step 12:

[0722] Return and display of nutrition advice

[0723] Specific actions

[0724] The server sends the nutrition advice received from the generating AI back to the user's device.

[0725] The user device displays the received nutrition advice on its screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[0726] input

[0727] Nutritional advice received from generative AI.

[0728] output

[0729] Nutrition advice displayed on your device.

[0730] Step 13:

[0731] Enter and submit progress information

[0732] Specific actions

[0733] Users enter exercise and diet progress information within the app.

[0734] Progress information is sent to the server in JSON format.

[0735] input

[0736] User-entered progress information.

[0737] output

[0738] Progress information sent to the server in JSON format.

[0739] Step 14:

[0740] Saving progress information

[0741] Specific actions

[0742] The server receives the progress data and stores it in a database.

[0743] input

[0744] The progress information sent.

[0745] output

[0746] Progress information stored in a database.

[0747] Step 15:

[0748] Request for feedback generation

[0749] Specific actions

[0750] The server then asks the generative AI model to generate feedback based on the progress data. For example, it generates a prompt like this:

[0751] "Consider the user's recent exercise and food logs and suggest next steps."

[0752] input

[0753] Saved progress information.

[0754] The generated prompt statement.

[0755] output

[0756] Request a generative AI model with a prompt to generate feedback.

[0757] Step 16:

[0758] Sending and viewing feedback

[0759] Specific actions

[0760] The server sends the feedback received from the generation AI back to the user's device.

[0761] The user device displays the received feedback on the screen, and the user can make adjustments for further improvement.

[0762] input

[0763] Feedback received from the generative AI.

[0764] output

[0765] Feedback displayed on the device.

[0766] Step 17:

[0767] Input and recording of emotional states

[0768] Specific actions

[0769] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[0770] input

[0771] A user-entered or recorded emotional state.

[0772] output

[0773] Emotion data sent to the server.

[0774] Step 18:

[0775] Emotional Data Analysis

[0776] Specific actions

[0777] A server-based emotion engine analyzes the collected emotion data to identify the user's emotional state.

[0778] input

[0779] The emotion data sent.

[0780] output

[0781] Results of analyzed emotional states.

[0782] Step 19:

[0783] Request a personalized plan

[0784] Specific actions

[0785] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[0786] "The user is under stress, please suggest some relaxation exercises."

[0787] input

[0788] Results of analyzed emotional states.

[0789] The generated prompt statement.

[0790] output

[0791] Request a generative AI model with a prompt to generate a personalized plan.

[0792] Step 20:

[0793] Return and view your personalized plan

[0794] Specific actions

[0795] The generated training plan and nutrition advice are sent from the server to the user terminal.

[0796] Users can obtain appropriate information at the right time on their devices and take action.

[0797] input

[0798] A personalized plan received from a generative AI model.

[0799] output

[0800] A personalized plan displayed on your device.

[0801] (Application example 2)

[0802] 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."

[0803] Modern autonomous vehicles face a lack of means to manage the health and mental health of their users while driving. As autonomous vehicles become more widespread, there is a demand for ways to make effective use of their driving time. However, current systems have difficulty providing personalized training plans and nutritional advice that reflect the user's individual needs and emotional state. This means that users are unable to make full use of their time while driving, making it difficult to manage stress and effectively manage their health.

[0804] The specific processing by the specific 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 means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the training plan based on the analyzed emotional state, and means for displaying the plan on a head-mounted display. This enables users to receive personalized training plans and nutritional advice in real time that are tailored to their individual needs and emotional state, even while in an autonomous vehicle.

[0805] The "means for accepting user requests" is a method for providing an interface for accepting requests sent by users.

[0806] The "means for obtaining user information from a database" is a method for reading stored user profile information from a database.

[0807] "Means for automatically generating training plans using generative AI" refers to a method for automatically generating training plans based on a user's health status and goals using a machine learning model.

[0808] The "means for transmitting the generated training plan to the user terminal" is a method for transferring the generated training plan to the user's device.

[0809] The "means for analyzing a user's emotional state using an emotion engine" is a method for interpreting a user's emotional data using emotion recognition technology to identify the user's current emotional state.

[0810] The "means for adjusting a training plan based on the analyzed emotional state" is a method for using the results from the emotion engine to adapt a training plan to a user.

[0811] The "means for displaying a plan on a head-mounted display" is a method for displaying the generated training plan and nutrition advice on a head-mounted display.

[0812] "Means for automatically generating nutritional advice using generative AI" refers to a method that uses machine learning models to automatically generate nutritional advice based on a user's goals and health status.

[0813] "Means of receiving user progress information and automatically generating feedback using AI" refers to a method of receiving progress data provided by the user and generating feedback using a machine learning model based on that data.

[0814] The present invention is a method for providing users with personalized training plans and nutritional advice within an autonomous vehicle using a system that combines a generative AI model and an emotion engine. This system is realized by the following specific components and procedures.

[0815] 1. A means of accepting user requests

[0816] The server accepts requests sent by the user through the head-mounted display, including requests for training plans and nutritional advice.

[0817] 2. A way to retrieve user information from the database

[0818] Based on the received request, the server retrieves user profile information from a database, including the user's age, gender, exercise experience, and health status.

[0819] 3. A means to automatically generate training plans using generative AI

[0820] The server automatically generates a training plan based on the acquired user information using a generative AI model, which uses machine learning algorithms to create an optimal exercise plan for the user.

[0821] 4. Means for sending the generated training plan to the user device

[0822] The server sends the generated training plan to the head-mounted display so that the user can visually check it.

[0823] 5. A method for analyzing the user's emotional state using an emotion engine

[0824] The server collects emotion data provided by the user through the head-mounted display and analyzes it with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state.

[0825] 6. A way to adjust your training plan based on your analyzed emotional state

[0826] The server then uses the emotional state analysis results from the emotion engine to adjust training plans and nutrition advice accordingly, for example adding relaxation exercises if the user is feeling stressed.

[0827] 7. A method for displaying plans on a head-mounted display

[0828] The server then displays tailored training plans and nutrition advice on the head-mounted display, allowing users to receive appropriate feedback in real time.

[0829] Hardware and software used

[0830] Hardware: Head-mounted display, server, database

[0831] Software: Flask, generative AI libraries, emotion engine libraries, database modules

[0832] Specific examples

[0833] 1. While wearing the HMD, the user clicks the "Request a training plan" button.

[0834] Example prompt: "User requests a new training plan. User ID is 12345."

[0835] 2. While wearing the HMD, the user clicks the "Request nutrition advice" button.

[0836] Example prompt: "User requests new nutrition advice. User ID is 12345."

[0837] 3. Input emotional state while the user is wearing the HMD

[0838] Sample prompt: "We have collected the user's emotional data and determined that they are feeling stressed. The emotion engine will generate stress relief advice."

[0839] The system will monitor the user's health and mental state even while in an autonomous vehicle, and provide individually optimized training plans and nutritional advice, thereby improving the user's quality of life.

[0840] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0841] Step 1:

[0842] The server accepts user requests through the head-mounted display, typically requests for training plans or nutrition advice. The input is the request data, and the output is a confirmation that the request was received.

[0843] Step 2:

[0844] The server retrieves user information from a database based on the received request. It uses a database query to collect profile information such as the user's age, gender, exercise experience, and health status. The input is the user ID, and the output is the retrieved user information.

[0845] Step 3:

[0846] The server automatically generates a training plan using a generative AI model based on the acquired user information. The generative AI model runs a trained machine learning algorithm to create a training plan optimized for the user. This generates the contents of the plan. The input is user information, and the output is the generated training plan.

[0847] Step 4:

[0848] The server sends the generated training plan to the user's head-mounted display and displays it, allowing the user to check the training plan in real time. The input is the training plan, and the output is the displayed training plan.

[0849] Step 5:

[0850] The user inputs emotional data through the head-mounted display. For example, data such as facial expressions and heart rate are collected using sensors and cameras built into the head-mounted display. The input is emotional data, and the output is data sent to the server.

[0851] Step 6:

[0852] The server analyzes the collected emotional data with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state. The input is the collected emotional data, and the output is the analyzed emotional state.

[0853] Step 7:

[0854] The server then adjusts the training plan and nutrition advice appropriately based on the emotional state obtained from the emotion engine. For example, if the user is feeling stressed, it suggests relaxation exercises to address that stress. The input is the analyzed emotional state, and the output is the adjusted training plan and nutrition advice.

[0855] Step 8:

[0856] The server sends the adjusted training plan and nutrition advice to the head-mounted display for the user to review in real time. The input is the adjusted plan and advice, and the output is the displayed content.

[0857] Through these steps, users can receive individually optimized training plans and nutritional advice in real time while in an autonomous vehicle, enabling them to efficiently manage their health.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] [Second embodiment]

[0862] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0863] 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.

[0864] 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).

[0865] 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.

[0866] 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.

[0867] 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).

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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."

[0874] This invention is a method for utilizing generative AI models to realize a system that provides sports science knowledge. Below, we will explain the important components of the system and their specific operations.

[0875] User Registration

[0876] 1. User Device:

[0877] The user installs the app and enters the required information on the new registration screen, including their name, email address, and password.

[0878] When the registration button is clicked, the form data is sent to the server in JSON format.

[0879] 2. Server:

[0880] The server receives the request and performs validation of the information entered, for example checking that the email address is formatted correctly or that the password is strong.

[0881] If validation is successful, the user information is saved in the database, a success response is sent back to the user's device, and a message indicating successful registration is displayed to the user.

[0882] Providing training plans

[0883] 1. User Device:

[0884] The user clicks the request a training plan button within the app.

[0885] The request is sent to the server in JSON format.

[0886] 2. Server:

[0887] The server receives the request and retrieves the profile information of the user from the database.

[0888] Based on the acquired user information, a generative AI model (e.g., ChatGPT) is asked to generate a training plan.

[0889] The generation AI generates a customized training plan, which the server then sends back to the user's device.

[0890] 3. User Device:

[0891] The user terminal displays the received training plan information on the screen, providing details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[0892] Providing nutritional advice

[0893] 1. User Device:

[0894] The user clicks the "Request Nutritional Advice" button.

[0895] The request is sent to the server in JSON format.

[0896] 2. Server:

[0897] The server receives the request and retrieves the nutrition-related information for the user from the database.

[0898] Based on the acquired user information and request content, the generative AI model is asked to generate nutritional advice.

[0899] The generation AI generates customized nutrition advice, and the server sends the advice back to the user's device.

[0900] 3. User Device:

[0901] The user terminal displays the received nutrition advice information on the screen and provides specific advice such as "eat a high-protein meal for breakfast."

[0902] Progress management and feedback

[0903] 1. User Device:

[0904] Users enter their exercise and diet progress information into the app.

[0905] 2. Server:

[0906] The server stores the progress data in a database and generates feedback using a generative AI model.

[0907] The generated feedback is sent to the user's device, providing the user with progress-based evaluations and suggestions for improvement.

[0908] Specific examples

[0909] Example 1: Retrieving a training plan

[0910] 1. User Device:

[0911] User A clicks the button to request a training plan.

[0912] The request is sent to the server in JSON format.

[0913] 2. Server:

[0914] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[0915] The training plan received from the generation AI is sent back to the user's device.

[0916] 3. User Device:

[0917] User A checks the received training plan on the screen and exercises based on the plan.

[0918] Example 2: Getting nutrition advice

[0919] 1. User Device:

[0920] User B clicks the button to request nutrition advice.

[0921] The request is sent to the server in JSON format.

[0922] 2. Server:

[0923] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[0924] The nutritional advice received from the generating AI is sent back to the user's device.

[0925] 3. User Device:

[0926] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[0927] As described above, this system uses generative AI to provide personalized training plans and nutritional advice based on user requests, thereby realizing efficient and high-quality services for a large number of users.

[0928] The processing flow will be explained below.

[0929] Handling user registration

[0930] Step 1:

[0931] User device: The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[0932] Step 2:

[0933] User device: When the registration button is clicked, the form data is sent to the server in JSON format.

[0934] Step 3:

[0935] Server: Receives the request and validates the entered information, specifically checking the format of the email address and the strength of the password.

[0936] Step 4:

[0937] Server: If validation is successful, save the user information to the database.

[0938] Step 5:

[0939] Server: Sends a success response to the user terminal, and the user terminal displays a message indicating successful registration.

[0940] Providing training plans

[0941] Step 1:

[0942] User device: The user clicks the training plan request button within the app.

[0943] Step 2:

[0944] User terminal: The request is sent to the server in JSON format.

[0945] Step 3:

[0946] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[0947] Step 4:

[0948] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[0949] Step 5:

[0950] Server: Returns the training plan received from the generation AI to the user device.

[0951] Step 6:

[0952] User device: Displays the received training plan information on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[0953] Providing nutritional advice

[0954] Step 1:

[0955] User terminal: The user clicks on the "Request nutrition advice" button.

[0956] Step 2:

[0957] User terminal: The request is sent to the server in JSON format.

[0958] Step 3:

[0959] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[0960] Step 4:

[0961] Server: Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice. The generative AI model takes into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[0962] Step 5:

[0963] Server: Returns the nutrition advice received from the generation AI to the user's device.

[0964] Step 6:

[0965] User device: The received nutrition advice information is displayed on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[0966] Progress management and feedback

[0967] Step 1:

[0968] User device: The user enters exercise and diet progress information into the app.

[0969] Step 2:

[0970] Server: Receives progress data and stores it in a database.

[0971] Step 3:

[0972] Server: Based on the progress data, the server requests the generative AI model to generate feedback. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[0973] Step 4:

[0974] Server: Returns the feedback received from the generation AI to the user device.

[0975] Step 5:

[0976] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[0977] Through the above processing flow, the system can provide users with personalized training plans and nutritional advice, and can also provide progress management and feedback functions, realizing an efficient and high-quality service.

[0978] Example 1

[0979] 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."

[0980] Traditional methods have not made it easy for users to quickly and efficiently obtain personalized training plans and nutritional advice. It has also been difficult to monitor users' progress in real time and provide appropriate feedback. Therefore, there has been a need for a system that can help users achieve their health and fitness goals.

[0981] 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.

[0982] In this invention, the server includes: means for transmitting form data in JSON format to the server when a user enters necessary information on a new registration screen and clicks the registration button; means for the server to receive the request, validate the entered information, and, if successful, store the user information in a database and return a success response to the user terminal; means for transmitting a request in JSON format to the server when the user terminal clicks a training plan request button; means for the server to receive the request, retrieve the user's profile information from the database, and request the generation AI model to generate a training plan; and means for returning the generated training plan to the user terminal and displaying the training plan received by the user terminal on the screen. This allows users to quickly and efficiently obtain personalized training plans and nutritional advice, and also enables progress management in real time.

[0983] A "user terminal" is an electronic device used by a user to input information and communicate with the system.

[0984] A "server" is a centralized computer system that receives requests from user devices, validates information, and interacts with databases.

[0985] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in an organized text format.

[0986] A "database" is a system that stores information in a structured format and allows it to be searched and updated later.

[0987] A "generative AI model" is an algorithm or software that uses artificial intelligence technology to generate information, such as a model that automatically generates training plans or nutritional advice.

[0988] "Validation" is the process of checking whether the entered information is in the correct format or meets certain conditions.

[0989] "Feedback" is information, including evaluations and suggestions for improvement, that the system provides based on the user's progress.

[0990] "Profile information" is information about the attributes and status of each user, including, for example, age, height, weight, and fitness level.

[0991] A "training plan" is an exercise program created by a generative AI model to achieve a user's fitness goals.

[0992] "Nutrition advice" refers to advice and suggestions about a user's diet, which are customized and generated by a generative AI model.

[0993] The present invention is a system that uses generative AI models to provide users with sports science-based training plans and nutrition advice. Specific embodiments of the present invention are described in detail below.

[0994] User Registration

[0995] First, in order for a user to use the system, they must register using their device. The user installs the app and enters information such as their name, email address, and password on the registration screen. Once the user has completed the entry and clicked the registration button, the entered information is sent to the server in JSON format.

[0996] The server receives the request sent from the user terminal and validates the input information. For example, it checks whether the email address format is correct and whether the password is strong. If validation is successful, the user information is saved in the database and a response indicating successful registration is sent back to the user terminal. The user terminal receives this response and displays a message indicating successful registration on its screen.

[0997] Providing training plans

[0998] To request a training plan, a user clicks on the training plan request button in the app. This request is sent to the server in JSON format. After receiving the request, the server retrieves the user's profile information from the database.

[0999] Next, a prompt is generated and sent to the generative AI model (e.g., ChatGPT). The prompt includes information such as the user's age, height, weight, and fitness level. Based on the generated prompt, the generative AI model generates a customized training plan. The server receives the generated training plan and sends it to the user's device. The user's device receives this information and displays details such as "chest training" on Mondays and "aerobic exercise" on Tuesdays.

[1000] Providing nutritional advice

[1001] When a user requests nutrition advice, they click the "Request Nutrition Advice" button in the app. The request is sent to the server in JSON format. After receiving the request, the server retrieves the user's nutrition-related information from the database.

[1002] Based on the acquired nutritional information, the server sends prompts to the generative AI model, asking it to generate customized nutritional advice. The generated nutritional advice is sent to the user's device via the server, and the user's device displays this information on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[1003] Progress management and feedback

[1004] Users enter their exercise and diet progress information into the app. The server receives and stores this progress information and requests the generative AI model to generate feedback. The generated feedback is sent from the server to the user's device, and the user is given an evaluation and suggestions for improvement based on their progress.

[1005] Examples of concrete examples and prompts

[1006] Example 1: Obtaining a training plan

[1007] When User A clicks the button to request a training plan, the request is sent in JSON format to the server. The server obtains the user's profile information and asks the generation AI to generate a training plan. The generated training plan is sent back to the user's device, and User A checks the received plan and performs the exercise.

[1008] Example 2: Getting nutrition advice

[1009] When User B clicks the button to request nutrition advice, the request is sent in JSON format to the server. The server obtains the user's nutrition-related information and asks the AI ​​to generate advice. The generated nutrition advice is sent back to the user's device, where User B can review the advice and plan their meals.

[1010] Prompt Sentence Examples

[1011] "Generate a training plan. Your profile information is as follows: age 30, height 175cm, weight 70kg, and fitness level intermediate."

[1012] "Generate nutrition advice. User's nutritional information is: vegan, goal weight 65kg, current weight 70kg."

[1013] As described above, the present invention uses generative AI models to provide users with personalized training plans and nutritional advice, and provides progress management and feedback, thereby achieving efficient and high-quality services.

[1014] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1015] Step 1: Enter user registration information

[1016] User device:

[1017] Input: User information such as name, email address, and password.

[1018] How it works: The user installs the app and enters the required information on the new registration screen.

[1019] Output: When the registration button is clicked, the entered information is sent to the server as JSON format data.

[1020] Step 2: Information validation and storage

[1021] server:

[1022] Input: JSON format user information sent from the user device.

[1023] What it does: The server receives the request, checks that the email address is valid and the password is strong, and if validation is successful, stores the user information in the database.

[1024] Output: Generates a response indicating successful registration and sends it to the user's device. If any information is inaccurate, generates and returns an error message.

[1025] Step 3: Viewing registration results

[1026] User device:

[1027] Input: Registration success or error message sent by the server.

[1028] Operation: The user terminal displays the received message on the screen.

[1029] Output: Registration success message or error message.

[1030] Step 4: Submit a training plan request

[1031] User device:

[1032] Enter: Click on Training Plan Request.

[1033] What happens: A user clicks the in-app training plan request button.

[1034] Output: The request is sent to the server as JSON data.

[1035] Step 5: Obtain user information

[1036] server:

[1037] Input: Training plan request sent from user device.

[1038] How it works: The server receives the request and retrieves the user's profile information (age, height, weight, fitness level, etc.) from the database.

[1039] Output: The retrieved profile information.

[1040] Step 6: Prompt generation and AI requests

[1041] server:

[1042] Input: User profile information.

[1043] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate a training plan.

[1044] Output: The generated training plan.

[1045] Step 7: Submit your training plan

[1046] server:

[1047] Input: The training plan received from the generative AI model.

[1048] Operation: The server transmits the generated training plan to the user terminal.

[1049] Output: The training plan sent to the user device.

[1050] Step 8: View your training plan

[1051] User device:

[1052] Input: The training plan sent by the server.

[1053] How it works: The user device displays the received training plan on the screen, providing details such as "chest workout" on Monday and "cardio" on Tuesday.

[1054] Output: Training plan displayed on the screen.

[1055] Step 9: Submit a nutrition advice request

[1056] User device:

[1057] Enter: Click on Request Nutritional Advice.

[1058] What happens: A user clicks the "Request Nutrition Advice" button in the app.

[1059] Output: The request is sent to the server as JSON data.

[1060] Step 10: Obtaining user nutrition information

[1061] server:

[1062] Input: A nutrition advice request sent from a user device.

[1063] How it works: The server receives the request and retrieves the user's nutrition-related information (such as dietary preferences and allergy information) from the database.

[1064] Output: Retrieved nutrition-related information.

[1065] Step 11: Prompt generation and AI request (nutritional advice)

[1066] server:

[1067] Input: User nutrition related information.

[1068] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate nutritional advice.

[1069] Output: The generated nutrition advice.

[1070] Step 12: Send nutrition advice

[1071] server:

[1072] Input: Nutrition advice received from a generative AI model.

[1073] Operation: The server transmits the generated nutrition advice to the user terminal.

[1074] Output: Nutrition advice sent to the user device.

[1075] Step 13: View nutrition advice

[1076] User device:

[1077] Input: Nutrition advice sent from the server.

[1078] Operation: The user device displays the received nutrition advice on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[1079] Output: Nutrition advice displayed on the screen.

[1080] Step 14: Enter progress information

[1081] User device:

[1082] Input: Exercise and diet progress information.

[1083] How it works: Users enter exercise and diet progress information into the app.

[1084] Output: The entered progress information is sent to the server in JSON format.

[1085] Step 15: Save progress information and request AI

[1086] server:

[1087] Input: Progress information sent from the user's device.

[1088] How it works: The server stores progress information in a database and asks the generative AI model to generate feedback based on the stored progress data.

[1089] Output: The generated feedback.

[1090] Step 16: Send feedback

[1091] server:

[1092] Input: Feedback received from the generative AI model.

[1093] Operation: The server sends the generated feedback to the user terminal.

[1094] Output: Feedback sent to the user device.

[1095] Step 17: Viewing feedback

[1096] User device:

[1097] Input: Feedback sent by the server.

[1098] How it works: The user device displays the received feedback on its screen, providing the user with a rating and suggestions for improvement based on their progress.

[1099] Output: Feedback displayed on the screen.

[1100] (Application example 1)

[1101] 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."

[1102] In today's advanced information society, various security threats exist on a daily basis, requiring rapid and appropriate responses to these threats. At the same time, there is a growing demand for personalized training plans and nutritional advice that utilize knowledge of sports science. However, there is a lack of mechanisms to efficiently provide these to individual users. Furthermore, it is difficult to utilize wearable devices such as smart glasses to perform real-time situation analysis and present appropriate defensive measures. Given this background, there is a need for a system that can provide personalized training plans and nutritional advice while also effectively providing security support through devices such as smart glasses.

[1103] 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.

[1104] In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the situation based on data acquired from sensors, and means for providing defensive measures according to the situation using the generation AI. This makes it possible to provide the user with a personalized training plan and nutritional advice, while also providing real-time security support through the wearable device.

[1105] "User" refers to an individual or corporation that uses this system, and whose information is registered in the database.

[1106] The "means for accepting a request" is an interface for receiving a request from a user in an input format and transmitting it to a server.

[1107] A "database" is a system for storing user information and related data, and for searching and retrieving them as needed.

[1108] "User information" refers to various data required by the system, such as a user's personal information, profile data, and activity history.

[1109] "Generative AI" is a technology that uses machine learning models trained on large datasets to generate training plans, nutritional advice, and situational defensive strategies based on user requests.

[1110] A "training plan" is an exercise program automatically created by the generation AI based on the user's health condition and goals.

[1111] "Nutrition advice" refers to dietary suggestions provided by the generative AI based on the user's diet and health status.

[1112] A "user terminal" is a device (e.g., a smartphone, smart glasses, head-mounted display, etc.) that a user uses to access the system.

[1113] A "sensor" is a device for detecting environmental information and user activity, and includes a camera, microphone, GPS, etc.

[1114] "Situation analysis" is the process of assessing the current environment and the user's situation based on data obtained from sensors.

[1115] "Defensive measures" are guidelines and countermeasures provided by the generative AI based on situational analysis to ensure the user's safety.

[1116] "Progress information" is data related to training plans and nutrition advice, such as records of exercise and meals a user has completed.

[1117] "Feedback" refers to evaluations and suggestions for improvement provided by the generating AI based on the user's progress information.

[1118] The present invention is a system that utilizes generative AI models to provide users with personalized training plans, nutritional advice, and security support. The specific operation of the system is described below.

[1119] 1. User Registration

[1120] User device:

[1121] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The form data is sent to the server in JSON format.

[1122] server:

[1123] The server receives the request, validates the entered information, and if successful, stores the user information in a database and returns a message to the user terminal indicating successful registration.

[1124] 2. Providing training plans

[1125] User device:

[1126] The user clicks the training plan request button and the request is sent to the server in JSON format.

[1127] server:

[1128] The server receives the request, retrieves the user's profile information from the database, and requests the generation AI to generate a training plan. The generated training plan is then sent back to the user's device.

[1129] User device:

[1130] The user displays the received training plan on the screen and performs exercise based on the plan's contents.

[1131] 3. Providing nutritional advice

[1132] User device:

[1133] The user clicks the request nutrition advice button and the request is sent in JSON format to the server.

[1134] server:

[1135] The server receives the request, retrieves the user's nutrition-related information from the database, and requests the AI ​​to generate advice. The generated nutrition advice is then sent back to the user's device.

[1136] User device:

[1137] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[1138] 4. Security Support

[1139] User device (smart glasses):

[1140] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings and send the data in JSON format to a server.

[1141] server:

[1142] The server receives and analyzes the data sent from the sensors and performs situation analysis. Based on the analysis results, the generative AI provides appropriate defensive measures.

[1143] User device:

[1144] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[1145] 5. Progress Management and Feedback

[1146] User device:

[1147] Users enter their exercise and diet progress information into the app.

[1148] server:

[1149] The server stores the progress data in a database, and the AI ​​generates feedback based on the progress. The generated feedback is sent to the user's device and displayed on the screen.

[1150] Hardware and Software Use

[1151] Hardware:

[1152] Smart glasses (e.g., Google Glass, Microsoft HoloLens)

[1153] Built-in sensors (camera, microphone, GPS)

[1154] software:

[1155] Web server (e.g. Python Flask, Django)

[1156] Database (e.g. MySQL, PostgreSQL)

[1157] Generative AI models (e.g. ChatGPT)

[1158] Specific examples

[1159] Get your training plan

[1160] 1. User Device:

[1161] User A clicks the button to request a training plan, and the request is sent to the server in JSON format.

[1162] 2. Server:

[1163] The server acquires the user's profile information and requests the AI ​​to generate a training plan. The AI ​​then returns the training plan to the user's device.

[1164] 3. User Device:

[1165] User A checks the received training plan on the screen and exercises based on the plan.

[1166] Prompt Sentence Examples

[1167] 1. Training plan generation prompt:

[1168] Current Situation: User A is looking to improve his muscle strength.

[1169] Q: Create a training plan for the week.

[1170] 2. Nutrition advice generation prompts:

[1171] Current Situation: User B is trying to lose weight.

[1172] Q: What is your daily meal plan?

[1173] 3. Situation Analysis Prompt:

[1174] Current situation: Unknown people are approaching you.

[1175] Information: It's 8pm and the location is on a deserted street.

[1176] Question: How can I stay safe?

[1177] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1178] Step 1:

[1179] User Registration

[1180] User device:

[1181] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The input data (name, email address, and password) is sent to the server in JSON format.

[1182] server:

[1183] The server receives the request and validates the input data. If validation is successful, the user information is saved in the database. A success response (registration successful message) is sent back to the user device.

[1184] Step 2:

[1185] Providing training plans

[1186] User device:

[1187] The user clicks the training plan request button, and the request (user ID and desired content data) is sent to the server in JSON format.

[1188] server:

[1189] The server receives the request and retrieves the user's profile information from the database. Based on the retrieved information, it asks the generation AI to generate a training plan. The generation AI generates the training plan and returns the data to the server. The server then returns the generated training plan data to the user's device.

[1190] User device:

[1191] The user displays the received training plan on the screen and performs exercise based on the plan.

[1192] Step 3:

[1193] Providing nutritional advice

[1194] User device:

[1195] The user clicks the request button for nutrition advice, and the request (user ID and desired content data) is sent to the server in JSON format.

[1196] server:

[1197] The server receives the request and retrieves the user's nutrition-related information from the database. Based on the retrieved information, it asks the generation AI to generate nutrition advice. The generation AI generates the nutrition advice and returns the data to the server. The server then returns the generated nutrition advice data to the user's device.

[1198] User device:

[1199] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[1200] Step 4:

[1201] Security Assistance

[1202] User device (smart glasses):

[1203] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings, and the collected data (environmental information, location information, etc.) is sent to the server in JSON format.

[1204] server:

[1205] The server receives data sent from the sensors and analyzes the situation. It processes the data (normalizes location information, analyzes audio data, analyzes image data, etc.) and passes the analysis results to the generation AI. The generation AI generates defensive measures according to the situation and returns the data to the server. The server then returns the generated defensive measures data to the user device.

[1206] User device:

[1207] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[1208] Step 5:

[1209] Progress management and feedback

[1210] User device:

[1211] Users input their exercise and diet progress information into the app. The input data (exercise status, diet details, etc.) is sent to the server in JSON format.

[1212] server:

[1213] The server stores the progress data in a database and requests the generation AI to generate feedback based on the progress information. The generation AI generates the feedback and returns the data to the server. The server then sends the generated feedback data back to the user's device.

[1214] User device:

[1215] Users can check the feedback they receive on screen and use it to guide their next actions.

[1216] 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.

[1217] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[1218] User Registration

[1219] 1. User Device

[1220] The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[1221] When you click the register button, the form data is sent to the server in JSON format.

[1222] 2. Server

[1223] The server receives the request and performs validation of the information entered, such as checking the format of the email address and the strength of the password.

[1224] If validation is successful, save the user information to the database.

[1225] 3. Server

[1226] A success response is sent to the user terminal, and the user terminal displays a message indicating successful registration.

[1227] Providing training plans

[1228] 1. User Device

[1229] The user clicks the request a training plan button within the app.

[1230] The request is sent to the server in JSON format.

[1231] 2. Server

[1232] The server receives the request and retrieves the profile information of the user from the database.

[1233] Based on the acquired user information, the generative AI model is asked to generate a training plan, which takes into account the user's age, gender, exercise experience, etc. to generate a customized plan.

[1234] 3. Server

[1235] The training plan received from the generation AI is sent back to the user's device.

[1236] 4. User Device

[1237] The received training plan information is displayed on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[1238] Providing nutritional advice

[1239] 1. User Device

[1240] The user clicks the "Request Nutritional Advice" button.

[1241] The request is sent to the server in JSON format.

[1242] 2. Server

[1243] The server receives the request and retrieves the nutrition-related information for the user from the database.

[1244] Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice, taking into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[1245] 3. Server

[1246] The nutritional advice received from the generating AI is sent back to the user's device.

[1247] 4. User Device

[1248] The received nutrition advice information is displayed on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[1249] Progress management and feedback

[1250] 1. User Device

[1251] Users enter their exercise and diet progress information into the app.

[1252] 2. Server

[1253] Receives progress data and stores it in a database.

[1254] 3. Server

[1255] Based on the progress data, the generative AI model is asked to generate feedback, which evaluates the user's progress and provides suggestions for improvement and next steps.

[1256] 4. Server

[1257] The feedback received from the generation AI is sent back to the user's device.

[1258] 5. User Device

[1259] The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[1260] Incorporating an emotion engine

[1261] 1. User Device

[1262] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[1263] 2. Server

[1264] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[1265] 3. Server

[1266] Based on the analysis results from the emotion engine, the generative AI model can further personalize training plans and nutrition advice, for example suggesting relaxation exercises if the user is under stress.

[1267] 4. Server

[1268] The generated training plan and nutrition advice are sent to the user's terminal, allowing the user to obtain appropriate information at the appropriate time.

[1269] Specific examples

[1270] Example 1: Retrieving a training plan

[1271] 1. User Device

[1272] User A clicks the button to request a training plan.

[1273] The request is sent to the server in JSON format.

[1274] 2. Server

[1275] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[1276] The training plan received from the generation AI is sent back to the user's device.

[1277] 3. User Device

[1278] User A checks the received training plan on the screen and exercises based on the plan.

[1279] Example 2: Getting nutrition advice

[1280] 1. User Device

[1281] User B clicks the button to request nutrition advice.

[1282] The request is sent to the server in JSON format.

[1283] 2. Server

[1284] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[1285] The nutritional advice received from the generating AI is sent back to the user's device.

[1286] 3. User Device

[1287] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[1288] Example 3: Using the Emotion Engine

[1289] 1. User Device

[1290] User C inputs his emotional state.

[1291] The data is sent to the server through the emotion engine.

[1292] 2. Server

[1293] The emotion engine analyzes the emotion data and provides the results to the generative AI.

[1294] Generative AI takes emotional state into account to generate training plans and nutritional advice.

[1295] 3. User Device

[1296] User C reviews the personalized training plan and nutrition advice he or she receives on the screen and acts accordingly.

[1297] As described above, by incorporating an emotion engine, this system provides more personalized training plans and nutritional advice that reflect the user's emotional state, enabling users to effectively manage their fitness and nutritional needs while taking their emotional state into account.

[1298] The processing flow will be explained below.

[1299] Providing training plans incorporating an emotion engine (example)

[1300] Step 1:

[1301] User device: The user clicks the training plan request button within the app.

[1302] Step 2:

[1303] User terminal: The request is sent to the server in JSON format.

[1304] Step 3:

[1305] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[1306] sql

[1307] SELECT FROM users WHERE user_id = 'user_a_id';

[1308] Step 4:

[1309] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[1310] Step 5:

[1311] Server: Temporarily stores the training plan received from the generation AI.

[1312] Step 6:

[1313] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[1314] json

[1315] {

[1316] "action": "get_emotion",

[1317] "user_id": "user_a_id"

[1318] }

[1319] Step 7:

[1320] Server: Receives the user's emotional state from the emotion engine.

[1321] Step 8:

[1322] Emotion Engine: Analyzes emotional data and makes appropriate adjustments to the training plan if the user is feeling stressed.

[1323] Step 9:

[1324] Server: Sends the adjusted training plan to the user device.

[1325] Step 10:

[1326] User terminal: Displays the received training plan information on the screen.

[1327] Providing nutrition advice using an emotion engine (example)

[1328] Step 1:

[1329] User terminal: The user clicks on the "Request nutrition advice" button.

[1330] Step 2:

[1331] User terminal: The request is sent to the server in JSON format.

[1332] Step 3:

[1333] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[1334] sql

[1335] SELECT FROM users WHERE user_id = 'user_b_id';

[1336] Step 4:

[1337] Server: Based on the acquired user information and request, the generative AI model is asked to generate nutrition advice. The generative AI model takes into account the user's health status and goals.

[1338] Step 5:

[1339] Server: Temporarily stores nutrition advice received from the generation AI.

[1340] Step 6:

[1341] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[1342] json

[1343] {

[1344] "action": "get_emotion",

[1345] "user_id": "user_b_id"

[1346] }

[1347] Step 7:

[1348] Server: Receives the user's emotional state from the emotion engine.

[1349] Step 8:

[1350] Emotion engine: Analyzes emotional data and makes appropriate adjustments to nutrition advice if the user is feeling stressed.

[1351] Step 9:

[1352] Server: Sends tailored nutrition advice to the user terminal.

[1353] Step 10:

[1354] User terminal: Displays the received nutrition advice information on the screen.

[1355] Progress management and feedback using emotion engine (example)

[1356] Step 1:

[1357] User device: The user enters exercise and diet progress information into the app.

[1358] Step 2:

[1359] Server: Receives progress data and stores it in a database.

[1360] sql

[1361] INSERT INTO progress (user_id, exercise_data, nutrition_data) VALUES ('user_c_id', 'exercise_data', 'nutrition_data');

[1362] Step 3:

[1363] Server: Requests the generative AI model to generate feedback based on the progress data. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[1364] Step 4:

[1365] Server: Temporarily stores feedback received from the generation AI.

[1366] Step 5:

[1367] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[1368] json

[1369] {

[1370] "action": "get_emotion",

[1371] "user_id": "user_c_id"

[1372] }

[1373] Step 6:

[1374] Server: Receives the user's emotional state from the emotion engine.

[1375] Step 7:

[1376] Emotion engine: Analyzes emotional data and provides encouraging and motivational feedback if the user is feeling down.

[1377] Step 8:

[1378] Server: Sends the adjusted feedback to the user device.

[1379] Step 9:

[1380] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[1381] By incorporating an emotion engine, the system can achieve further personalization that takes into account the user's emotional state, providing training plans, nutritional advice, progress management, and feedback.

[1382] Example 2

[1383] 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."

[1384] Conventional training planning and nutrition advice systems provide uniform plans and advice without considering the user's individual emotional state, making it difficult to obtain optimal feedback for the user. It is also difficult to provide prompt, personalized feedback based on the user's progress.

[1385] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generative AI model, means for transmitting the generated training plan to a user terminal, means including an emotion engine for collecting and analyzing the user's emotional state, and means for generating a training plan taking the user's emotional state into consideration using the generative AI model. This makes it possible to provide an optimal training plan and nutritional advice taking the user's emotional state and individual progress information into consideration.

[1386] "Means for accepting user requests" refers to an interface that allows users to make requests to the system for training plans, nutritional advice, etc.

[1387] "Means for obtaining user information from a database" refers to a function for searching and extracting data about users stored in a database within the system.

[1388] "Means for automatically generating training plans using generative AI models" refers to a process that uses artificial intelligence to automatically create personalized training plans based on a user's profile information.

[1389] The "means for transmitting the generated training plan to the user terminal" refers to a function for transmitting the generated training plan to the user's device via a network.

[1390] "Means including an emotion engine that collects and analyzes the user's emotional state" refers to a system that collects and analyzes user's emotional data using text, voice, images, etc.

[1391] "Means for generating a training plan that takes into account a user's emotional state using a generative AI model" refers to a process that uses artificial intelligence to create an individualized training plan that reflects a user's emotional state.

[1392] "Means for automatically generating nutritional advice" refers to a system that uses generative AI to automatically create nutritional advice, taking into account the user's health condition and goals.

[1393] "Means of receiving user progress information and automatically generating feedback using a generation AI" refers to the function of receiving exercise and diet progress data entered by the user and having the generation AI create personalized feedback based on that data.

[1394] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[1395] System configuration

[1396] This system consists of the following main components:

[1397] User terminal

[1398] server

[1399] Database

[1400] Generative AI Models

[1401] Emotion Engine

[1402] User Registration

[1403] 1. User Device

[1404] The user installs the application on their smartphone or computer, opens the new registration screen, enters the required information such as name, email address, and password, and clicks the register button. The entered information is sent to the server in JSON format.

[1405] 2. Server

[1406] The server receives a request from the user's device. It checks the format of the email address and the strength of the password, and if validation is successful, it saves the user information in the database. It then sends a response indicating successful registration to the user's device.

[1407] 3. User Device

[1408] A registration success message will be displayed on the user's device.

[1409] Providing training plans

[1410] 1. User Device

[1411] The user clicks the Request a Training Plan button in the application, and the request is sent to the server in JSON format.

[1412] 2. Server

[1413] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[1414] 3. Server

[1415] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[1416] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[1417] 4. Server

[1418] The training plan received from the generation AI is sent back to the user's device.

[1419] 5. User Device

[1420] The user terminal displays the received training plan, which may include details such as "chest training" on Monday and "cardio" on Tuesday.

[1421] Providing nutritional advice

[1422] 1. User Device

[1423] The user clicks the "Request Nutrition Advice" button, and the request is sent to the server in JSON format.

[1424] 2. Server

[1425] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[1426] 3. Server

[1427] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[1428] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[1429] 4. Server

[1430] The nutritional advice received from the generating AI is sent back to the user's device.

[1431] 5. User Device

[1432] The received nutrition advice is displayed on the user's device. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[1433] Progress management and feedback

[1434] 1. User Device

[1435] Users enter exercise and diet progress information within the app.

[1436] 2. Server

[1437] Receives progress data and stores it in a database.

[1438] 3. Server

[1439] Based on the progress data, the generative AI model is asked to generate feedback, for example, a prompt sentence like this:

[1440] "Consider the user's recent exercise and food logs and suggest next steps."

[1441] 4. Server

[1442] The feedback received from the generation AI is sent back to the user's device.

[1443] 5. User Device

[1444] The received feedback is displayed on the user's device, and the user can make adjustments for further improvement.

[1445] Incorporating an emotion engine

[1446] 1. User Device

[1447] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[1448] 2. Server

[1449] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[1450] 3. Server

[1451] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[1452] "The user is under stress, please suggest some relaxation exercises."

[1453] 4. Server

[1454] The generated training plan and nutrition advice are sent to the user terminal.

[1455] 5. User Device

[1456] Users can obtain appropriate information at the right time on their devices and take action.

[1457] This concludes the concrete implementation of a sports science knowledge provision system using a generative AI model, which enables users to receive optimal fitness and nutritional management that takes into account their individual emotional state and progress information.

[1458] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1459] Step 1:

[1460] Enter and submit user registration information

[1461] Specific actions

[1462] Users install the application on their smartphone or computer and open the new registration screen.

[1463] Fill in the form with the required information, such as your name, email address, and password.

[1464] Click the Register button.

[1465] input

[1466] Information entered by the user, such as name, email address, and password.

[1467] output

[1468] Registration information sent to the server in JSON format.

[1469] Step 2:

[1470] Validation of user information by the server

[1471] Specific actions

[1472] The server receives the user information sent from the terminal.

[1473] Check the format of the email address (e.g., check the format such as example@example.com) and the strength of the password (e.g., check that it is at least 8 characters long, including uppercase and lowercase letters, numbers, and special characters).

[1474] input

[1475] User information sent from the device in JSON format.

[1476] output

[1477] The result of validation: success or failure.

[1478] Step 3:

[1479] Server saves user information and sends response

[1480] Specific actions

[1481] If validation is successful, the server saves the user information in the database.

[1482] A response indicating that the user registration was successful is generated and sent to the terminal.

[1483] input

[1484] User information that has passed validation.

[1485] output

[1486] A response indicating successful registration.

[1487] Step 4:

[1488] Displaying a successful registration message for users

[1489] Specific actions

[1490] The user terminal receives the success response from the server and displays a registration success message on the screen.

[1491] input

[1492] A successful registration response received from the server.

[1493] output

[1494] A successful registration message will be displayed on the device screen.

[1495] Step 5:

[1496] Submit a Training Plan Request

[1497] Specific actions

[1498] The user clicks the request training plan button within the application.

[1499] The request is sent to the server in JSON format.

[1500] input

[1501] User training plan request.

[1502] output

[1503] The request data sent to the server in JSON format.

[1504] Step 6:

[1505] Server retrieval of user profile

[1506] Specific actions

[1507] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[1508] input

[1509] Training plan request received by the server.

[1510] User profile information in the database.

[1511] output

[1512] The user profile information retrieved.

[1513] Step 7:

[1514] Request to generate a training plan

[1515] Specific actions

[1516] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[1517] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[1518] input

[1519] The retrieved user profile information.

[1520] The generated prompt statement.

[1521] output

[1522] A prompt is used to request a generative AI model to generate a training plan.

[1523] Step 8:

[1524] Return and view your training plan

[1525] Specific actions

[1526] The server returns the training plan received from the generation AI to the user's device.

[1527] The user device displays the received training plan on its screen, which may include details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[1528] input

[1529] The training plan received from the generative AI.

[1530] output

[1531] Training plan displayed on device.

[1532] Step 9:

[1533] Submit a Nutrition Advice Request

[1534] Specific actions

[1535] The user clicks the "Request Nutritional Advice" button.

[1536] The request is sent to the server in JSON format.

[1537] input

[1538] User nutrition advice requests.

[1539] output

[1540] The request data sent to the server in JSON format.

[1541] Step 10:

[1542] Obtaining nutritional information

[1543] Specific actions

[1544] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[1545] input

[1546] A nutrition advice request received by the server.

[1547] Nutrition-related information in the database.

[1548] output

[1549] Nutrition-related information obtained.

[1550] Step 11:

[1551] Request for nutrition advice generation

[1552] Specific actions

[1553] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[1554] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[1555] input

[1556] Nutrition-related information obtained.

[1557] The generated prompt statement.

[1558] output

[1559] A prompt is used to request a generative AI model to generate nutrition advice.

[1560] Step 12:

[1561] Return and display of nutrition advice

[1562] Specific actions

[1563] The server sends the nutrition advice received from the generating AI back to the user's device.

[1564] The user device displays the received nutrition advice on its screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[1565] input

[1566] Nutritional advice received from generative AI.

[1567] output

[1568] Nutrition advice displayed on your device.

[1569] Step 13:

[1570] Enter and submit progress information

[1571] Specific actions

[1572] Users enter exercise and diet progress information within the app.

[1573] Progress information is sent to the server in JSON format.

[1574] input

[1575] User-entered progress information.

[1576] output

[1577] Progress information sent to the server in JSON format.

[1578] Step 14:

[1579] Saving progress information

[1580] Specific actions

[1581] The server receives the progress data and stores it in a database.

[1582] input

[1583] The progress information sent.

[1584] output

[1585] Progress information stored in a database.

[1586] Step 15:

[1587] Request for feedback generation

[1588] Specific actions

[1589] The server then asks the generative AI model to generate feedback based on the progress data. For example, it generates a prompt like this:

[1590] "Consider the user's recent exercise and food logs and suggest next steps."

[1591] input

[1592] Saved progress information.

[1593] The generated prompt statement.

[1594] output

[1595] Request a generative AI model with a prompt to generate feedback.

[1596] Step 16:

[1597] Sending and viewing feedback

[1598] Specific actions

[1599] The server sends the feedback received from the generation AI back to the user's device.

[1600] The user device displays the received feedback on the screen, and the user can make adjustments for further improvement.

[1601] input

[1602] Feedback received from the generative AI.

[1603] output

[1604] Feedback displayed on the device.

[1605] Step 17:

[1606] Input and recording of emotional states

[1607] Specific actions

[1608] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[1609] input

[1610] A user-entered or recorded emotional state.

[1611] output

[1612] Emotion data sent to the server.

[1613] Step 18:

[1614] Emotional Data Analysis

[1615] Specific actions

[1616] A server-based emotion engine analyzes the collected emotion data to identify the user's emotional state.

[1617] input

[1618] The emotion data sent.

[1619] output

[1620] Results of analyzed emotional states.

[1621] Step 19:

[1622] Request a personalized plan

[1623] Specific actions

[1624] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[1625] "The user is under stress, please suggest some relaxation exercises."

[1626] input

[1627] Results of analyzed emotional states.

[1628] The generated prompt statement.

[1629] output

[1630] Request a generative AI model with a prompt to generate a personalized plan.

[1631] Step 20:

[1632] Return and view your personalized plan

[1633] Specific actions

[1634] The generated training plan and nutrition advice are sent from the server to the user terminal.

[1635] Users can obtain appropriate information at the right time on their devices and take action.

[1636] input

[1637] A personalized plan received from a generative AI model.

[1638] output

[1639] A personalized plan displayed on your device.

[1640] (Application example 2)

[1641] 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."

[1642] Modern autonomous vehicles face a lack of means to manage the health and mental health of their users while driving. As autonomous vehicles become more widespread, there is a demand for ways to make effective use of their driving time. However, current systems have difficulty providing personalized training plans and nutritional advice that reflect the user's individual needs and emotional state. This means that users are unable to make full use of their time while driving, making it difficult to manage stress and effectively manage their health.

[1643] The specific processing by the specific 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 means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the training plan based on the analyzed emotional state, and means for displaying the plan on a head-mounted display. This enables users to receive personalized training plans and nutritional advice in real time that are tailored to their individual needs and emotional state, even while in an autonomous vehicle.

[1644] The "means for accepting user requests" is a method for providing an interface for accepting requests sent by users.

[1645] The "means for obtaining user information from a database" is a method for reading stored user profile information from a database.

[1646] "Means for automatically generating training plans using generative AI" refers to a method for automatically generating training plans based on a user's health status and goals using a machine learning model.

[1647] The "means for transmitting the generated training plan to the user terminal" is a method for transferring the generated training plan to the user's device.

[1648] The "means for analyzing a user's emotional state using an emotion engine" is a method for interpreting a user's emotional data using emotion recognition technology to identify the user's current emotional state.

[1649] The "means for adjusting a training plan based on the analyzed emotional state" is a method for using the results from the emotion engine to adapt a training plan to a user.

[1650] The "means for displaying a plan on a head-mounted display" is a method for displaying the generated training plan and nutrition advice on a head-mounted display.

[1651] "Means for automatically generating nutritional advice using generative AI" refers to a method that uses machine learning models to automatically generate nutritional advice based on a user's goals and health status.

[1652] "Means of receiving user progress information and automatically generating feedback using AI" refers to a method of receiving progress data provided by the user and generating feedback using a machine learning model based on that data.

[1653] The present invention is a method for providing users with personalized training plans and nutritional advice within an autonomous vehicle using a system that combines a generative AI model and an emotion engine. This system is realized by the following specific components and procedures.

[1654] 1. A means of accepting user requests

[1655] The server accepts requests sent by the user through the head-mounted display, including requests for training plans and nutritional advice.

[1656] 2. A way to retrieve user information from the database

[1657] Based on the received request, the server retrieves user profile information from a database, including the user's age, gender, exercise experience, and health status.

[1658] 3. A means to automatically generate training plans using generative AI

[1659] The server automatically generates a training plan based on the acquired user information using a generative AI model, which uses machine learning algorithms to create an optimal exercise plan for the user.

[1660] 4. Means for sending the generated training plan to the user device

[1661] The server sends the generated training plan to the head-mounted display so that the user can visually check it.

[1662] 5. A method for analyzing the user's emotional state using an emotion engine

[1663] The server collects emotion data provided by the user through the head-mounted display and analyzes it with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state.

[1664] 6. A way to adjust your training plan based on your analyzed emotional state

[1665] The server then uses the emotional state analysis results from the emotion engine to adjust training plans and nutrition advice accordingly, for example adding relaxation exercises if the user is feeling stressed.

[1666] 7. A method for displaying plans on a head-mounted display

[1667] The server then displays tailored training plans and nutrition advice on the head-mounted display, allowing users to receive appropriate feedback in real time.

[1668] Hardware and software used

[1669] Hardware: Head-mounted display, server, database

[1670] Software: Flask, generative AI libraries, emotion engine libraries, database modules

[1671] Specific examples

[1672] 1. While wearing the HMD, the user clicks the "Request a training plan" button.

[1673] Example prompt: "User requests a new training plan. User ID is 12345."

[1674] 2. While wearing the HMD, the user clicks the "Request nutrition advice" button.

[1675] Example prompt: "User requests new nutrition advice. User ID is 12345."

[1676] 3. Input emotional state while the user is wearing the HMD

[1677] Sample prompt: "We have collected the user's emotional data and determined that they are feeling stressed. The emotion engine will generate stress relief advice."

[1678] The system will monitor the user's health and mental state even while in an autonomous vehicle, and provide individually optimized training plans and nutritional advice, thereby improving the user's quality of life.

[1679] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1680] Step 1:

[1681] The server accepts user requests through the head-mounted display, typically requests for training plans or nutrition advice. The input is the request data, and the output is a confirmation that the request was received.

[1682] Step 2:

[1683] The server retrieves user information from a database based on the received request. It uses a database query to collect profile information such as the user's age, gender, exercise experience, and health status. The input is the user ID, and the output is the retrieved user information.

[1684] Step 3:

[1685] The server automatically generates a training plan using a generative AI model based on the acquired user information. The generative AI model runs a trained machine learning algorithm to create a training plan optimized for the user. This generates the contents of the plan. The input is user information, and the output is the generated training plan.

[1686] Step 4:

[1687] The server sends the generated training plan to the user's head-mounted display and displays it, allowing the user to check the training plan in real time. The input is the training plan, and the output is the displayed training plan.

[1688] Step 5:

[1689] The user inputs emotional data through the head-mounted display. For example, data such as facial expressions and heart rate are collected using sensors and cameras built into the head-mounted display. The input is emotional data, and the output is data sent to the server.

[1690] Step 6:

[1691] The server analyzes the collected emotional data with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state. The input is the collected emotional data, and the output is the analyzed emotional state.

[1692] Step 7:

[1693] The server then adjusts the training plan and nutrition advice appropriately based on the emotional state obtained from the emotion engine. For example, if the user is feeling stressed, it suggests relaxation exercises to address that stress. The input is the analyzed emotional state, and the output is the adjusted training plan and nutrition advice.

[1694] Step 8:

[1695] The server sends the adjusted training plan and nutrition advice to the head-mounted display for the user to review in real time. The input is the adjusted plan and advice, and the output is the displayed content.

[1696] Through these steps, users can receive individually optimized training plans and nutritional advice in real time while in an autonomous vehicle, enabling them to efficiently manage their health.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] [Third embodiment]

[1701] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1702] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1703] 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).

[1704] 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.

[1705] 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.

[1706] 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).

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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."

[1713] This invention is a method for utilizing generative AI models to realize a system that provides sports science knowledge. Below, we will explain the important components of the system and their specific operations.

[1714] User Registration

[1715] 1. User Device:

[1716] The user installs the app and enters the required information on the new registration screen, including their name, email address, and password.

[1717] When the registration button is clicked, the form data is sent to the server in JSON format.

[1718] 2. Server:

[1719] The server receives the request and performs validation of the information entered, for example checking that the email address is formatted correctly or that the password is strong.

[1720] If validation is successful, the user information is saved in the database, a success response is sent back to the user's device, and a message indicating successful registration is displayed to the user.

[1721] Providing training plans

[1722] 1. User Device:

[1723] The user clicks the request a training plan button within the app.

[1724] The request is sent to the server in JSON format.

[1725] 2. Server:

[1726] The server receives the request and retrieves the profile information of the user from the database.

[1727] Based on the acquired user information, a generative AI model (e.g., ChatGPT) is asked to generate a training plan.

[1728] The generation AI generates a customized training plan, which the server then sends back to the user's device.

[1729] 3. User Device:

[1730] The user terminal displays the received training plan information on the screen, providing details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[1731] Providing nutritional advice

[1732] 1. User Device:

[1733] The user clicks the "Request Nutritional Advice" button.

[1734] The request is sent to the server in JSON format.

[1735] 2. Server:

[1736] The server receives the request and retrieves the nutrition-related information for the user from the database.

[1737] Based on the acquired user information and request content, the generative AI model is asked to generate nutritional advice.

[1738] The generation AI generates customized nutrition advice, and the server sends the advice back to the user's device.

[1739] 3. User Device:

[1740] The user terminal displays the received nutrition advice information on the screen and provides specific advice such as "eat a high-protein meal for breakfast."

[1741] Progress management and feedback

[1742] 1. User Device:

[1743] Users enter their exercise and diet progress information into the app.

[1744] 2. Server:

[1745] The server stores the progress data in a database and generates feedback using a generative AI model.

[1746] The generated feedback is sent to the user's device, providing the user with progress-based evaluations and suggestions for improvement.

[1747] Specific examples

[1748] Example 1: Retrieving a training plan

[1749] 1. User Device:

[1750] User A clicks the button to request a training plan.

[1751] The request is sent to the server in JSON format.

[1752] 2. Server:

[1753] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[1754] The training plan received from the generation AI is sent back to the user's device.

[1755] 3. User Device:

[1756] User A checks the received training plan on the screen and exercises based on the plan.

[1757] Example 2: Getting nutrition advice

[1758] 1. User Device:

[1759] User B clicks the button to request nutrition advice.

[1760] The request is sent to the server in JSON format.

[1761] 2. Server:

[1762] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[1763] The nutritional advice received from the generating AI is sent back to the user's device.

[1764] 3. User Device:

[1765] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[1766] As described above, this system uses generative AI to provide personalized training plans and nutritional advice based on user requests, thereby realizing efficient and high-quality services for a large number of users.

[1767] The processing flow will be explained below.

[1768] Handling user registration

[1769] Step 1:

[1770] User device: The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[1771] Step 2:

[1772] User device: When the registration button is clicked, the form data is sent to the server in JSON format.

[1773] Step 3:

[1774] Server: Receives the request and validates the entered information, specifically checking the format of the email address and the strength of the password.

[1775] Step 4:

[1776] Server: If validation is successful, save the user information to the database.

[1777] Step 5:

[1778] Server: Sends a success response to the user terminal, and the user terminal displays a message indicating successful registration.

[1779] Providing training plans

[1780] Step 1:

[1781] User device: The user clicks the training plan request button within the app.

[1782] Step 2:

[1783] User terminal: The request is sent to the server in JSON format.

[1784] Step 3:

[1785] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[1786] Step 4:

[1787] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[1788] Step 5:

[1789] Server: Returns the training plan received from the generation AI to the user device.

[1790] Step 6:

[1791] User device: Displays the received training plan information on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[1792] Providing nutritional advice

[1793] Step 1:

[1794] User terminal: The user clicks on the "Request nutrition advice" button.

[1795] Step 2:

[1796] User terminal: The request is sent to the server in JSON format.

[1797] Step 3:

[1798] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[1799] Step 4:

[1800] Server: Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice. The generative AI model takes into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[1801] Step 5:

[1802] Server: Returns the nutrition advice received from the generation AI to the user's device.

[1803] Step 6:

[1804] User device: The received nutrition advice information is displayed on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[1805] Progress management and feedback

[1806] Step 1:

[1807] User device: The user enters exercise and diet progress information into the app.

[1808] Step 2:

[1809] Server: Receives progress data and stores it in a database.

[1810] Step 3:

[1811] Server: Based on the progress data, the server requests the generative AI model to generate feedback. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[1812] Step 4:

[1813] Server: Returns the feedback received from the generation AI to the user device.

[1814] Step 5:

[1815] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[1816] Through the above processing flow, the system can provide users with personalized training plans and nutritional advice, and can also provide progress management and feedback functions, realizing an efficient and high-quality service.

[1817] Example 1

[1818] 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."

[1819] Traditional methods have not made it easy for users to quickly and efficiently obtain personalized training plans and nutritional advice. It has also been difficult to monitor users' progress in real time and provide appropriate feedback. Therefore, there has been a need for a system that can help users achieve their health and fitness goals.

[1820] 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.

[1821] In this invention, the server includes: means for transmitting form data in JSON format to the server when a user enters necessary information on a new registration screen and clicks the registration button; means for the server to receive the request, validate the entered information, and, if successful, store the user information in a database and return a success response to the user terminal; means for transmitting a request in JSON format to the server when the user terminal clicks a training plan request button; means for the server to receive the request, retrieve the user's profile information from the database, and request the generation AI model to generate a training plan; and means for returning the generated training plan to the user terminal and displaying the training plan received by the user terminal on the screen. This allows users to quickly and efficiently obtain personalized training plans and nutritional advice, and also enables progress management in real time.

[1822] A "user terminal" is an electronic device used by a user to input information and communicate with the system.

[1823] A "server" is a centralized computer system that receives requests from user devices, validates information, and interacts with databases.

[1824] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in an organized text format.

[1825] A "database" is a system that stores information in a structured format and allows it to be searched and updated later.

[1826] A "generative AI model" is an algorithm or software that uses artificial intelligence technology to generate information, such as a model that automatically generates training plans or nutritional advice.

[1827] "Validation" is the process of checking whether the entered information is in the correct format or meets certain conditions.

[1828] "Feedback" is information, including evaluations and suggestions for improvement, that the system provides based on the user's progress.

[1829] "Profile information" is information about the attributes and status of each user, including, for example, age, height, weight, and fitness level.

[1830] A "training plan" is an exercise program created by a generative AI model to achieve a user's fitness goals.

[1831] "Nutrition advice" refers to advice and suggestions about a user's diet, which are customized and generated by a generative AI model.

[1832] The present invention is a system that uses generative AI models to provide users with sports science-based training plans and nutrition advice. Specific embodiments of the present invention are described in detail below.

[1833] User Registration

[1834] First, in order for a user to use the system, they must register using their device. The user installs the app and enters information such as their name, email address, and password on the registration screen. Once the user has completed the entry and clicked the registration button, the entered information is sent to the server in JSON format.

[1835] The server receives the request sent from the user terminal and validates the input information. For example, it checks whether the email address format is correct and whether the password is strong. If validation is successful, the user information is saved in the database and a response indicating successful registration is sent back to the user terminal. The user terminal receives this response and displays a message indicating successful registration on its screen.

[1836] Providing training plans

[1837] To request a training plan, a user clicks on the training plan request button in the app. This request is sent to the server in JSON format. After receiving the request, the server retrieves the user's profile information from the database.

[1838] Next, a prompt is generated and sent to the generative AI model (e.g., ChatGPT). The prompt includes information such as the user's age, height, weight, and fitness level. Based on the generated prompt, the generative AI model generates a customized training plan. The server receives the generated training plan and sends it to the user's device. The user's device receives this information and displays details such as "chest training" on Mondays and "aerobic exercise" on Tuesdays.

[1839] Providing nutritional advice

[1840] When a user requests nutrition advice, they click the "Request Nutrition Advice" button in the app. The request is sent to the server in JSON format. After receiving the request, the server retrieves the user's nutrition-related information from the database.

[1841] Based on the acquired nutritional information, the server sends prompts to the generative AI model, asking it to generate customized nutritional advice. The generated nutritional advice is sent to the user's device via the server, and the user's device displays this information on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[1842] Progress management and feedback

[1843] Users enter their exercise and diet progress information into the app. The server receives and stores this progress information and requests the generative AI model to generate feedback. The generated feedback is sent from the server to the user's device, and the user is given an evaluation and suggestions for improvement based on their progress.

[1844] Examples of concrete examples and prompts

[1845] Example 1: Obtaining a training plan

[1846] When User A clicks the button to request a training plan, the request is sent in JSON format to the server. The server obtains the user's profile information and asks the generation AI to generate a training plan. The generated training plan is sent back to the user's device, and User A checks the received plan and performs the exercise.

[1847] Example 2: Getting nutrition advice

[1848] When User B clicks the button to request nutrition advice, the request is sent in JSON format to the server. The server obtains the user's nutrition-related information and asks the AI ​​to generate advice. The generated nutrition advice is sent back to the user's device, where User B can review the advice and plan their meals.

[1849] Prompt Sentence Examples

[1850] "Generate a training plan. Your profile information is as follows: age 30, height 175cm, weight 70kg, and fitness level intermediate."

[1851] "Generate nutrition advice. User's nutritional information is: vegan, goal weight 65kg, current weight 70kg."

[1852] As described above, the present invention uses generative AI models to provide users with personalized training plans and nutritional advice, and provides progress management and feedback, thereby achieving efficient and high-quality services.

[1853] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1854] Step 1: Enter user registration information

[1855] User device:

[1856] Input: User information such as name, email address, and password.

[1857] How it works: The user installs the app and enters the required information on the new registration screen.

[1858] Output: When the registration button is clicked, the entered information is sent to the server as JSON format data.

[1859] Step 2: Information validation and storage

[1860] server:

[1861] Input: JSON format user information sent from the user device.

[1862] What it does: The server receives the request, checks that the email address is valid and the password is strong, and if validation is successful, stores the user information in the database.

[1863] Output: Generates a response indicating successful registration and sends it to the user's device. If any information is inaccurate, generates and returns an error message.

[1864] Step 3: Viewing registration results

[1865] User device:

[1866] Input: Registration success or error message sent by the server.

[1867] Operation: The user terminal displays the received message on the screen.

[1868] Output: Registration success message or error message.

[1869] Step 4: Submit a training plan request

[1870] User device:

[1871] Enter: Click on Training Plan Request.

[1872] What happens: A user clicks the in-app training plan request button.

[1873] Output: The request is sent to the server as JSON data.

[1874] Step 5: Obtain user information

[1875] server:

[1876] Input: Training plan request sent from user device.

[1877] How it works: The server receives the request and retrieves the user's profile information (age, height, weight, fitness level, etc.) from the database.

[1878] Output: The retrieved profile information.

[1879] Step 6: Prompt generation and AI requests

[1880] server:

[1881] Input: User profile information.

[1882] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate a training plan.

[1883] Output: The generated training plan.

[1884] Step 7: Submit your training plan

[1885] server:

[1886] Input: The training plan received from the generative AI model.

[1887] Operation: The server transmits the generated training plan to the user terminal.

[1888] Output: The training plan sent to the user device.

[1889] Step 8: View your training plan

[1890] User device:

[1891] Input: The training plan sent by the server.

[1892] How it works: The user device displays the received training plan on the screen, providing details such as "chest workout" on Monday and "cardio" on Tuesday.

[1893] Output: Training plan displayed on the screen.

[1894] Step 9: Submit a nutrition advice request

[1895] User device:

[1896] Enter: Click on Request Nutritional Advice.

[1897] What happens: A user clicks the "Request Nutrition Advice" button in the app.

[1898] Output: The request is sent to the server as JSON data.

[1899] Step 10: Obtaining user nutrition information

[1900] server:

[1901] Input: A nutrition advice request sent from a user device.

[1902] How it works: The server receives the request and retrieves the user's nutrition-related information (such as dietary preferences and allergy information) from the database.

[1903] Output: Retrieved nutrition-related information.

[1904] Step 11: Prompt generation and AI request (nutritional advice)

[1905] server:

[1906] Input: User nutrition related information.

[1907] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate nutritional advice.

[1908] Output: The generated nutrition advice.

[1909] Step 12: Send nutrition advice

[1910] server:

[1911] Input: Nutrition advice received from a generative AI model.

[1912] Operation: The server transmits the generated nutrition advice to the user terminal.

[1913] Output: Nutrition advice sent to the user device.

[1914] Step 13: View nutrition advice

[1915] User device:

[1916] Input: Nutrition advice sent from the server.

[1917] Operation: The user device displays the received nutrition advice on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[1918] Output: Nutrition advice displayed on the screen.

[1919] Step 14: Enter progress information

[1920] User device:

[1921] Input: Exercise and diet progress information.

[1922] How it works: Users enter exercise and diet progress information into the app.

[1923] Output: The entered progress information is sent to the server in JSON format.

[1924] Step 15: Save progress information and request AI

[1925] server:

[1926] Input: Progress information sent from the user's device.

[1927] How it works: The server stores progress information in a database and asks the generative AI model to generate feedback based on the stored progress data.

[1928] Output: The generated feedback.

[1929] Step 16: Send feedback

[1930] server:

[1931] Input: Feedback received from the generative AI model.

[1932] Operation: The server sends the generated feedback to the user terminal.

[1933] Output: Feedback sent to the user device.

[1934] Step 17: Viewing feedback

[1935] User device:

[1936] Input: Feedback sent by the server.

[1937] How it works: The user device displays the received feedback on its screen, providing the user with a rating and suggestions for improvement based on their progress.

[1938] Output: Feedback displayed on the screen.

[1939] (Application example 1)

[1940] 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."

[1941] In today's advanced information society, various security threats exist on a daily basis, requiring rapid and appropriate responses to these threats. At the same time, there is a growing demand for personalized training plans and nutritional advice that utilize knowledge of sports science. However, there is a lack of mechanisms to efficiently provide these to individual users. Furthermore, it is difficult to utilize wearable devices such as smart glasses to perform real-time situation analysis and present appropriate defensive measures. Given this background, there is a need for a system that can provide personalized training plans and nutritional advice while also effectively providing security support through devices such as smart glasses.

[1942] 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.

[1943] In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the situation based on data acquired from sensors, and means for providing defensive measures according to the situation using the generation AI. This makes it possible to provide the user with a personalized training plan and nutritional advice, while also providing real-time security support through the wearable device.

[1944] "User" refers to an individual or corporation that uses this system, and whose information is registered in the database.

[1945] The "means for accepting a request" is an interface for receiving a request from a user in an input format and transmitting it to a server.

[1946] A "database" is a system for storing user information and related data, and for searching and retrieving them as needed.

[1947] "User information" refers to various data required by the system, such as a user's personal information, profile data, and activity history.

[1948] "Generative AI" is a technology that uses machine learning models trained on large datasets to generate training plans, nutritional advice, and situational defensive strategies based on user requests.

[1949] A "training plan" is an exercise program automatically created by the generation AI based on the user's health condition and goals.

[1950] "Nutrition advice" refers to dietary suggestions provided by the generative AI based on the user's diet and health status.

[1951] A "user terminal" is a device (e.g., a smartphone, smart glasses, head-mounted display, etc.) that a user uses to access the system.

[1952] A "sensor" is a device for detecting environmental information and user activity, and includes a camera, microphone, GPS, etc.

[1953] "Situation analysis" is the process of assessing the current environment and the user's situation based on data obtained from sensors.

[1954] "Defensive measures" are guidelines and countermeasures provided by the generative AI based on situational analysis to ensure the user's safety.

[1955] "Progress information" is data related to training plans and nutrition advice, such as records of exercise and meals a user has completed.

[1956] "Feedback" refers to evaluations and suggestions for improvement provided by the generating AI based on the user's progress information.

[1957] The present invention is a system that utilizes generative AI models to provide users with personalized training plans, nutritional advice, and security support. The specific operation of the system is described below.

[1958] 1. User Registration

[1959] User device:

[1960] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The form data is sent to the server in JSON format.

[1961] server:

[1962] The server receives the request, validates the entered information, and if successful, stores the user information in a database and returns a message to the user terminal indicating successful registration.

[1963] 2. Providing training plans

[1964] User device:

[1965] The user clicks the training plan request button and the request is sent to the server in JSON format.

[1966] server:

[1967] The server receives the request, retrieves the user's profile information from the database, and requests the generation AI to generate a training plan. The generated training plan is then sent back to the user's device.

[1968] User device:

[1969] The user displays the received training plan on the screen and performs exercise based on the plan's contents.

[1970] 3. Providing nutritional advice

[1971] User device:

[1972] The user clicks the request nutrition advice button and the request is sent in JSON format to the server.

[1973] server:

[1974] The server receives the request, retrieves the user's nutrition-related information from the database, and requests the AI ​​to generate advice. The generated nutrition advice is then sent back to the user's device.

[1975] User device:

[1976] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[1977] 4. Security Support

[1978] User device (smart glasses):

[1979] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings and send the data in JSON format to a server.

[1980] server:

[1981] The server receives and analyzes the data sent from the sensors and performs situation analysis. Based on the analysis results, the generative AI provides appropriate defensive measures.

[1982] User device:

[1983] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[1984] 5. Progress Management and Feedback

[1985] User device:

[1986] Users enter their exercise and diet progress information into the app.

[1987] server:

[1988] The server stores the progress data in a database, and the AI ​​generates feedback based on the progress. The generated feedback is sent to the user's device and displayed on the screen.

[1989] Hardware and Software Use

[1990] Hardware:

[1991] Smart glasses (e.g., Google Glass, Microsoft HoloLens)

[1992] Built-in sensors (camera, microphone, GPS)

[1993] software:

[1994] Web server (e.g. Python Flask, Django)

[1995] Database (e.g. MySQL, PostgreSQL)

[1996] Generative AI models (e.g. ChatGPT)

[1997] Specific examples

[1998] Get your training plan

[1999] 1. User Device:

[2000] User A clicks the button to request a training plan, and the request is sent to the server in JSON format.

[2001] 2. Server:

[2002] The server acquires the user's profile information and requests the AI ​​to generate a training plan. The AI ​​then returns the training plan to the user's device.

[2003] 3. User Device:

[2004] User A checks the received training plan on the screen and exercises based on the plan.

[2005] Prompt Sentence Examples

[2006] 1. Training plan generation prompt:

[2007] Current Situation: User A is looking to improve his muscle strength.

[2008] Q: Create a training plan for the week.

[2009] 2. Nutrition advice generation prompts:

[2010] Current Situation: User B is trying to lose weight.

[2011] Q: What is your daily meal plan?

[2012] 3. Situation Analysis Prompt:

[2013] Current situation: Unknown people are approaching you.

[2014] Information: It's 8pm and the location is on a deserted street.

[2015] Question: How can I stay safe?

[2016] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2017] Step 1:

[2018] User Registration

[2019] User device:

[2020] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The input data (name, email address, and password) is sent to the server in JSON format.

[2021] server:

[2022] The server receives the request and validates the input data. If validation is successful, the user information is saved in the database. A success response (registration successful message) is sent back to the user device.

[2023] Step 2:

[2024] Providing training plans

[2025] User device:

[2026] The user clicks the training plan request button, and the request (user ID and desired content data) is sent to the server in JSON format.

[2027] server:

[2028] The server receives the request and retrieves the user's profile information from the database. Based on the retrieved information, it asks the generation AI to generate a training plan. The generation AI generates the training plan and returns the data to the server. The server then returns the generated training plan data to the user's device.

[2029] User device:

[2030] The user displays the received training plan on the screen and performs exercise based on the plan.

[2031] Step 3:

[2032] Providing nutritional advice

[2033] User device:

[2034] The user clicks the request button for nutrition advice, and the request (user ID and desired content data) is sent to the server in JSON format.

[2035] server:

[2036] The server receives the request and retrieves the user's nutrition-related information from the database. Based on the retrieved information, it asks the generation AI to generate nutrition advice. The generation AI generates the nutrition advice and returns the data to the server. The server then returns the generated nutrition advice data to the user's device.

[2037] User device:

[2038] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[2039] Step 4:

[2040] Security Assistance

[2041] User device (smart glasses):

[2042] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings, and the collected data (environmental information, location information, etc.) is sent to the server in JSON format.

[2043] server:

[2044] The server receives data sent from the sensors and analyzes the situation. It processes the data (normalizes location information, analyzes audio data, analyzes image data, etc.) and passes the analysis results to the generation AI. The generation AI generates defensive measures according to the situation and returns the data to the server. The server then returns the generated defensive measures data to the user device.

[2045] User device:

[2046] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[2047] Step 5:

[2048] Progress management and feedback

[2049] User device:

[2050] Users input their exercise and diet progress information into the app. The input data (exercise status, diet details, etc.) is sent to the server in JSON format.

[2051] server:

[2052] The server stores the progress data in a database and requests the generation AI to generate feedback based on the progress information. The generation AI generates the feedback and returns the data to the server. The server then sends the generated feedback data back to the user's device.

[2053] User device:

[2054] Users can check the feedback they receive on screen and use it to guide their next actions.

[2055] 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.

[2056] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[2057] User Registration

[2058] 1. User Device

[2059] The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[2060] When you click the register button, the form data is sent to the server in JSON format.

[2061] 2. Server

[2062] The server receives the request and performs validation of the information entered, such as checking the format of the email address and the strength of the password.

[2063] If validation is successful, save the user information to the database.

[2064] 3. Server

[2065] A success response is sent to the user terminal, and the user terminal displays a message indicating successful registration.

[2066] Providing training plans

[2067] 1. User Device

[2068] The user clicks the request a training plan button within the app.

[2069] The request is sent to the server in JSON format.

[2070] 2. Server

[2071] The server receives the request and retrieves the profile information of the user from the database.

[2072] Based on the acquired user information, the generative AI model is asked to generate a training plan, which takes into account the user's age, gender, exercise experience, etc. to generate a customized plan.

[2073] 3. Server

[2074] The training plan received from the generation AI is sent back to the user's device.

[2075] 4. User Device

[2076] The received training plan information is displayed on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[2077] Providing nutritional advice

[2078] 1. User Device

[2079] The user clicks the "Request Nutritional Advice" button.

[2080] The request is sent to the server in JSON format.

[2081] 2. Server

[2082] The server receives the request and retrieves the nutrition-related information for the user from the database.

[2083] Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice, taking into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[2084] 3. Server

[2085] The nutritional advice received from the generating AI is sent back to the user's device.

[2086] 4. User Device

[2087] The received nutrition advice information is displayed on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[2088] Progress management and feedback

[2089] 1. User Device

[2090] Users enter their exercise and diet progress information into the app.

[2091] 2. Server

[2092] Receives progress data and stores it in a database.

[2093] 3. Server

[2094] Based on the progress data, the generative AI model is asked to generate feedback, which evaluates the user's progress and provides suggestions for improvement and next steps.

[2095] 4. Server

[2096] The feedback received from the generation AI is sent back to the user's device.

[2097] 5. User Device

[2098] The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[2099] Incorporating an emotion engine

[2100] 1. User Device

[2101] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[2102] 2. Server

[2103] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[2104] 3. Server

[2105] Based on the analysis results from the emotion engine, the generative AI model can further personalize training plans and nutrition advice, for example suggesting relaxation exercises if the user is under stress.

[2106] 4. Server

[2107] The generated training plan and nutrition advice are sent to the user's terminal, allowing the user to obtain appropriate information at the appropriate time.

[2108] Specific examples

[2109] Example 1: Retrieving a training plan

[2110] 1. User Device

[2111] User A clicks the button to request a training plan.

[2112] The request is sent to the server in JSON format.

[2113] 2. Server

[2114] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[2115] The training plan received from the generation AI is sent back to the user's device.

[2116] 3. User Device

[2117] User A checks the received training plan on the screen and exercises based on the plan.

[2118] Example 2: Getting nutrition advice

[2119] 1. User Device

[2120] User B clicks the button to request nutrition advice.

[2121] The request is sent to the server in JSON format.

[2122] 2. Server

[2123] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[2124] The nutritional advice received from the generating AI is sent back to the user's device.

[2125] 3. User Device

[2126] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[2127] Example 3: Using the Emotion Engine

[2128] 1. User Device

[2129] User C inputs his emotional state.

[2130] The data is sent to the server through the emotion engine.

[2131] 2. Server

[2132] The emotion engine analyzes the emotion data and provides the results to the generative AI.

[2133] Generative AI takes emotional state into account to generate training plans and nutritional advice.

[2134] 3. User Device

[2135] User C reviews the personalized training plan and nutrition advice he or she receives on the screen and acts accordingly.

[2136] As described above, by incorporating an emotion engine, this system provides more personalized training plans and nutritional advice that reflect the user's emotional state, enabling users to effectively manage their fitness and nutritional needs while taking their emotional state into account.

[2137] The processing flow will be explained below.

[2138] Providing training plans incorporating an emotion engine (example)

[2139] Step 1:

[2140] User device: The user clicks the training plan request button within the app.

[2141] Step 2:

[2142] User terminal: The request is sent to the server in JSON format.

[2143] Step 3:

[2144] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[2145] sql

[2146] SELECT FROM users WHERE user_id = 'user_a_id';

[2147] Step 4:

[2148] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[2149] Step 5:

[2150] Server: Temporarily stores the training plan received from the generation AI.

[2151] Step 6:

[2152] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[2153] json

[2154] {

[2155] "action": "get_emotion",

[2156] "user_id": "user_a_id"

[2157] }

[2158] Step 7:

[2159] Server: Receives the user's emotional state from the emotion engine.

[2160] Step 8:

[2161] Emotion Engine: Analyzes emotional data and makes appropriate adjustments to the training plan if the user is feeling stressed.

[2162] Step 9:

[2163] Server: Sends the adjusted training plan to the user device.

[2164] Step 10:

[2165] User terminal: Displays the received training plan information on the screen.

[2166] Providing nutrition advice using an emotion engine (example)

[2167] Step 1:

[2168] User terminal: The user clicks on the "Request nutrition advice" button.

[2169] Step 2:

[2170] User terminal: The request is sent to the server in JSON format.

[2171] Step 3:

[2172] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[2173] sql

[2174] SELECT FROM users WHERE user_id = 'user_b_id';

[2175] Step 4:

[2176] Server: Based on the acquired user information and request, the generative AI model is asked to generate nutrition advice. The generative AI model takes into account the user's health status and goals.

[2177] Step 5:

[2178] Server: Temporarily stores nutrition advice received from the generation AI.

[2179] Step 6:

[2180] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[2181] json

[2182] {

[2183] "action": "get_emotion",

[2184] "user_id": "user_b_id"

[2185] }

[2186] Step 7:

[2187] Server: Receives the user's emotional state from the emotion engine.

[2188] Step 8:

[2189] Emotion engine: Analyzes emotional data and makes appropriate adjustments to nutrition advice if the user is feeling stressed.

[2190] Step 9:

[2191] Server: Sends tailored nutrition advice to the user terminal.

[2192] Step 10:

[2193] User terminal: Displays the received nutrition advice information on the screen.

[2194] Progress management and feedback using emotion engine (example)

[2195] Step 1:

[2196] User device: The user enters exercise and diet progress information into the app.

[2197] Step 2:

[2198] Server: Receives progress data and stores it in a database.

[2199] sql

[2200] INSERT INTO progress (user_id, exercise_data, nutrition_data) VALUES ('user_c_id', 'exercise_data', 'nutrition_data');

[2201] Step 3:

[2202] Server: Requests the generative AI model to generate feedback based on the progress data. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[2203] Step 4:

[2204] Server: Temporarily stores feedback received from the generation AI.

[2205] Step 5:

[2206] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[2207] json

[2208] {

[2209] "action": "get_emotion",

[2210] "user_id": "user_c_id"

[2211] }

[2212] Step 6:

[2213] Server: Receives the user's emotional state from the emotion engine.

[2214] Step 7:

[2215] Emotion engine: Analyzes emotional data and provides encouraging and motivational feedback if the user is feeling down.

[2216] Step 8:

[2217] Server: Sends the adjusted feedback to the user device.

[2218] Step 9:

[2219] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[2220] By incorporating an emotion engine, the system can achieve further personalization that takes into account the user's emotional state, providing training plans, nutritional advice, progress management, and feedback.

[2221] Example 2

[2222] 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."

[2223] Conventional training planning and nutrition advice systems provide uniform plans and advice without considering the user's individual emotional state, making it difficult to obtain optimal feedback for the user. It is also difficult to provide prompt, personalized feedback based on the user's progress.

[2224] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generative AI model, means for transmitting the generated training plan to a user terminal, means including an emotion engine for collecting and analyzing the user's emotional state, and means for generating a training plan taking the user's emotional state into consideration using the generative AI model. This makes it possible to provide an optimal training plan and nutritional advice taking the user's emotional state and individual progress information into consideration.

[2225] "Means for accepting user requests" refers to an interface that allows users to make requests to the system for training plans, nutritional advice, etc.

[2226] "Means for obtaining user information from a database" refers to a function for searching and extracting data about users stored in a database within the system.

[2227] "Means for automatically generating training plans using generative AI models" refers to a process that uses artificial intelligence to automatically create personalized training plans based on a user's profile information.

[2228] The "means for transmitting the generated training plan to the user terminal" refers to a function for transmitting the generated training plan to the user's device via a network.

[2229] "Means including an emotion engine that collects and analyzes the user's emotional state" refers to a system that collects and analyzes user's emotional data using text, voice, images, etc.

[2230] "Means for generating a training plan that takes into account a user's emotional state using a generative AI model" refers to a process that uses artificial intelligence to create an individualized training plan that reflects a user's emotional state.

[2231] "Means for automatically generating nutritional advice" refers to a system that uses generative AI to automatically create nutritional advice, taking into account the user's health condition and goals.

[2232] "Means of receiving user progress information and automatically generating feedback using a generation AI" refers to the function of receiving exercise and diet progress data entered by the user and having the generation AI create personalized feedback based on that data.

[2233] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[2234] System configuration

[2235] This system consists of the following main components:

[2236] User terminal

[2237] server

[2238] Database

[2239] Generative AI Models

[2240] Emotion Engine

[2241] User Registration

[2242] 1. User Device

[2243] The user installs the application on their smartphone or computer, opens the new registration screen, enters the required information such as name, email address, and password, and clicks the register button. The entered information is sent to the server in JSON format.

[2244] 2. Server

[2245] The server receives a request from the user's device. It checks the format of the email address and the strength of the password, and if validation is successful, it saves the user information in the database. It then sends a response indicating successful registration to the user's device.

[2246] 3. User Device

[2247] A registration success message will be displayed on the user's device.

[2248] Providing training plans

[2249] 1. User Device

[2250] The user clicks the Request a Training Plan button in the application, and the request is sent to the server in JSON format.

[2251] 2. Server

[2252] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[2253] 3. Server

[2254] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[2255] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[2256] 4. Server

[2257] The training plan received from the generation AI is sent back to the user's device.

[2258] 5. User Device

[2259] The user terminal displays the received training plan, which may include details such as "chest training" on Monday and "cardio" on Tuesday.

[2260] Providing nutritional advice

[2261] 1. User Device

[2262] The user clicks the "Request Nutrition Advice" button, and the request is sent to the server in JSON format.

[2263] 2. Server

[2264] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[2265] 3. Server

[2266] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[2267] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[2268] 4. Server

[2269] The nutritional advice received from the generating AI is sent back to the user's device.

[2270] 5. User Device

[2271] The received nutrition advice is displayed on the user's device. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[2272] Progress management and feedback

[2273] 1. User Device

[2274] Users enter exercise and diet progress information within the app.

[2275] 2. Server

[2276] Receives progress data and stores it in a database.

[2277] 3. Server

[2278] Based on the progress data, the generative AI model is asked to generate feedback, for example, a prompt sentence like this:

[2279] "Consider the user's recent exercise and food logs and suggest next steps."

[2280] 4. Server

[2281] The feedback received from the generation AI is sent back to the user's device.

[2282] 5. User Device

[2283] The received feedback is displayed on the user's device, and the user can make adjustments for further improvement.

[2284] Incorporating an emotion engine

[2285] 1. User Device

[2286] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[2287] 2. Server

[2288] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[2289] 3. Server

[2290] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[2291] "The user is under stress, please suggest some relaxation exercises."

[2292] 4. Server

[2293] The generated training plan and nutrition advice are sent to the user terminal.

[2294] 5. User Device

[2295] Users can obtain appropriate information at the right time on their devices and take action.

[2296] This concludes the concrete implementation of a sports science knowledge provision system using a generative AI model, which enables users to receive optimal fitness and nutritional management that takes into account their individual emotional state and progress information.

[2297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2298] Step 1:

[2299] Enter and submit user registration information

[2300] Specific actions

[2301] Users install the application on their smartphone or computer and open the new registration screen.

[2302] Fill in the form with the required information, such as your name, email address, and password.

[2303] Click the Register button.

[2304] input

[2305] Information entered by the user, such as name, email address, and password.

[2306] output

[2307] Registration information sent to the server in JSON format.

[2308] Step 2:

[2309] Validation of user information by the server

[2310] Specific actions

[2311] The server receives the user information sent from the terminal.

[2312] Check the format of the email address (e.g., check the format such as example@example.com) and the strength of the password (e.g., check that it is at least 8 characters long, including uppercase and lowercase letters, numbers, and special characters).

[2313] input

[2314] User information sent from the device in JSON format.

[2315] output

[2316] The result of validation: success or failure.

[2317] Step 3:

[2318] Server saves user information and sends response

[2319] Specific actions

[2320] If validation is successful, the server saves the user information in the database.

[2321] A response indicating that the user registration was successful is generated and sent to the terminal.

[2322] input

[2323] User information that has passed validation.

[2324] output

[2325] A response indicating successful registration.

[2326] Step 4:

[2327] Displaying a successful registration message for users

[2328] Specific actions

[2329] The user terminal receives the success response from the server and displays a registration success message on the screen.

[2330] input

[2331] A successful registration response received from the server.

[2332] output

[2333] A successful registration message will be displayed on the device screen.

[2334] Step 5:

[2335] Submit a Training Plan Request

[2336] Specific actions

[2337] The user clicks the request training plan button within the application.

[2338] The request is sent to the server in JSON format.

[2339] input

[2340] User training plan request.

[2341] output

[2342] The request data sent to the server in JSON format.

[2343] Step 6:

[2344] Server retrieval of user profile

[2345] Specific actions

[2346] The server receives the request and retrieves the user's profile information from the database, including age, gender, and exercise experience.

[2347] input

[2348] Training plan request received by the server.

[2349] User profile information in the database.

[2350] output

[2351] The user profile information retrieved.

[2352] Step 7:

[2353] Request to generate a training plan

[2354] Specific actions

[2355] Based on the acquired user information, the generative AI model is asked to generate a training plan. For example, it generates a prompt sentence like this:

[2356] "A 25-year-old male with intermediate exercise experience who wants to train three times a week. Please create a training plan that suits him."

[2357] input

[2358] The retrieved user profile information.

[2359] The generated prompt statement.

[2360] output

[2361] A prompt is used to request a generative AI model to generate a training plan.

[2362] Step 8:

[2363] Return and view your training plan

[2364] Specific actions

[2365] The server returns the training plan received from the generation AI to the user's device.

[2366] The user device displays the received training plan on its screen, which may include details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[2367] input

[2368] The training plan received from the generative AI.

[2369] output

[2370] Training plan displayed on device.

[2371] Step 9:

[2372] Submit a Nutrition Advice Request

[2373] Specific actions

[2374] The user clicks the "Request Nutritional Advice" button.

[2375] The request is sent to the server in JSON format.

[2376] input

[2377] User nutrition advice requests.

[2378] output

[2379] The request data sent to the server in JSON format.

[2380] Step 10:

[2381] Obtaining nutritional information

[2382] Specific actions

[2383] The server receives the request and retrieves the user's nutrition-related information from the database, including the user's health status and dietary goals.

[2384] input

[2385] A nutrition advice request received by the server.

[2386] Nutrition-related information in the database.

[2387] output

[2388] Nutrition-related information obtained.

[2389] Step 11:

[2390] Request for nutrition advice generation

[2391] Specific actions

[2392] Based on the acquired user information and the request content, the generative AI model is asked to generate nutrition advice. For example, the following prompt sentence is generated:

[2393] "A 30-year-old woman wants to lose weight and limit her daily calorie intake to 1600 kcal. Create a weekly meal plan for her."

[2394] input

[2395] Nutrition-related information obtained.

[2396] The generated prompt statement.

[2397] output

[2398] A prompt is used to request a generative AI model to generate nutrition advice.

[2399] Step 12:

[2400] Return and display of nutrition advice

[2401] Specific actions

[2402] The server sends the nutrition advice received from the generating AI back to the user's device.

[2403] The user device displays the received nutrition advice on its screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[2404] input

[2405] Nutritional advice received from generative AI.

[2406] output

[2407] Nutrition advice displayed on your device.

[2408] Step 13:

[2409] Enter and submit progress information

[2410] Specific actions

[2411] Users enter exercise and diet progress information within the app.

[2412] Progress information is sent to the server in JSON format.

[2413] input

[2414] User-entered progress information.

[2415] output

[2416] Progress information sent to the server in JSON format.

[2417] Step 14:

[2418] Saving progress information

[2419] Specific actions

[2420] The server receives the progress data and stores it in a database.

[2421] input

[2422] The progress information sent.

[2423] output

[2424] Progress information stored in a database.

[2425] Step 15:

[2426] Request for feedback generation

[2427] Specific actions

[2428] The server then asks the generative AI model to generate feedback based on the progress data. For example, it generates a prompt like this:

[2429] "Consider the user's recent exercise and food logs and suggest next steps."

[2430] input

[2431] Saved progress information.

[2432] The generated prompt statement.

[2433] output

[2434] Request a generative AI model with a prompt to generate feedback.

[2435] Step 16:

[2436] Sending and viewing feedback

[2437] Specific actions

[2438] The server sends the feedback received from the generation AI back to the user's device.

[2439] The user device displays the received feedback on the screen, and the user can make adjustments for further improvement.

[2440] input

[2441] Feedback received from the generative AI.

[2442] output

[2443] Feedback displayed on the device.

[2444] Step 17:

[2445] Input and recording of emotional states

[2446] Specific actions

[2447] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[2448] input

[2449] A user-entered or recorded emotional state.

[2450] output

[2451] Emotion data sent to the server.

[2452] Step 18:

[2453] Emotional Data Analysis

[2454] Specific actions

[2455] A server-based emotion engine analyzes the collected emotion data to identify the user's emotional state.

[2456] input

[2457] The emotion data sent.

[2458] output

[2459] Results of analyzed emotional states.

[2460] Step 19:

[2461] Request a personalized plan

[2462] Specific actions

[2463] Based on the analysis results of the emotion engine, the generative AI model can then generate more personalized training plans and nutritional advice, for example, generating prompts like:

[2464] "The user is under stress, please suggest some relaxation exercises."

[2465] input

[2466] Results of analyzed emotional states.

[2467] The generated prompt statement.

[2468] output

[2469] Request a generative AI model with a prompt to generate a personalized plan.

[2470] Step 20:

[2471] Return and view your personalized plan

[2472] Specific actions

[2473] The generated training plan and nutrition advice are sent from the server to the user terminal.

[2474] Users can obtain appropriate information at the right time on their devices and take action.

[2475] input

[2476] A personalized plan received from a generative AI model.

[2477] output

[2478] A personalized plan displayed on your device.

[2479] (Application example 2)

[2480] 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."

[2481] Modern autonomous vehicles face a lack of means to manage the health and mental health of their users while driving. As autonomous vehicles become more widespread, there is a demand for ways to make effective use of their driving time. However, current systems have difficulty providing personalized training plans and nutritional advice that reflect the user's individual needs and emotional state. This means that users are unable to make full use of their time while driving, making it difficult to manage stress and effectively manage their health.

[2482] The specific processing by the specific 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 means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the user's emotional state using an emotion engine, means for adjusting the training plan based on the analyzed emotional state, and means for displaying the plan on a head-mounted display. This enables users to receive personalized training plans and nutritional advice in real time that are tailored to their individual needs and emotional state, even while in an autonomous vehicle.

[2483] The "means for accepting user requests" is a method for providing an interface for accepting requests sent by users.

[2484] The "means for obtaining user information from a database" is a method for reading stored user profile information from a database.

[2485] "Means for automatically generating training plans using generative AI" refers to a method for automatically generating training plans based on a user's health status and goals using a machine learning model.

[2486] The "means for transmitting the generated training plan to the user terminal" is a method for transferring the generated training plan to the user's device.

[2487] The "means for analyzing a user's emotional state using an emotion engine" is a method for interpreting a user's emotional data using emotion recognition technology to identify the user's current emotional state.

[2488] The "means for adjusting a training plan based on the analyzed emotional state" is a method for using the results from the emotion engine to adapt a training plan to a user.

[2489] The "means for displaying a plan on a head-mounted display" is a method for displaying the generated training plan and nutrition advice on a head-mounted display.

[2490] "Means for automatically generating nutritional advice using generative AI" refers to a method that uses machine learning models to automatically generate nutritional advice based on a user's goals and health status.

[2491] "Means of receiving user progress information and automatically generating feedback using AI" refers to a method of receiving progress data provided by the user and generating feedback using a machine learning model based on that data.

[2492] The present invention is a method for providing users with personalized training plans and nutritional advice within an autonomous vehicle using a system that combines a generative AI model and an emotion engine. This system is realized by the following specific components and procedures.

[2493] 1. A means of accepting user requests

[2494] The server accepts requests sent by the user through the head-mounted display, including requests for training plans and nutritional advice.

[2495] 2. A way to retrieve user information from the database

[2496] Based on the received request, the server retrieves user profile information from a database, including the user's age, gender, exercise experience, and health status.

[2497] 3. A means to automatically generate training plans using generative AI

[2498] The server automatically generates a training plan based on the acquired user information using a generative AI model, which uses machine learning algorithms to create an optimal exercise plan for the user.

[2499] 4. Means for sending the generated training plan to the user device

[2500] The server sends the generated training plan to the head-mounted display so that the user can visually check it.

[2501] 5. A method for analyzing the user's emotional state using an emotion engine

[2502] The server collects emotion data provided by the user through the head-mounted display and analyzes it with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state.

[2503] 6. A way to adjust your training plan based on your analyzed emotional state

[2504] The server then uses the emotional state analysis results from the emotion engine to adjust training plans and nutrition advice accordingly, for example adding relaxation exercises if the user is feeling stressed.

[2505] 7. A method for displaying plans on a head-mounted display

[2506] The server then displays tailored training plans and nutrition advice on the head-mounted display, allowing users to receive appropriate feedback in real time.

[2507] Hardware and software used

[2508] Hardware: Head-mounted display, server, database

[2509] Software: Flask, generative AI libraries, emotion engine libraries, database modules

[2510] Specific examples

[2511] 1. While wearing the HMD, the user clicks the "Request a training plan" button.

[2512] Example prompt: "User requests a new training plan. User ID is 12345."

[2513] 2. While wearing the HMD, the user clicks the "Request nutrition advice" button.

[2514] Example prompt: "User requests new nutrition advice. User ID is 12345."

[2515] 3. Input emotional state while the user is wearing the HMD

[2516] Sample prompt: "We have collected the user's emotional data and determined that they are feeling stressed. The emotion engine will generate stress relief advice."

[2517] The system will monitor the user's health and mental state even while in an autonomous vehicle, and provide individually optimized training plans and nutritional advice, thereby improving the user's quality of life.

[2518] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2519] Step 1:

[2520] The server accepts user requests through the head-mounted display, typically requests for training plans or nutrition advice. The input is the request data, and the output is a confirmation that the request was received.

[2521] Step 2:

[2522] The server retrieves user information from a database based on the received request. It uses a database query to collect profile information such as the user's age, gender, exercise experience, and health status. The input is the user ID, and the output is the retrieved user information.

[2523] Step 3:

[2524] The server automatically generates a training plan using a generative AI model based on the acquired user information. The generative AI model runs a trained machine learning algorithm to create a training plan optimized for the user. This generates the contents of the plan. The input is user information, and the output is the generated training plan.

[2525] Step 4:

[2526] The server sends the generated training plan to the user's head-mounted display and displays it, allowing the user to check the training plan in real time. The input is the training plan, and the output is the displayed training plan.

[2527] Step 5:

[2528] The user inputs emotional data through the head-mounted display. For example, data such as facial expressions and heart rate are collected using sensors and cameras built into the head-mounted display. The input is emotional data, and the output is data sent to the server.

[2529] Step 6:

[2530] The server analyzes the collected emotional data with an emotion engine, which uses emotion recognition technology to identify the user's current emotional state. The input is the collected emotional data, and the output is the analyzed emotional state.

[2531] Step 7:

[2532] The server then adjusts the training plan and nutrition advice appropriately based on the emotional state obtained from the emotion engine. For example, if the user is feeling stressed, it suggests relaxation exercises to address that stress. The input is the analyzed emotional state, and the output is the adjusted training plan and nutrition advice.

[2533] Step 8:

[2534] The server sends the adjusted training plan and nutrition advice to the head-mounted display for the user to review in real time. The input is the adjusted plan and advice, and the output is the displayed content.

[2535] Through these steps, users can receive individually optimized training plans and nutritional advice in real time while in an autonomous vehicle, enabling them to efficiently manage their health.

[2536] 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.

[2537] 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.

[2538] 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.

[2539] [Fourth embodiment]

[2540] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2541] 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.

[2542] 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).

[2543] 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.

[2544] 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.

[2545] 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).

[2546] 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.

[2547] 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.

[2548] 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.

[2549] 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.

[2550] 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.

[2551] 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.

[2552] 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."

[2553] This invention is a method for utilizing generative AI models to realize a system that provides sports science knowledge. Below, we will explain the important components of the system and their specific operations.

[2554] User Registration

[2555] 1. User Device:

[2556] The user installs the app and enters the required information on the new registration screen, including their name, email address, and password.

[2557] When the registration button is clicked, the form data is sent to the server in JSON format.

[2558] 2. Server:

[2559] The server receives the request and performs validation of the information entered, for example checking that the email address is formatted correctly or that the password is strong.

[2560] If validation is successful, the user information is saved in the database, a success response is sent back to the user's device, and a message indicating successful registration is displayed to the user.

[2561] Providing training plans

[2562] 1. User Device:

[2563] The user clicks the request a training plan button within the app.

[2564] The request is sent to the server in JSON format.

[2565] 2. Server:

[2566] The server receives the request and retrieves the profile information of the user from the database.

[2567] Based on the acquired user information, a generative AI model (e.g., ChatGPT) is asked to generate a training plan.

[2568] The generation AI generates a customized training plan, which the server then sends back to the user's device.

[2569] 3. User Device:

[2570] The user terminal displays the received training plan information on the screen, providing details such as "chest training" on Monday and "aerobic exercise" on Tuesday.

[2571] Providing nutritional advice

[2572] 1. User Device:

[2573] The user clicks the "Request Nutritional Advice" button.

[2574] The request is sent to the server in JSON format.

[2575] 2. Server:

[2576] The server receives the request and retrieves the nutrition-related information for the user from the database.

[2577] Based on the acquired user information and request content, the generative AI model is asked to generate nutritional advice.

[2578] The generation AI generates customized nutrition advice, and the server sends the advice back to the user's device.

[2579] 3. User Device:

[2580] The user terminal displays the received nutrition advice information on the screen and provides specific advice such as "eat a high-protein meal for breakfast."

[2581] Progress management and feedback

[2582] 1. User Device:

[2583] Users enter their exercise and diet progress information into the app.

[2584] 2. Server:

[2585] The server stores the progress data in a database and generates feedback using a generative AI model.

[2586] The generated feedback is sent to the user's device, providing the user with progress-based evaluations and suggestions for improvement.

[2587] Specific examples

[2588] Example 1: Retrieving a training plan

[2589] 1. User Device:

[2590] User A clicks the button to request a training plan.

[2591] The request is sent to the server in JSON format.

[2592] 2. Server:

[2593] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[2594] The training plan received from the generation AI is sent back to the user's device.

[2595] 3. User Device:

[2596] User A checks the received training plan on the screen and exercises based on the plan.

[2597] Example 2: Getting nutrition advice

[2598] 1. User Device:

[2599] User B clicks the button to request nutrition advice.

[2600] The request is sent to the server in JSON format.

[2601] 2. Server:

[2602] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[2603] The nutritional advice received from the generating AI is sent back to the user's device.

[2604] 3. User Device:

[2605] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[2606] As described above, this system uses generative AI to provide personalized training plans and nutritional advice based on user requests, thereby realizing efficient and high-quality services for a large number of users.

[2607] The processing flow will be explained below.

[2608] Handling user registration

[2609] Step 1:

[2610] User device: The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[2611] Step 2:

[2612] User device: When the registration button is clicked, the form data is sent to the server in JSON format.

[2613] Step 3:

[2614] Server: Receives the request and validates the entered information, specifically checking the format of the email address and the strength of the password.

[2615] Step 4:

[2616] Server: If validation is successful, save the user information to the database.

[2617] Step 5:

[2618] Server: Sends a success response to the user terminal, and the user terminal displays a message indicating successful registration.

[2619] Providing training plans

[2620] Step 1:

[2621] User device: The user clicks the training plan request button within the app.

[2622] Step 2:

[2623] User terminal: The request is sent to the server in JSON format.

[2624] Step 3:

[2625] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[2626] Step 4:

[2627] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[2628] Step 5:

[2629] Server: Returns the training plan received from the generation AI to the user device.

[2630] Step 6:

[2631] User device: Displays the received training plan information on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[2632] Providing nutritional advice

[2633] Step 1:

[2634] User terminal: The user clicks on the "Request nutrition advice" button.

[2635] Step 2:

[2636] User terminal: The request is sent to the server in JSON format.

[2637] Step 3:

[2638] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[2639] Step 4:

[2640] Server: Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice. The generative AI model takes into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[2641] Step 5:

[2642] Server: Returns the nutrition advice received from the generation AI to the user's device.

[2643] Step 6:

[2644] User device: The received nutrition advice information is displayed on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[2645] Progress management and feedback

[2646] Step 1:

[2647] User device: The user enters exercise and diet progress information into the app.

[2648] Step 2:

[2649] Server: Receives progress data and stores it in a database.

[2650] Step 3:

[2651] Server: Based on the progress data, the server requests the generative AI model to generate feedback. The generative AI model evaluates the user's progress and provides suggestions for improvement and next steps.

[2652] Step 4:

[2653] Server: Returns the feedback received from the generation AI to the user device.

[2654] Step 5:

[2655] User device: The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[2656] Through the above processing flow, the system can provide users with personalized training plans and nutritional advice, and can also provide progress management and feedback functions, realizing an efficient and high-quality service.

[2657] Example 1

[2658] 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."

[2659] Traditional methods have not made it easy for users to quickly and efficiently obtain personalized training plans and nutritional advice. It has also been difficult to monitor users' progress in real time and provide appropriate feedback. Therefore, there has been a need for a system that can help users achieve their health and fitness goals.

[2660] 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.

[2661] In this invention, the server includes: means for transmitting form data in JSON format to the server when a user enters necessary information on a new registration screen and clicks the registration button; means for the server to receive the request, validate the entered information, and, if successful, store the user information in a database and return a success response to the user terminal; means for transmitting a request in JSON format to the server when the user terminal clicks a training plan request button; means for the server to receive the request, retrieve the user's profile information from the database, and request the generation AI model to generate a training plan; and means for returning the generated training plan to the user terminal and displaying the training plan received by the user terminal on the screen. This allows users to quickly and efficiently obtain personalized training plans and nutritional advice, and also enables progress management in real time.

[2662] A "user terminal" is an electronic device used by a user to input information and communicate with the system.

[2663] A "server" is a centralized computer system that receives requests from user devices, validates information, and interacts with databases.

[2664] "JSON format" stands for JavaScript Object Notation and is a standard format for representing data in an organized text format.

[2665] A "database" is a system that stores information in a structured format and allows it to be searched and updated later.

[2666] A "generative AI model" is an algorithm or software that uses artificial intelligence technology to generate information, such as a model that automatically generates training plans or nutritional advice.

[2667] "Validation" is the process of checking whether the entered information is in the correct format or meets certain conditions.

[2668] "Feedback" is information, including evaluations and suggestions for improvement, that the system provides based on the user's progress.

[2669] "Profile information" is information about the attributes and status of each user, including, for example, age, height, weight, and fitness level.

[2670] A "training plan" is an exercise program created by a generative AI model to achieve a user's fitness goals.

[2671] "Nutrition advice" refers to advice and suggestions about a user's diet, which are customized and generated by a generative AI model.

[2672] The present invention is a system that uses generative AI models to provide users with sports science-based training plans and nutrition advice. Specific embodiments of the present invention are described in detail below.

[2673] User Registration

[2674] First, in order for a user to use the system, they must register using their device. The user installs the app and enters information such as their name, email address, and password on the registration screen. Once the user has completed the entry and clicked the registration button, the entered information is sent to the server in JSON format.

[2675] The server receives the request sent from the user terminal and validates the input information. For example, it checks whether the email address format is correct and whether the password is strong. If validation is successful, the user information is saved in the database and a response indicating successful registration is sent back to the user terminal. The user terminal receives this response and displays a message indicating successful registration on its screen.

[2676] Providing training plans

[2677] To request a training plan, a user clicks on the training plan request button in the app. This request is sent to the server in JSON format. After receiving the request, the server retrieves the user's profile information from the database.

[2678] Next, a prompt is generated and sent to the generative AI model (e.g., ChatGPT). The prompt includes information such as the user's age, height, weight, and fitness level. Based on the generated prompt, the generative AI model generates a customized training plan. The server receives the generated training plan and sends it to the user's device. The user's device receives this information and displays details such as "chest training" on Mondays and "aerobic exercise" on Tuesdays.

[2679] Providing nutritional advice

[2680] When a user requests nutrition advice, they click the "Request Nutrition Advice" button in the app. The request is sent to the server in JSON format. After receiving the request, the server retrieves the user's nutrition-related information from the database.

[2681] Based on the acquired nutritional information, the server sends prompts to the generative AI model, asking it to generate customized nutritional advice. The generated nutritional advice is sent to the user's device via the server, and the user's device displays this information on the screen. For example, specific advice such as "Eat a high-protein meal for breakfast" is provided.

[2682] Progress management and feedback

[2683] Users enter their exercise and diet progress information into the app. The server receives and stores this progress information and requests the generative AI model to generate feedback. The generated feedback is sent from the server to the user's device, and the user is given an evaluation and suggestions for improvement based on their progress.

[2684] Examples of concrete examples and prompts

[2685] Example 1: Obtaining a training plan

[2686] When User A clicks the button to request a training plan, the request is sent in JSON format to the server. The server obtains the user's profile information and asks the generation AI to generate a training plan. The generated training plan is sent back to the user's device, and User A checks the received plan and performs the exercise.

[2687] Example 2: Getting nutrition advice

[2688] When User B clicks the button to request nutrition advice, the request is sent in JSON format to the server. The server obtains the user's nutrition-related information and asks the AI ​​to generate advice. The generated nutrition advice is sent back to the user's device, where User B can review the advice and plan their meals.

[2689] Prompt Sentence Examples

[2690] "Generate a training plan. Your profile information is as follows: age 30, height 175cm, weight 70kg, and fitness level intermediate."

[2691] "Generate nutrition advice. User's nutritional information is: vegan, goal weight 65kg, current weight 70kg."

[2692] As described above, the present invention uses generative AI models to provide users with personalized training plans and nutritional advice, and provides progress management and feedback, thereby achieving efficient and high-quality services.

[2693] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2694] Step 1: Enter user registration information

[2695] User device:

[2696] Input: User information such as name, email address, and password.

[2697] How it works: The user installs the app and enters the required information on the new registration screen.

[2698] Output: When the registration button is clicked, the entered information is sent to the server as JSON format data.

[2699] Step 2: Information validation and storage

[2700] server:

[2701] Input: JSON format user information sent from the user device.

[2702] What it does: The server receives the request, checks that the email address is valid and the password is strong, and if validation is successful, stores the user information in the database.

[2703] Output: Generates a response indicating successful registration and sends it to the user's device. If any information is inaccurate, generates and returns an error message.

[2704] Step 3: Viewing registration results

[2705] User device:

[2706] Input: Registration success or error message sent by the server.

[2707] Operation: The user terminal displays the received message on the screen.

[2708] Output: Registration success message or error message.

[2709] Step 4: Submit a training plan request

[2710] User device:

[2711] Enter: Click on Training Plan Request.

[2712] What happens: A user clicks the in-app training plan request button.

[2713] Output: The request is sent to the server as JSON data.

[2714] Step 5: Obtain user information

[2715] server:

[2716] Input: Training plan request sent from user device.

[2717] How it works: The server receives the request and retrieves the user's profile information (age, height, weight, fitness level, etc.) from the database.

[2718] Output: The retrieved profile information.

[2719] Step 6: Prompt generation and AI requests

[2720] server:

[2721] Input: User profile information.

[2722] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate a training plan.

[2723] Output: The generated training plan.

[2724] Step 7: Submit your training plan

[2725] server:

[2726] Input: The training plan received from the generative AI model.

[2727] Operation: The server transmits the generated training plan to the user terminal.

[2728] Output: The training plan sent to the user device.

[2729] Step 8: View your training plan

[2730] User device:

[2731] Input: The training plan sent by the server.

[2732] How it works: The user device displays the received training plan on the screen, providing details such as "chest workout" on Monday and "cardio" on Tuesday.

[2733] Output: Training plan displayed on the screen.

[2734] Step 9: Submit a nutrition advice request

[2735] User device:

[2736] Enter: Click on Request Nutritional Advice.

[2737] What happens: A user clicks the "Request Nutrition Advice" button in the app.

[2738] Output: The request is sent to the server as JSON data.

[2739] Step 10: Obtaining user nutrition information

[2740] server:

[2741] Input: A nutrition advice request sent from a user device.

[2742] How it works: The server receives the request and retrieves the user's nutrition-related information (such as dietary preferences and allergy information) from the database.

[2743] Output: Retrieved nutrition-related information.

[2744] Step 11: Prompt generation and AI request (nutritional advice)

[2745] server:

[2746] Input: User nutrition related information.

[2747] Operation: The server generates a prompt sentence to send to the generative AI model, and sends it to the generative AI model, requesting it to generate nutritional advice.

[2748] Output: The generated nutrition advice.

[2749] Step 12: Send nutrition advice

[2750] server:

[2751] Input: Nutrition advice received from a generative AI model.

[2752] Operation: The server transmits the generated nutrition advice to the user terminal.

[2753] Output: Nutrition advice sent to the user device.

[2754] Step 13: View nutrition advice

[2755] User device:

[2756] Input: Nutrition advice sent from the server.

[2757] Operation: The user device displays the received nutrition advice on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[2758] Output: Nutrition advice displayed on the screen.

[2759] Step 14: Enter progress information

[2760] User device:

[2761] Input: Exercise and diet progress information.

[2762] How it works: Users enter exercise and diet progress information into the app.

[2763] Output: The entered progress information is sent to the server in JSON format.

[2764] Step 15: Save progress information and request AI

[2765] server:

[2766] Input: Progress information sent from the user's device.

[2767] How it works: The server stores progress information in a database and asks the generative AI model to generate feedback based on the stored progress data.

[2768] Output: The generated feedback.

[2769] Step 16: Send feedback

[2770] server:

[2771] Input: Feedback received from the generative AI model.

[2772] Operation: The server sends the generated feedback to the user terminal.

[2773] Output: Feedback sent to the user device.

[2774] Step 17: Viewing feedback

[2775] User device:

[2776] Input: Feedback sent by the server.

[2777] How it works: The user device displays the received feedback on its screen, providing the user with a rating and suggestions for improvement based on their progress.

[2778] Output: Feedback displayed on the screen.

[2779] (Application example 1)

[2780] 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."

[2781] In today's advanced information society, various security threats exist on a daily basis, requiring rapid and appropriate responses to these threats. At the same time, there is a growing demand for personalized training plans and nutritional advice that utilize knowledge of sports science. However, there is a lack of mechanisms to efficiently provide these to individual users. Furthermore, it is difficult to utilize wearable devices such as smart glasses to perform real-time situation analysis and present appropriate defensive measures. Given this background, there is a need for a system that can provide personalized training plans and nutritional advice while also effectively providing security support through devices such as smart glasses.

[2782] 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.

[2783] In this invention, the server includes means for accepting a user request, means for acquiring user information from a database, means for automatically generating a training plan using a generation AI, means for transmitting the generated training plan to a user terminal, means for analyzing the situation based on data acquired from sensors, and means for providing defensive measures according to the situation using the generation AI. This makes it possible to provide the user with a personalized training plan and nutritional advice, while also providing real-time security support through the wearable device.

[2784] "User" refers to an individual or corporation that uses this system, and whose information is registered in the database.

[2785] The "means for accepting a request" is an interface for receiving a request from a user in an input format and transmitting it to a server.

[2786] A "database" is a system for storing user information and related data, and for searching and retrieving them as needed.

[2787] "User information" refers to various data required by the system, such as a user's personal information, profile data, and activity history.

[2788] "Generative AI" is a technology that uses machine learning models trained on large datasets to generate training plans, nutritional advice, and situational defensive strategies based on user requests.

[2789] A "training plan" is an exercise program automatically created by the generation AI based on the user's health condition and goals.

[2790] "Nutrition advice" refers to dietary suggestions provided by the generative AI based on the user's diet and health status.

[2791] A "user terminal" is a device (e.g., a smartphone, smart glasses, head-mounted display, etc.) that a user uses to access the system.

[2792] A "sensor" is a device for detecting environmental information and user activity, and includes a camera, microphone, GPS, etc.

[2793] "Situation analysis" is the process of assessing the current environment and the user's situation based on data obtained from sensors.

[2794] "Defensive measures" are guidelines and countermeasures provided by the generative AI based on situational analysis to ensure the user's safety.

[2795] "Progress information" is data related to training plans and nutrition advice, such as records of exercise and meals a user has completed.

[2796] "Feedback" refers to evaluations and suggestions for improvement provided by the generating AI based on the user's progress information.

[2797] The present invention is a system that utilizes generative AI models to provide users with personalized training plans, nutritional advice, and security support. The specific operation of the system is described below.

[2798] 1. User Registration

[2799] User device:

[2800] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The form data is sent to the server in JSON format.

[2801] server:

[2802] The server receives the request, validates the entered information, and if successful, stores the user information in a database and returns a message to the user terminal indicating successful registration.

[2803] 2. Providing training plans

[2804] User device:

[2805] The user clicks the training plan request button and the request is sent to the server in JSON format.

[2806] server:

[2807] The server receives the request, retrieves the user's profile information from the database, and requests the generation AI to generate a training plan. The generated training plan is then sent back to the user's device.

[2808] User device:

[2809] The user displays the received training plan on the screen and performs exercise based on the plan's contents.

[2810] 3. Providing nutritional advice

[2811] User device:

[2812] The user clicks the request nutrition advice button and the request is sent in JSON format to the server.

[2813] server:

[2814] The server receives the request, retrieves the user's nutrition-related information from the database, and requests the AI ​​to generate advice. The generated nutrition advice is then sent back to the user's device.

[2815] User device:

[2816] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[2817] 4. Security Support

[2818] User device (smart glasses):

[2819] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings and send the data in JSON format to a server.

[2820] server:

[2821] The server receives and analyzes the data sent from the sensors and performs situation analysis. Based on the analysis results, the generative AI provides appropriate defensive measures.

[2822] User device:

[2823] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[2824] 5. Progress Management and Feedback

[2825] User device:

[2826] Users enter their exercise and diet progress information into the app.

[2827] server:

[2828] The server stores the progress data in a database, and the AI ​​generates feedback based on the progress. The generated feedback is sent to the user's device and displayed on the screen.

[2829] Hardware and Software Use

[2830] Hardware:

[2831] Smart glasses (e.g., Google Glass, Microsoft HoloLens)

[2832] Built-in sensors (camera, microphone, GPS)

[2833] software:

[2834] Web server (e.g. Python Flask, Django)

[2835] Database (e.g. MySQL, PostgreSQL)

[2836] Generative AI models (e.g. ChatGPT)

[2837] Specific examples

[2838] Get your training plan

[2839] 1. User Device:

[2840] User A clicks the button to request a training plan, and the request is sent to the server in JSON format.

[2841] 2. Server:

[2842] The server acquires the user's profile information and requests the AI ​​to generate a training plan. The AI ​​then returns the training plan to the user's device.

[2843] 3. User Device:

[2844] User A checks the received training plan on the screen and exercises based on the plan.

[2845] Prompt Sentence Examples

[2846] 1. Training plan generation prompt:

[2847] Current Situation: User A is looking to improve his muscle strength.

[2848] Q: Create a training plan for the week.

[2849] 2. Nutrition advice generation prompts:

[2850] Current Situation: User B is trying to lose weight.

[2851] Q: What is your daily meal plan?

[2852] 3. Situation Analysis Prompt:

[2853] Current situation: Unknown people are approaching you.

[2854] Information: It's 8pm and the location is on a deserted street.

[2855] Question: How can I stay safe?

[2856] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2857] Step 1:

[2858] User Registration

[2859] User device:

[2860] The user installs the app, enters their name, email address, and password on the new registration screen, and clicks the Register button. The input data (name, email address, and password) is sent to the server in JSON format.

[2861] server:

[2862] The server receives the request and validates the input data. If validation is successful, the user information is saved in the database. A success response (registration successful message) is sent back to the user device.

[2863] Step 2:

[2864] Providing training plans

[2865] User device:

[2866] The user clicks the training plan request button, and the request (user ID and desired content data) is sent to the server in JSON format.

[2867] server:

[2868] The server receives the request and retrieves the user's profile information from the database. Based on the retrieved information, it asks the generation AI to generate a training plan. The generation AI generates the training plan and returns the data to the server. The server then returns the generated training plan data to the user's device.

[2869] User device:

[2870] The user displays the received training plan on the screen and performs exercise based on the plan.

[2871] Step 3:

[2872] Providing nutritional advice

[2873] User device:

[2874] The user clicks the request button for nutrition advice, and the request (user ID and desired content data) is sent to the server in JSON format.

[2875] server:

[2876] The server receives the request and retrieves the user's nutrition-related information from the database. Based on the retrieved information, it asks the generation AI to generate nutrition advice. The generation AI generates the nutrition advice and returns the data to the server. The server then returns the generated nutrition advice data to the user's device.

[2877] User device:

[2878] The user displays the received nutrition advice on the screen and plans their meals according to the instructions.

[2879] Step 4:

[2880] Security Assistance

[2881] User device (smart glasses):

[2882] The smart glasses' sensors (camera, microphone, GPS) collect information about the surroundings, and the collected data (environmental information, location information, etc.) is sent to the server in JSON format.

[2883] server:

[2884] The server receives data sent from the sensors and analyzes the situation. It processes the data (normalizes location information, analyzes audio data, analyzes image data, etc.) and passes the analysis results to the generation AI. The generation AI generates defensive measures according to the situation and returns the data to the server. The server then returns the generated defensive measures data to the user device.

[2885] User device:

[2886] The user can view the generated defense measures on the smart glasses display and take appropriate action.

[2887] Step 5:

[2888] Progress management and feedback

[2889] User device:

[2890] Users input their exercise and diet progress information into the app. The input data (exercise status, diet details, etc.) is sent to the server in JSON format.

[2891] server:

[2892] The server stores the progress data in a database and requests the generation AI to generate feedback based on the progress information. The generation AI generates the feedback and returns the data to the server. The server then sends the generated feedback data back to the user's device.

[2893] User device:

[2894] Users can check the feedback they receive on screen and use it to guide their next actions.

[2895] 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.

[2896] This invention is a method for realizing a sports science knowledge provision system that utilizes a generative AI model and combines it with a user emotion engine. Below, we will explain the important components of the system and their specific operation.

[2897] User Registration

[2898] 1. User Device

[2899] The user installs the app and enters the required information such as name, email address, and password on the new registration screen.

[2900] When you click the register button, the form data is sent to the server in JSON format.

[2901] 2. Server

[2902] The server receives the request and performs validation of the information entered, such as checking the format of the email address and the strength of the password.

[2903] If validation is successful, save the user information to the database.

[2904] 3. Server

[2905] A success response is sent to the user terminal, and the user terminal displays a message indicating successful registration.

[2906] Providing training plans

[2907] 1. User Device

[2908] The user clicks the request a training plan button within the app.

[2909] The request is sent to the server in JSON format.

[2910] 2. Server

[2911] The server receives the request and retrieves the profile information of the user from the database.

[2912] Based on the acquired user information, the generative AI model is asked to generate a training plan, which takes into account the user's age, gender, exercise experience, etc. to generate a customized plan.

[2913] 3. Server

[2914] The training plan received from the generation AI is sent back to the user's device.

[2915] 4. User Device

[2916] The received training plan information is displayed on the screen. The plan may include details such as "chest training" on Monday and "cardio" on Tuesday.

[2917] Providing nutritional advice

[2918] 1. User Device

[2919] The user clicks the "Request Nutritional Advice" button.

[2920] The request is sent to the server in JSON format.

[2921] 2. Server

[2922] The server receives the request and retrieves the nutrition-related information for the user from the database.

[2923] Based on the acquired user information and the request, the generative AI model is asked to generate nutritional advice, taking into account the user's health status and goals (e.g., weight loss, muscle building, etc.).

[2924] 3. Server

[2925] The nutritional advice received from the generating AI is sent back to the user's device.

[2926] 4. User Device

[2927] The received nutrition advice information is displayed on the screen, providing specific advice such as "Eat a high-protein meal for breakfast."

[2928] Progress management and feedback

[2929] 1. User Device

[2930] Users enter their exercise and diet progress information into the app.

[2931] 2. Server

[2932] Receives progress data and stores it in a database.

[2933] 3. Server

[2934] Based on the progress data, the generative AI model is asked to generate feedback, which evaluates the user's progress and provides suggestions for improvement and next steps.

[2935] 4. Server

[2936] The feedback received from the generation AI is sent back to the user's device.

[2937] 5. User Device

[2938] The received feedback information is displayed on the screen, and the user can make adjustments for further improvement.

[2939] Incorporating an emotion engine

[2940] 1. User Device

[2941] Users can input their emotional state during training or in daily life, or their emotional state is automatically recorded using voice and image recognition technology.

[2942] 2. Server

[2943] The emotion engine analyzes the collected emotion data to identify the user's emotional state.

[2944] 3. Server

[2945] Based on the analysis results from the emotion engine, the generative AI model can further personalize training plans and nutrition advice, for example suggesting relaxation exercises if the user is under stress.

[2946] 4. Server

[2947] The generated training plan and nutrition advice are sent to the user's terminal, allowing the user to obtain appropriate information at the appropriate time.

[2948] Specific examples

[2949] Example 1: Retrieving a training plan

[2950] 1. User Device

[2951] User A clicks the button to request a training plan.

[2952] The request is sent to the server in JSON format.

[2953] 2. Server

[2954] The server obtains the profile information of the relevant user and asks the generation AI to generate a training plan.

[2955] The training plan received from the generation AI is sent back to the user's device.

[2956] 3. User Device

[2957] User A checks the received training plan on the screen and exercises based on the plan.

[2958] Example 2: Getting nutrition advice

[2959] 1. User Device

[2960] User B clicks the button to request nutrition advice.

[2961] The request is sent to the server in JSON format.

[2962] 2. Server

[2963] The server obtains the nutrition-related information of the user and asks the generation AI to generate advice.

[2964] The nutritional advice received from the generating AI is sent back to the user's device.

[2965] 3. User Device

[2966] User B checks the received nutrition advice on the screen and plans a meal based on the advice.

[2967] Example 3: Using the Emotion Engine

[2968] 1. User Device

[2969] User C inputs his emotional state.

[2970] The data is sent to the server through the emotion engine.

[2971] 2. Server

[2972] The emotion engine analyzes the emotion data and provides the results to the generative AI.

[2973] Generative AI takes emotional state into account to generate training plans and nutritional advice.

[2974] 3. User Device

[2975] User C reviews the personalized training plan and nutrition advice he or she receives on the screen and acts accordingly.

[2976] As described above, by incorporating an emotion engine, this system provides more personalized training plans and nutritional advice that reflect the user's emotional state, enabling users to effectively manage their fitness and nutritional needs while taking their emotional state into account.

[2977] The processing flow will be explained below.

[2978] Providing training plans incorporating an emotion engine (example)

[2979] Step 1:

[2980] User device: The user clicks the training plan request button within the app.

[2981] Step 2:

[2982] User terminal: The request is sent to the server in JSON format.

[2983] Step 3:

[2984] Server: Receives the request and retrieves the profile information of the corresponding user from the database.

[2985] sql

[2986] SELECT FROM users WHERE user_id = 'user_a_id';

[2987] Step 4:

[2988] Server: Based on the acquired user information, the server requests the generative AI model to generate a training plan. The generative AI model generates a customized plan taking into account the user's age, gender, exercise experience, etc.

[2989] Step 5:

[2990] Server: Temporarily stores the training plan received from the generation AI.

[2991] Step 6:

[2992] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[2993] json

[2994] {

[2995] "action": "get_emotion",

[2996] "user_id": "user_a_id"

[2997] }

[2998] Step 7:

[2999] Server: Receives the user's emotional state from the emotion engine.

[3000] Step 8:

[3001] Emotion Engine: Analyzes emotional data and makes appropriate adjustments to the training plan if the user is feeling stressed.

[3002] Step 9:

[3003] Server: Sends the adjusted training plan to the user device.

[3004] Step 10:

[3005] User terminal: Displays the received training plan information on the screen.

[3006] Providing nutrition advice using an emotion engine (example)

[3007] Step 1:

[3008] User terminal: The user clicks on the "Request nutrition advice" button.

[3009] Step 2:

[3010] User terminal: The request is sent to the server in JSON format.

[3011] Step 3:

[3012] Server: Receives the request and retrieves the nutrition-related information for the user from the database.

[3013] sql

[3014] SELECT FROM users WHERE user_id = 'user_b_id';

[3015] Step 4:

[3016] Server: Based on the acquired user information and request, the generative AI model is asked to generate nutrition advice. The generative AI model takes into account the user's health status and goals.

[3017] Step 5:

[3018] Server: Temporarily stores nutrition advice received from the generation AI.

[3019] Step 6:

[3020] Server: Sends a request to the emotion engine to ascertain the user's emotional state.

[3021] json

[3022] {

[3023] "action": "get_emotion",

[3024] "user_id": "user_b_id"

[3025] }

[3026] Step 7:

[3027] Server: Receives the user's emotional state from the emotion eng...

Claims

1. means for accepting user requests; a means for retrieving user information from a database; A means for automatically generating training plans using generative AI; means for transmitting the generated training plan to a user terminal; A system including:

2. The system of claim 1 , further comprising means for automatically generating nutrition advice using a generation AI.

3. The system of claim 1 , further comprising means for receiving user progress information and automatically generating feedback using a generation AI.

Images