System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting body type information of a user; means for generating body type data using an image analysis technique based on the body type information; means for inputting target information of the user; means for generating an optimal training menu using a generative artificial intelligence model based on the body type data and the target information; means for providing the training menu to a user terminal; means for inputting a training progress of the user; and means for generating and providing a new training menu based on the progress.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] In modern society, with health consciousness on the rise, many people are training to maintain their physique and health. However, there are many people who find it difficult to regularly visit a fitness gym, or who are unable to continue training because they do not understand the correct training methods. Furthermore, since the COVID-19 pandemic, people have become reluctant to go to the gym, making it even more difficult to continue training. In response to this situation, there is a demand for a system that can easily provide training menus tailored to each individual and enable users to efficiently train at home. [Means for solving the problem]

[0005] The present invention provides a system that automatically generates an optimal training menu using a generative AI model based on a user's physique information and goal information, and provides the menu to the user's terminal. Specifically, the system includes the following means.

[0006] 1. Means for inputting user's body shape information

[0007] 2. Means for generating body shape data using image analysis technology based on the body shape information

[0008] 3. Means for inputting user goal information

[0009] 4. Means for generating an optimal training menu using a generative artificial intelligence model based on the body type data and goal information.

[0010] 5. Means for providing the training menu to a user terminal

[0011] 6. Means for inputting user training progress

[0012] 7. Means for generating and providing a new training menu based on the progress

[0013] In addition, by including a means for sending push notifications to encourage users to continue training, and a means for using image data as the user's body shape information and estimating body fat percentage and muscle mass using the image analysis technology, a system is realized that allows users to train continuously and maximize the effects of their training.

[0014] "User's body type information" is information that indicates the user's physical characteristics, and specifically includes image data that indicates weight, height, age, sex, and body type.

[0015] "Goal information" is information indicating the physical goal that the user wants to achieve, and specifically includes the target weight, the target body shape, and the like.

[0016] A "generative AI model" is a model that uses machine learning and artificial intelligence to analyze and predict data, and in particular generates optimal training menus based on the user's body type and goal information.

[0017] A "training menu" is a plan that combines exercises such as strength training and aerobic exercise, and is customized according to the user's body type and goals.

[0018] "Image analysis technology" is a technology that processes image data and extracts or identifies specific information, and is specifically used to analyze a user's body shape data.

[0019] "Push notifications" are a technology that allows a device to display notifications to a user, and are used to send users training reminders and motivational messages.

[0020] A "user device" is an electronic device such as a smartphone or tablet that allows users to check training menus and enter progress through an application.

[0021] "Progress data" is information showing the records and results of the user's training, and specifically includes the date of training, completed training items, changes in weight, and the like. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] This invention is a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information. Specific embodiments of this system will be described below.

[0044] System Overview

[0045] This system is used by users through an application and mainly provides the following functions.

[0046] 1. Enter and submit your body type and goal information

[0047] 2. Generating body shape data using image analysis technology

[0048] 3. Generating and providing optimal training menus using generative AI models

[0049] 4. Monitoring training progress and creating and providing new training menus

[0050] 5. Send push notifications to encourage continued training

[0051] Program processing

[0052] The system's programs operate through the exchange of information between the server, terminals, and users.

[0053] 1. User information entry and submission

[0054] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[0055] Terminal: Saves the user's input information and prepares it to be sent to the server.

[0056] 2. Generating body shape data using image analysis technology

[0057] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[0058] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[0059] 3. Creation and provision of optimal training menus

[0060] Server: Input the generated body shape data and goal information into the generative AI model.

[0061] Generative AI model: Generates the optimal training menu for the user based on input data.

[0062] Server: Receives the generated training menu and sends it to the user's device.

[0063] Terminal: Displays the training menu to the user.

[0064] 4. Monitoring training progress and creating and providing new training menus

[0065] User: During or after training, enter progress information (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[0066] Terminal: Sends the entered progress data to the server.

[0067] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[0068] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[0069] Server: Receives new training menus and sends them to the user's device.

[0070] Device: Display the updated training menu to the user.

[0071] 5. Push notifications to keep you on track

[0072] Server: Sets push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[0073] Server: Sends the configured push notification to the user's device.

[0074] On the device: Push notifications are displayed to encourage users to continue training.

[0075] Specific examples

[0076] For example, if a 30-year-old male user wants to lose body fat and gain muscle, the system works as follows:

[0077] User: Take a photo of their body and enter their height: 175cm, weight: 80kg, and target weight: 75kg.

[0078] Server: Analyzes the received information and estimates the body fat percentage to be 20%.

[0079] Generative AI model: Generates a mixed workout menu of strength training and cardio exercise four times a week based on body data and goals.

[0080] Server and terminal: Provides the generated menu to the user.

[0081] User: After one week, the progress report states that one workout was completed and no weight change was observed.

[0082] Server and generative AI model: Generates new menus and provides next week's menu with slight intensity adjustments.

[0083] As described above, this system is designed to allow users to easily receive personal training at home and continue training on an ongoing basis.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] user

[0087] Launch the application and enter your body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[0088] Step 2:

[0089] Terminal

[0090] Save the user's input information and prepare it to be sent to the server.

[0091] Step 3:

[0092] Terminal

[0093] The saved body type information and goal information of the user are transmitted to the server.

[0094] Step 4:

[0095] server

[0096] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[0097] Step 5:

[0098] server

[0099] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[0100] Step 6:

[0101] server

[0102] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[0103] Step 7:

[0104] server

[0105] The generated body shape data and target information are input into the generative AI model.

[0106] Step 8:

[0107] Generative AI Models

[0108] Based on the input data, a training menu optimal for the user is generated.

[0109] Step 9:

[0110] server

[0111] The generated training menu is received and sent to the user's terminal.

[0112] Step 10:

[0113] Terminal

[0114] Display the training menu to the user.

[0115] Step 11:

[0116] user

[0117] During or after training, enter your progress (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[0118] Step 12:

[0119] Terminal

[0120] The entered progress data is sent to the server.

[0121] Step 13:

[0122] server

[0123] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[0124] Step 14:

[0125] Generative AI Models

[0126] A new training menu is generated based on the progress data and sent back to the server.

[0127] Step 15:

[0128] server

[0129] Receive new training menus and send them to the user's device.

[0130] Step 16:

[0131] Terminal

[0132] The updated training menu is displayed to the user.

[0133] Step 17:

[0134] server

[0135] Set push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[0136] Step 18:

[0137] server

[0138] The configured push notification is sent to the user's device.

[0139] Step 19:

[0140] Terminal

[0141] Push notifications are displayed to users to encourage them to continue training.

[0142] Example 1

[0143] 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."

[0144] Conventional training programs only offer general menus, making it difficult to automatically generate optimal plans for each user's body type and goals. Furthermore, they lacked functionality for continually updating training menus based on the user's progress, or for encouraging continued training. This made it difficult for many users to continue, and they were unable to achieve effective results.

[0145] 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.

[0146] In this invention, the server includes means for inputting a user's body type information, means for generating body type data based on the body type information using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative AI model based on the body type data and goal information, means for sending push notifications to encourage continuation of training, means for using image data as the user's body type information and estimating body fat percentage and muscle mass using the image analysis technology, and means for creating prompts to input the user's body type data and goal information into the generative AI model. This makes it possible to automatically generate an optimized training menu for each user, continuously update the menu according to progress, and support the continuation of training.

[0147] "Body type information" is information about an individual's physical characteristics, such as a photograph showing the user's height, weight, age, sex, and body type.

[0148] "Image analysis technology" is a technology that uses computer vision and pattern recognition technology to analyze image data and extract specific information.

[0149] "Body shape data" is quantitative data about a user's physical characteristics, such as body fat percentage and muscle mass, generated using image analysis technology.

[0150] "Goal information" refers to the physical goals that the user wants to achieve, such as a target weight or a target body shape.

[0151] A "generative AI model" is an algorithm or system that uses machine learning or artificial intelligence techniques to generate results based on specific input data.

[0152] A "training menu" is a specific training plan created based on the user's body type information and goal information.

[0153] "Push notifications" is a function that allows the server to send training reminders and motivational messages to the user's device.

[0154] A "prompt sentence" is a text sentence that gives specific instructions or questions to the generative AI model based on input data.

[0155] "User progress information" is information about the user's training progress, such as the training items the user has completed and changes in weight.

[0156] This invention is a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information. The system is used by the user through an application, and operates by exchanging information between the server, terminal, and user.

[0157] The server receives the user's body type and goal information, and uses a generative AI model to generate an optimal training menu based on this data. It also updates the training menu according to the user's progress and provides it to the user's device.

[0158] The device transmits the information input by the user to the server, displays the training menu received from the server, and transmits the user's training progress back to the server to support continuous updating of the training menu.

[0159] Specifically, the system works as follows:

[0160] 1. Entering user information

[0161] User: Launches the application and enters the following body type and goal information:

[0162] Body information: photo, height, weight, age, gender

[0163] Goal information: target weight, target body shape

[0164] 2. Data transmission

[0165] Terminal: Temporarily stores the information entered by the user to be sent to the server and then sends it as a data package.

[0166] 3. Generating body shape data through image analysis

[0167] Server: Analyzes the received image data using Python's OpenCV library and generates body shape data such as body fat percentage and muscle mass.

[0168] 4. Creation of training menu

[0169] Server: Creates prompts based on body shape data and goal information, and inputs them into the generative AI model. For example, the prompts are:

[0170] User's body data:

[0171] Height: 175cm

[0172] Weight: 80kg

[0173] Body fat percentage: 20%

[0174] Target Data:

[0175] Target weight: 75kg

[0176] Training Goal: Build muscle and burn fat

[0177] Generate the optimal training menu based on the given data.

[0178] Generative AI model: This generates optimal training regimens, such as a mix of strength and cardio exercises four times a week.

[0179] 5. Provision and display of training menus

[0180] Server: Sends the generated training menu to the user's device.

[0181] Device: Display the received training menu on the app's user interface.

[0182] 6. Monitoring and updating your training progress

[0183] User: Enter progress information into the app during or after training.

[0184] Terminal: Sends the entered progress data to the server.

[0185] Server: Analyzes the received progress data and requests the generative AI model to generate a new training menu.

[0186] Generative AI model: Generates new training menus based on your progress data.

[0187] Server: Sends new training menus to the device, which then displays them to the user.

[0188] 7. Push notifications to keep you on track

[0189] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[0190] Server: Sends the configured push notification to the user's device.

[0191] Device: Receives the push notification and displays it to the user.

[0192] In this way, the system can provide a training menu optimized for each user and provide continuous training support.

[0193] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0194] Step 1:

[0195] User information entry and submission

[0196] User: Start the application and enter their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[0197] Input: Photo, height, weight, age, gender, target weight, target body type

[0198] Output: Input body shape information and target information

[0199] Terminal: Stores the user's input information and prepares it for transmission to the server. Temporarily stores the input data and formats it into a data package.

[0200] Input: Body type and goal information entered by the user

[0201] Data processing: Formatting data (JSON, etc.)

[0202] Output: A formatted data package

[0203] Step 2:

[0204] Generating body shape data through image analysis

[0205] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[0206] Input: Data package sent from the device

[0207] Output: Received data package

[0208] Server: Using Python's OpenCV library, the received image data is analyzed and body shape data such as body fat percentage and muscle mass are generated.

[0209] Input: Received image data

[0210] Data calculation: Image analysis using OpenCV

[0211] Output: Body fat percentage, muscle mass, and other body shape data

[0212] Step 3:

[0213] Creation and provision of training menus

[0214] Server: Creates prompt sentences based on the generated body shape data and goal information, and inputs them into the generative AI model.

[0215] Input: Body shape data, goal information

[0216] Data processing: Prompt sentence creation

[0217] Output: prompt statement

[0218] Generative AI model: Generates the optimal training menu for the user based on the input prompt.

[0219] Input: prompt statement

[0220] Data calculation: Training menu generation

[0221] Output: Generated training menu

[0222] Server: Receives the generated training menu and sends it to the user's device.

[0223] Input: Generated training menu

[0224] Output: Data sent to the user's device

[0225] Terminal: Displays the training menu to the user.

[0226] Input: Training menu sent from the server

[0227] Output: Displayed in the user interface

[0228] Step 4:

[0229] Monitoring training progress and creating and providing new training menus

[0230] User: Enter progress information into the app during or after training.

[0231] Input: Training progress (training items completed, dates, changes in body weight)

[0232] Output: progress information

[0233] Terminal: Sends the entered progress data to the server.

[0234] Input: Progress data from the user

[0235] Output: Data to send to the server

[0236] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[0237] Input: Progress data

[0238] Data calculation: Analysis of progress data

[0239] Output: prompt statement

[0240] Generative AI model: Generates new training menus based on progress data.

[0241] Input: prompt statement

[0242] Data calculation: generating new training menus

[0243] Output: New training menu

[0244] Server: Receives new training menus and sends them to the user's device.

[0245] Enter: New training menu

[0246] Output: Data sent to the user's device

[0247] Device: Display the updated training menu to the user.

[0248] Input: New training menu sent from the server

[0249] Output: Displayed in the user interface

[0250] Step 5:

[0251] Push notifications to keep you training

[0252] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[0253] Input: Progress data

[0254] Data Processing: Push Notification Settings

[0255] Output: Push notification data

[0256] Server: Sends the configured push notification to the user's device.

[0257] Input: Push notification data

[0258] Output: Data sent to the user's device

[0259] Device: Show the push notification to the user.

[0260] Input: Push notification sent from the server

[0261] Output: Displayed in the user interface

[0262] (Application example 1)

[0263] 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."

[0264] The rapid increase in the use of modern self-driving vehicles has led to improved travel efficiency, but there is a lack of systems that utilize travel time to maintain health and fitness. For busy people today, finding time for fitness is particularly challenging, and there is a need for efficient training programs and their ongoing management. The present invention aims to solve this problem by providing a fitness system that can be easily used in self-driving vehicles, enabling users to train efficiently while traveling.

[0265] 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.

[0266] In this invention, the server includes means for inputting body shape information of a user, means for generating body shape data based on the body shape information using image analysis technology, means for inputting user goal information, means for generating an optimal training menu based on the body shape data and goal information using a generative artificial intelligence model, means for providing the training menu to an in-vehicle terminal of an autonomous vehicle, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, and means for displaying the training menu on an in-vehicle display or a smartphone. This enables efficient fitness training even while on the move.

[0267] "Body type information" is data that represents the body type of the user, and includes image data and information such as height and weight.

[0268] "Image analysis technology" is a technology that analyzes image data and extracts useful information, and is particularly used to generate body shape data.

[0269] "Body shape data" is numerical data about a user's body shape generated using image analysis technology, and includes body fat percentage, muscle mass, etc.

[0270] "Goal information" is information relating to the goal that the user wants to achieve, including, for example, a target weight and a target body shape.

[0271] A "generative artificial intelligence model" is a model that uses artificial intelligence to process data, and is particularly used to generate fitness programs.

[0272] A "training menu" is a fitness exercise plan that a user performs, and is generated by a generative artificial intelligence model.

[0273] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for human operation.

[0274] An "in-vehicle terminal" is a device that is installed inside an autonomous vehicle and can display and input various information.

[0275] "Progress" is data showing the results of the user's training, including the training items performed and changes in body shape.

[0276] An "in-vehicle display" is a display device installed inside an autonomous vehicle and is used to display various information.

[0277] A "smartphone" is a mobile information terminal that has multiple computer functions in addition to the functions of a mobile phone.

[0278] The present invention is a system for enabling a user to efficiently engage in fitness activities in an autonomous vehicle. The following hardware and software configurations and data processing are used to implement the present invention.

[0279] System configuration

[0280] 1. Hardware

[0281] Camera systems for autonomous vehicles: These are installed at entrances and seats to collect information.

[0282] In-car device and smartphone: Used to display the training menu and enter progress.

[0283] Server: Responsible for data analysis and running generative artificial intelligence models.

[0284] 2. Software

[0285] Image analysis library (e.g., Python's OpenCV): Analyzes collected image data and generates information about the user's body shape.

[0286] Generative artificial intelligence model (e.g., PyTorch or TENSORFLOW®): Inputs body type data and goal information to generate an optimal training menu.

[0287] Health monitoring application: Allows users to enter their body information, view training menus, and track their progress.

[0288] Data processing and calculation details

[0289] 1. Image Data Acquisition and Analysis

[0290] The server collects image data in real time from cameras inside the autonomous vehicle.

[0291] Using an image analysis library (OpenCV), the system analyzes the user's body shape information from the collected image data and estimates body fat percentage and muscle mass.

[0292] 2. Creation of training menu

[0293] The server inputs the collected body type data and the user's goal information into the generative artificial intelligence model.

[0294] Using a generative artificial intelligence model (PyTorch or TensorFlow), an optimal training menu is generated based on body shape data and goal information.

[0295] 3. Providing training menus

[0296] The server transmits the generated training menu to the in-vehicle terminal and the smartphone.

[0297] The in-car terminal and smartphone display the training menu to the user.

[0298] 4. Managing progress data and creating new menus

[0299] Users enter their training progress into their smartphone or in-car device.

[0300] The server receives the input progress data and causes the generative artificial intelligence model to generate a new training menu based on the data.

[0301] The server provides new training menus to the in-car terminal and smartphone and displays them to the user.

[0302] Specific examples

[0303] For example, if a 30-year-old male user wants to lose body fat and gain muscle after riding in an autonomous vehicle, the system will operate as follows:

[0304] The server collects body images taken by cameras at the boarding and alighting doors.

[0305] Using an image analysis library (OpenCV), the body fat percentage and weight are analyzed and sent to the server along with the target weight of 75 kg.

[0306] A generative artificial intelligence model (PyTorch or TensorFlow) generates a menu of a mix of strength training and aerobic exercise four times a week and displays it on the in-car device.

[0307] Check the training menu on the in-car display or smartphone and start training while on the move.

[0308] After one week, the training progress is recorded as one completed training session and no weight change is reported.

[0309] The server analyzes the progress data, generates a new training menu, and provides the menu for the next week.

[0310] Prompt Sentence Examples

[0311] 1. "I'm 30 years old, 175cm tall, and weigh 80kg. My goal weight is 75kg. I want to lose body fat and gain muscle mass. Please create a training menu for me, with four sessions per week."

[0312] 2. "I'm a 45-year-old woman with 30% body fat and I want to lose weight while gaining muscle mass. I want to reach my goal weight within two months."

[0313] As a result, it is possible to efficiently train for fitness even while on the move.

[0314] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0315] Step 1:

[0316] After getting into an autonomous vehicle, a user captures a body image using an in-vehicle camera system. The input is video data from the in-vehicle camera, and the output is sent to a server as image data.

[0317] Step 2:

[0318] The server analyzes the received image data using an image analysis library such as OpenCV and generates body shape data such as body fat percentage and muscle mass. The input is the image data, and the output is the analyzed body shape data.

[0319] Step 3:

[0320] A user inputs target body shape information (e.g., target weight, target body shape) into a smartphone or an in-car terminal. The input is the target information from the user, and the output is the target information being sent to a server.

[0321] Step 4:

[0322] The server inputs the generated body shape data and the user's goal information into a generative artificial intelligence model (PyTorch or TensorFlow) to generate an optimal training menu. The input is body shape data and goal information, and the output is an optimal training menu.

[0323] Step 5:

[0324] The server transmits the generated training menu to the in-vehicle terminal and the smartphone. The input is the training menu, and the output is the menu displayed on the terminal.

[0325] Step 6:

[0326] The user performs fitness activities according to the training menu and inputs their progress into a smartphone or in-car device. The input is training progress data, and the output is the progress data being sent to a server.

[0327] Step 7:

[0328] The server analyzes the received progress data and generates a new training menu based on the analysis using a generative artificial intelligence model. The input is the progress data and the output is the new training menu.

[0329] Step 8:

[0330] The server again transmits the generated new training menu to the in-vehicle terminal and the smartphone, and displays it to the user. The input is the new training menu, and the output is the updated menu.

[0331] Step 9:

[0332] The server periodically sends training reminders and motivational messages via push notifications to encourage users to continue training. The input is the training schedule and motivational messages, and the output is notifications displayed on the user's smartphone or in-car device.

[0333] 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.

[0334] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[0335] System Overview

[0336] This system is used by users through an application and mainly provides the following functions.

[0337] 1. Enter and submit your body type and goal information

[0338] 2. Generating body shape data using image analysis technology

[0339] 3. Generating and providing optimal training menus using generative AI models

[0340] 4. Monitoring training progress and creating and providing new training menus

[0341] 5. Recognizing the user's emotional state using an emotion engine

[0342] 6. Adjust your training routine based on your emotional state

[0343] 7. Push notifications to encourage continued training

[0344] Program processing

[0345] The programs in this system operate through the exchange of information between the server, the terminal, and the user.

[0346] 1. User information entry and submission

[0347] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[0348] Terminal: Saves the user's input information and prepares it to be sent to the server.

[0349] 2. Generating body shape data using image analysis technology

[0350] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[0351] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[0352] 3. Creation and provision of optimal training menus

[0353] Server: Input the generated body shape data and goal information into the generative AI model.

[0354] Generative AI model: Generates the optimal training menu for the user based on input data.

[0355] Server: Receives the generated training menu and sends it to the user's device.

[0356] Terminal: Displays the training menu to the user.

[0357] 4. Monitoring training progress and creating and providing new training menus

[0358] User: During or after training, enter progress information (e.g., completed training items, dates of completion, weight changes, etc.) into the application.

[0359] Terminal: Sends the entered progress data to the server.

[0360] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[0361] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[0362] Server: Generates new training menus and sends them to the user's device.

[0363] Device: Display the updated training menu to the user.

[0364] 5. Recognizing emotional states using an emotion engine and adjusting training menus

[0365] User: During training, input their emotional state through the application (e.g., stress, fatigue, pleasure).

[0366] Terminal: Analyzes the emotional state using the emotion engine and sends the results to the server.

[0367] Server: Analyzes the received emotional state data and adjusts the training menu based on the emotional state.

[0368] Generative AI model: Generates a new training menu that reflects the emotional state data and sends it back to the server.

[0369] Server and terminal: Provides users with tailored training menus.

[0370] 6. Push notifications to keep you on track

[0371] Server: Sets push notifications at appropriate times based on the user's training progress and emotional state (e.g., training reminders, motivational messages).

[0372] Server: Sends the configured push notification to the user's device.

[0373] On the device: Push notifications are displayed to encourage users to continue training.

[0374] Specific examples

[0375] For example, if a 25-year-old female user wants to lose body fat and gain muscle, the system works as follows:

[0376] User: Take a photo of their body and enter their height: 160cm, weight: 60kg, and target weight: 55kg.

[0377] Server: Analyzes the received information and estimates body fat percentage to be 25%.

[0378] Generative AI model: Generates a mixed menu of strength training and cardio exercise three times a week based on body data and goals.

[0379] Server and terminal: Provides the generated menu to the user.

[0380] User: After training, enter into the app that their current emotional state is fatigued.

[0381] Emotion engine: Analyzes fatigue state and sends it to the server.

[0382] Generative AI model: Reflects the fatigue state and generates a new menu including relaxing stretches and light aerobic exercise, which is sent back to the server.

[0383] Server and terminal: Provides tailored training menus to users.

[0384] This system is designed to allow users to easily receive personal training at home and continue training continuously, and by taking into account the user's emotional state, it is possible to maximize the effectiveness of the training.

[0385] The processing flow will be explained below.

[0386] Step 1:

[0387] user

[0388] Launch the application and enter your body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[0389] Step 2:

[0390] Terminal

[0391] Save the user's input information and prepare it to be sent to the server.

[0392] Step 3:

[0393] Terminal

[0394] The saved body type information and goal information of the user are transmitted to the server.

[0395] Step 4:

[0396] server

[0397] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[0398] Step 5:

[0399] server

[0400] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[0401] Step 6:

[0402] server

[0403] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[0404] Step 7:

[0405] server

[0406] The generated body shape data and target information are input into the generative AI model.

[0407] Step 8:

[0408] Generative AI Models

[0409] Based on the input data, a training menu optimal for the user is generated.

[0410] Step 9:

[0411] server

[0412] The generated training menu is received and sent to the user's terminal.

[0413] Step 10:

[0414] Terminal

[0415] Display the training menu to the user.

[0416] Step 11:

[0417] user

[0418] During or after training, enter your progress (training items completed, dates performed, weight changes, etc.) into the application.

[0419] Step 12:

[0420] Terminal

[0421] The entered progress data is sent to the server.

[0422] Step 13:

[0423] server

[0424] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[0425] Step 14:

[0426] Generative AI Models

[0427] A new training menu is generated based on the progress data and sent back to the server.

[0428] Step 15:

[0429] server

[0430] A new training menu is generated and sent to the user's device.

[0431] Step 16:

[0432] Terminal

[0433] The updated training menu is displayed to the user.

[0434] Step 17:

[0435] user

[0436] During training, you enter your emotional state (stress, fatigue, pleasure, etc.) into the application.

[0437] Step 18:

[0438] Terminal

[0439] The emotional state is analyzed using an emotion engine and the results are sent to the server.

[0440] Step 19:

[0441] server

[0442] The received emotional state data is analyzed, and a training menu is adjusted based on the emotional state.

[0443] Step 20:

[0444] Generative AI Models

[0445] A new training menu reflecting the emotional state data is generated and sent back to the server.

[0446] Step 21:

[0447] server

[0448] The adjusted training menu is received and sent to the user's device.

[0449] Step 22:

[0450] Terminal

[0451] The adjusted training menu is displayed to the user.

[0452] Step 23:

[0453] server

[0454] Set push notifications at appropriate times based on the user's training progress and emotional state (training reminders, motivational messages).

[0455] Step 24:

[0456] server

[0457] The configured push notification is sent to the user's device.

[0458] Step 25:

[0459] Terminal

[0460] Push notifications are displayed to users to encourage them to continue training.

[0461] Example 2

[0462] 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."

[0463] In modern society, it is important for people to continue training in order to maintain a healthy lifestyle. However, many people find it difficult to create appropriate training menus for themselves, and they often lack the time to continue training. Another issue is that motivation is not maintained because a lack of consideration is given to the user's emotional state during training. Therefore, there is a need for a system that provides a training menu that comprehensively takes into account the user's physique information, goals, training progress, and emotional state, thereby maximizing the effectiveness of training and maintaining motivation to continue training.

[0464] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0465] In this invention, the server includes means for inputting a user's physique information, means for generating physique data using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative artificial intelligence model, means for providing the training menu to a user terminal, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, means for recognizing the user's emotional state, means for adjusting the training menu based on the emotional state, and means for sending push notifications to encourage continuation of training. This makes it possible to provide an optimal training menu and support continuous training by comprehensively considering the user's physique, goals, training progress, and emotional state.

[0466] "User's body type information" is information that indicates the user's physical characteristics, and includes image data and numerical data such as height and weight.

[0467] "Image analysis technology" refers to technology for extracting and analyzing meaningful information from image data, such as methods for estimating body fat percentage and muscle mass.

[0468] "Body shape data" refers to numerical data such as a user's body fat percentage and muscle mass generated using image analysis technology.

[0469] "User goal information" is information indicating the goal, such as weight or body shape, that the user wants to achieve.

[0470] A "generative artificial intelligence model" refers to a machine learning model that generates an optimal training menu based on input data.

[0471] A "training menu" refers to a list of specific exercises and workouts generated based on a user's physical characteristics and goals.

[0472] "User's training progress" is information indicating the content, results, and progress of training that the user has done in the past.

[0473] "Emotional state" refers to the psychological state, such as stress, fatigue, or pleasure, that a user experiences during training.

[0474] "Push notification" refers to a function that sends messages to a user's device to remind and motivate the user to continue their training.

[0475] A "server" is a computer system that receives and analyzes user data, executes AI models, and transmits information to user devices.

[0476] "Terminal" means a device that allows a user to operate an application and input / receive information, including smartphones and tablets.

[0477] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[0478] System Overview

[0479] This system is used by users through an application and provides the following main functions:

[0480] 1. Enter and submit your body type and goal information

[0481] 2. Generating body shape data using image analysis technology

[0482] 3. Generating and providing optimal training menus using generative AI models

[0483] 4. Monitoring training progress and creating and providing new training menus

[0484] 5. Recognizing the user's emotional state using an emotion engine

[0485] 6. Adjust your training routine based on your emotional state

[0486] 7. Push notifications to encourage continued training

[0487] Hardware and software used

[0488] Terminal: A smartphone or tablet is used as a device for users to operate the application. The terminal provides the user interface and transmits data to the server.

[0489] Server: A computer system that receives, analyzes, and stores various data, and executes generative AI models. The server uses a programming language such as Python, an image analysis library such as OpenCV, and an emotion analysis engine.

[0490] Generative AI model: A generative model that generates an optimal training menu based on the user's body type data and goal information. The training menu is optimized using a machine learning algorithm.

[0491] Specific operation of the system

[0492] Enter and submit your body type and goal information

[0493] The user starts the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved on the device.

[0494] The device stores the entered information and sends it to the server as a POST request, often in JSON format.

[0495] Generating body shape data using image analysis technology

[0496] The server receives the user's body type information (image data) and goal information (text data) sent from the terminal.

[0497] The server analyzes the image data using image analysis libraries such as Python's OpenCV, and generates numerical data on body shape, such as body fat percentage and muscle mass, which allows the user to understand their specific body shape.

[0498] Creation and provision of optimal training menus

[0499] The server inputs a prompt sentence into the generative AI model using the generated body shape data and goal information. The following is a specific example.

[0500] Input data: [Height: 160cm, Weight: 60kg, Age: 25, Gender: Female, Target Weight: 55kg, Body Fat Percentage: 25%]

[0501] Emotional state data: [Fatigue: High, Stress: Low, Pleasure: Medium]

[0502] Instructing the generative AI model: Generates a training menu that is optimal for the user, and also adjusts based on their emotional state.

[0503] Based on the input data, the generative AI model generates an optimal training menu for the user, including specific exercises.

[0504] The server receives the generated training menu and transmits it to the user's terminal.

[0505] The device analyzes the training menu and displays it on the user interface.

[0506] Monitor your training progress and generate new workouts

[0507] Users enter their training progress (e.g., completed training items, training dates, weight changes, etc.) into the application and save it on their device.

[0508] The terminal transmits the progress data to the server.

[0509] The server analyzes the progress data and asks the generative AI model to optimize the next training menu. It also generates new prompts based on the progress data and inputs them into the model.

[0510] The generative AI model generates a new training menu and sends it back to the server.

[0511] The server provides a new training menu and sends it to the terminal.

[0512] The device displays the updated training menu on the user interface.

[0513] Recognizing emotional states and adjusting training menus

[0514] During training, users input their emotional state (e.g., stress, fatigue, pleasure) into the application.

[0515] The device uses an emotion engine to analyze the emotional state and transmits the results to the server.

[0516] The server analyzes the emotional state data and inputs new prompts into the generative AI model to adjust the training menu.

[0517] The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server.

[0518] The server and the terminal provide the adjusted training menu to the user.

[0519] Push notifications to keep you training

[0520] The server schedules timely push notifications based on the user's training progress and emotional state, including workout reminders and motivational messages.

[0521] The server sends the configured push notification to the user's device.

[0522] The device receives a push notification and displays it on the user interface to encourage the user to continue training.

[0523] This system allows users to receive the optimal training menu that takes into consideration their physical condition, progress, and emotional state, enabling them to easily receive personal training at home and maintain their health on an ongoing basis.

[0524] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The user launches the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved in a local database on the device in JSON format. The specific operation is completed by keying in the data into the application's input form and pressing the submit button.

[0527] Input: User's body type and goal information

[0528] Output: Temporarily saved data in JSON format

[0529] Step 2:

[0530] The device prepares to send the entered information to the server. It sends an HTTP POST request with the saved data in a JSON-formatted payload. The HTTP request is then sent to the server. This is done by executing an API call associated with the click event of the submit button.

[0531] Input: Temporarily saved JSON format data

[0532] Output: HTTP POST request to the server

[0533] Step 3:

[0534] The server receives the user's body shape information (image data) and goal information (text data) sent from the device. Using a web framework such as Python's Flask or Django, the server receives the data at an API endpoint and stores it on a disk or in a database.

[0535] Input: JSON format data sent via HTTP POST request

[0536] Output: Body shape and goal information stored on disk and in a database

[0537] Step 4:

[0538] The server uses Python's OpenCV library to generate body shape data from the received image data. This process involves extracting the contours of specific body parts from the image and using algorithms to estimate body fat percentage and muscle mass. Specific operations are achieved by loading the received image data into OpenCV, extracting contours, and applying algorithms.

[0539] Input: Received image data

[0540] Output: Numerical body shape data including body fat percentage and muscle mass

[0541] Step 5:

[0542] The server uses the generated body shape data and goal information to input prompt sentences into the generative AI model. The generative AI model is a pre-trained machine learning model that generates an optimal training menu for the user based on the input data. Specifically, the server converts the body shape data and goal information into a specific format (prompt sentences) and sends them to the generative AI model via an API.

[0543] Input: Body type data and goal information

[0544] Output: Optimal training menu

[0545] Step 6:

[0546] The server receives the generated training menu and sends it to the user's device in JSON format. This data is sent as an HTTP response. The specific operation is to receive the results from the generative AI model and return them in format as an HTTP response.

[0547] Input: Generated training menu

[0548] Output: HTTP response to the user's device

[0549] Step 7:

[0550] The device parses the received training menu and displays it on the user interface. Specifically, it parses the received JSON data and visually displays it to the user in list or calendar format.

[0551] Input: Training menu received from the server

[0552] Output: Training menu displayed in the user interface

[0553] Step 8:

[0554] Users enter their training progress into the application and save it on their device. This includes details such as exercises completed, weight changes, and dates of exercise. Specifically, data is entered and saved on the progress input screen.

[0555] Input: Training progress data

[0556] Output: Progress data saved on the device

[0557] Step 9:

[0558] The device sends the saved progress data to the server in JSON format as an HTTP POST request. The specific operation is to click the Send Progress Data button to execute an API call.

[0559] Input: Progress data stored on the device

[0560] Output: HTTP POST request to the server

[0561] Step 10:

[0562] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu. This is done by generating prompts using the progress data and sending them to the AI ​​model. The specific operation is the process of analyzing the received progress data and generating new prompts.

[0563] Input: Received progress data

[0564] Output: New optimized training menu

[0565] Step 11:

[0566] The generative AI model generates an optimized training menu based on the new progress data and sends it back to the server. The specific operation is the process of analyzing the progress data and generating a training menu based on it.

[0567] Input: Prompt statement reflecting progress data

[0568] Output: New training menu

[0569] Step 12:

[0570] The server receives the new training menu and sends it to the user's terminal. Specifically, it formats the new training menu in JSON format and sends it to the terminal as an HTTP response.

[0571] Enter: New training menu

[0572] Output: HTTP response to the user's device

[0573] Step 13:

[0574] The device parses the updated training menu and displays it in the user interface. The specific operation is to parse the received JSON data and reflect the menu in the user interface.

[0575] Input: New training menu received from the server

[0576] Output: Display of updated training menu

[0577] Step 14:

[0578] While training, users input their emotional state (stress, fatigue, pleasure, etc.) into the app. This data is temporarily stored on the device. Specifically, users input their emotional state using sliders and buttons on the emotion input interface.

[0579] Input: Emotional state data

[0580] Output: Emotion data temporarily stored on the device

[0581] Step 15:

[0582] The device uses the emotion engine to analyze the emotional state and sends the results to the server. Specifically, it calls the emotion analysis API and sends the analysis results to the server in JSON format.

[0583] Input: Temporarily stored emotional state data

[0584] Output: Sending analysis results to the server

[0585] Step 16:

[0586] The server analyzes the received emotional state data and inputs new prompt sentences to the generative AI model to adjust the training menu. Specifically, it creates new prompt sentences based on the emotional data and sends them to the generative AI model.

[0587] Input: Received emotional state data

[0588] Output: New and adjusted training menu

[0589] Step 17:

[0590] The generative AI model generates an adjusted training menu that reflects the emotional state and sends it back to the server. The specific operation is the process of generating an adaptive exercise list using emotional data.

[0591] Input: Prompt sentence reflecting emotional state data

[0592] Output: Tailored training menu

[0593] Step 18:

[0594] The server sends the adjusted training menu to the user's terminal. Specifically, the server formats the generated menu in JSON format and sends it as an HTTP response.

[0595] Enter: a tailored training menu.

[0596] Output: HTTP response to the user's device

[0597] Step 19:

[0598] The device displays the adjusted training menu on the user interface. Specifically, it parses the received JSON data and reflects the menu on the user interface.

[0599] Enter: a tailored training menu.

[0600] Output: Display of adjusted training menu

[0601] Step 20:

[0602] The server schedules push notifications at appropriate times based on the user's training progress and emotional state, allowing training reminders and motivational messages to be sent. Specifically, the server analyzes progress and emotional data and schedules push notifications.

[0603] Input: Progress data and emotional state data

[0604] Output: Configured push notifications

[0605] Step 21:

[0606] The server sends the configured push notification to the user's device. Specifically, the server uses the push notification service to periodically deliver notification messages to the device.

[0607] Input: Configured push notification

[0608] Output: Send push notification to user device

[0609] Step 22:

[0610] The device receives the push notification and displays it in the user interface, providing reminders and motivation to encourage the user to continue training. The specific behavior is to display the received push notification as a pop-up.

[0611] Input: Push notification received from the server

[0612] Output: Push notification displayed in the user interface

[0613] Through the above processing steps, the system provides users with a personalized training menu, maximizing the effectiveness of their training and maintaining continuous motivation.

[0614] (Application example 2)

[0615] 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."

[0616] While conventional training support systems can provide training menus based on the user's physique data and goal information, they do not take into account the user's emotional state and make adjustments, making it difficult to maintain motivation to continue training over the long term. Furthermore, there is a lack of training support in virtual environments, making it difficult to receive effective feedback, especially when training at home. This has resulted in an insufficient environment for efficient and continuous training.

[0617] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0618] In this invention, the server includes: means for inputting a user's physique information; means for generating physique data using image analysis technology; means for inputting the user's goal information; means for generating an optimal training menu using a generative AI model based on the physique data and goal information in a user-implemented device; means for providing the training menu to a user terminal; means for inputting the user's training progress; means for generating and providing a new training menu based on the progress; means for using a display device to provide training in a virtual environment; means for recognizing the user's emotional state and adjusting the training menu based thereon; and means for providing the adjusted training menu to the display device. This allows the user to be provided with a training menu that takes their emotional state into account, thereby maintaining motivation over the long term. Furthermore, support from a fitness instructor is realized in a virtual environment, enabling effective training even at home.

[0619] "Body type information" is data relating to the physical characteristics of the user, and specific examples include height, weight, age, sex, and image data.

[0620] "Image analysis technology" is a technology for quantifying a user's physical characteristics from acquired image data, and specific examples include estimating body fat percentage and muscle mass.

[0621] "Goal information" is data relating to the purpose or goal of training that the user wishes to achieve, and specific examples include a target weight and body fat percentage.

[0622] A "generative AI model" is an artificial intelligence model that generates specific outputs based on input data, in this context specifically for automatically generating optimal training menus.

[0623] A "training menu" is a plan that lists the specific exercises and training items that a user should do and the order in which they should do them.

[0624] A "user terminal" is an electronic device that is directly operated by the user, and in this system is used to provide training menus and input progress.

[0625] "Progress" is information that refers to the results and current status that a user has achieved in training, and specific examples include completed training items and changes in weight.

[0626] "Display device" means a visual output device used to deliver training in a virtual environment, including, for example, VR goggles and smart glasses.

[0627] "Emotional state" is information that indicates the user's current mental and emotional state, and specific examples include stress, fatigue, and pleasure.

[0628] "Adjustment" refers to the act of changing the content and order of the training menu based on specific conditions or the user's state.

[0629] This invention combines a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information, with an emotion engine. This system has the following specific configuration:

[0630] Overall structure

[0631] This system is used by users through an application and mainly uses the following hardware and software.

[0632] Hardware

[0633] Smartphone: A device on which users run applications and input information about their body shape and training progress.

[0634] VR goggles or smart glasses: display devices for delivering training in a virtual environment.

[0635] software

[0636] Image analysis library (e.g., Python's OpenCV): Software for generating body shape data from acquired images.

[0637] Generative AI model (e.g., neural network model using Keras): Software for generating optimal training menus based on body shape data and goal information.

[0638] Emotion Engine: Software that recognizes the user's emotional state and adjusts the training menu accordingly.

[0639] Processing Overview

[0640] 1. User information entry and submission

[0641] The user launches the smartphone application and enters body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen. The device saves this information and prepares it for transmission to the server. The server uses image analysis technology to generate body type data based on the received body type information and goal information.

[0642] 2. Creation and provision of training menus

[0643] The server inputs the generated body shape data and goal information into the generative AI model to generate an optimal training menu, which is then sent from the server to the user's device and displayed to the user.

[0644] 3. Monitor your training progress and regenerate your training menu

[0645] After completing a workout, the user enters their progress (e.g., completed workout items, workout dates, weight changes, etc.) into the application. This progress data is sent from the device to the server and used to optimize the next workout menu.

[0646] 4. Recognizing emotional states

[0647] Users input their emotional state through the application. The emotion engine analyzes this emotional state and sends the data to the server. Based on this data, the generative AI model generates a new training menu that reflects the emotional state, and the server then provides it to the user's device.

[0648] Specific examples

[0649] For example, if a 30-year-old male user wants to continue their fitness routine at home, the app works as follows: The user uploads an image of their body shape and enters their age, height, weight, and gender via the smartphone app. The server analyzes the image, calculates their body fat percentage, and supplies it to the generative AI model. The AI ​​model then generates an optimal training menu and provides it to the user. The user puts on VR goggles and receives training instructions from a virtual instructor. After training, the user enters their level of fatigue into the app, and the emotion engine analyzes that information and adjusts the next training menu. A new, adjusted training menu is then provided, allowing the user to continue training.

[0650] Prompt Sentence Examples

[0651] The prompt text is entered in the following format: "The user is 30 years old, 175 cm tall, weighs 80 kg, and currently has a body fat percentage of 20%. The user's goal is to increase muscle mass and reduce the body fat percentage to 15%. Please generate the optimal training menu."

[0652] As described above, this system provides an environment where users can perform personalized training at home and continue training sustainably. Furthermore, by taking into account the user's emotional state, efficient and effective training can be achieved.

[0653] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0654] Step 1: Enter user information

[0655] The user starts the smartphone app and inputs their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type). The device saves this input data and prepares to send it to the server.

[0656] (Input): User's body type information and goal information

[0657] (Output): The dataset sent to the server

[0658] Step 2: Analyzing the image data

[0659] The server analyzes the image data of the body shape information received from the device using image analysis technology (such as Python's OpenCV), and derives numerical data such as body fat percentage and muscle mass.

[0660] (Input): Image data sent by the user

[0661] (Output): Body shape data as analysis results (e.g., body fat percentage, muscle mass)

[0662] Step 3: Create a training menu

[0663] The server inputs the analyzed body shape data and goal information into a generative AI model to generate an optimal training menu. The generative AI model (using Keras) automatically generates the training menu using a neural network.

[0664] (Input): Body shape data and goal information

[0665] (Output): Generated training menu

[0666] Step 4: Providing training menus

[0667] The server sends the generated training menu to the user's device, which displays the received training menu to the user and prepares to start training in the virtual environment.

[0668] (Input): Generated training menu

[0669] (Output): Training menu displayed to the user

[0670] Step 5: Enter your training progress

[0671] After completing a workout, the user uses a smartphone app to input progress information (e.g., completed workout items, workout dates, weight changes). The device saves this progress data and sends it to the server.

[0672] (Input): Training progress data

[0673] (Output): Progress dataset sent to the server

[0674] Step 6: Analyze progress data and regenerate menus

[0675] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data. The generative AI model then regenerates a new training menu based on the analysis results and sends it back to the server.

[0676] (Input): Training progress data

[0677] (Output): New training menu

[0678] Step 7: Input and analysis of emotional states

[0679] Users input their emotional state (e.g., stress, fatigue, pleasure) through the app during or after training. The device then analyzes the emotional state using an emotion engine and sends the results to the server.

[0680] (Input): Emotional state data

[0681] (Output): Parsed emotion data

[0682] Step 8: Adjust the menu with emotional data

[0683] The server adjusts the training menu according to the emotional state based on the received emotional state data. The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server. The adjusted training menu is then provided to the user's device.

[0684] (Input): Emotional state data

[0685] (Output): Adjusted training menu

[0686] Step 9: Remind me to continue the task

[0687] The server sets push notifications (e.g., training reminders, motivational messages) at appropriate times based on the user's training progress and emotional state. The server sends the set push notifications to the user's device, and the device displays the push notifications to the user.

[0688] (Input): Training progress data and emotional state data

[0689] (Output): Push notification displayed to the user

[0690] 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.

[0691] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0692] 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.

[0693] [Second embodiment]

[0694] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0695] 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.

[0696] 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).

[0697] 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.

[0698] 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.

[0699] 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).

[0700] 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. 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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."

[0706] This invention is a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information. Specific embodiments of this system will be described below.

[0707] System Overview

[0708] This system is used by users through an application and mainly provides the following functions.

[0709] 1. Enter and submit your body type and goal information

[0710] 2. Generating body shape data using image analysis technology

[0711] 3. Generating and providing optimal training menus using generative AI models

[0712] 4. Monitoring training progress and creating and providing new training menus

[0713] 5. Send push notifications to encourage continued training

[0714] Program processing

[0715] The system's programs operate through the exchange of information between the server, terminals, and users.

[0716] 1. User information entry and submission

[0717] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[0718] Terminal: Saves the user's input information and prepares it to be sent to the server.

[0719] 2. Generating body shape data using image analysis technology

[0720] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[0721] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[0722] 3. Creation and provision of optimal training menus

[0723] Server: Input the generated body shape data and goal information into the generative AI model.

[0724] Generative AI model: Generates the optimal training menu for the user based on input data.

[0725] Server: Receives the generated training menu and sends it to the user's device.

[0726] Terminal: Displays the training menu to the user.

[0727] 4. Monitoring training progress and creating and providing new training menus

[0728] User: During or after training, enter progress information (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[0729] Terminal: Sends the entered progress data to the server.

[0730] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[0731] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[0732] Server: Receives new training menus and sends them to the user's device.

[0733] Device: Display the updated training menu to the user.

[0734] 5. Push notifications to keep you on track

[0735] Server: Sets push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[0736] Server: Sends the configured push notification to the user's device.

[0737] On the device: Push notifications are displayed to encourage users to continue training.

[0738] Specific examples

[0739] For example, if a 30-year-old male user wants to lose body fat and gain muscle, the system works as follows:

[0740] User: Take a photo of their body and enter their height: 175cm, weight: 80kg, and target weight: 75kg.

[0741] Server: Analyzes the received information and estimates the body fat percentage to be 20%.

[0742] Generative AI model: Generates a mixed workout menu of strength training and cardio exercise four times a week based on body data and goals.

[0743] Server and terminal: Provides the generated menu to the user.

[0744] User: After one week, the progress report states that one workout was completed and no weight change was observed.

[0745] Server and generative AI model: Generates new menus and provides next week's menu with slight intensity adjustments.

[0746] As described above, this system is designed to allow users to easily receive personal training at home and continue training on an ongoing basis.

[0747] The processing flow will be explained below.

[0748] Step 1:

[0749] user

[0750] Launch the application and enter your body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[0751] Step 2:

[0752] Terminal

[0753] Save the user's input information and prepare it to be sent to the server.

[0754] Step 3:

[0755] Terminal

[0756] The saved body type information and goal information of the user are transmitted to the server.

[0757] Step 4:

[0758] server

[0759] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[0760] Step 5:

[0761] server

[0762] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[0763] Step 6:

[0764] server

[0765] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[0766] Step 7:

[0767] server

[0768] The generated body shape data and target information are input into the generative AI model.

[0769] Step 8:

[0770] Generative AI Models

[0771] Based on the input data, a training menu optimal for the user is generated.

[0772] Step 9:

[0773] server

[0774] The generated training menu is received and sent to the user's terminal.

[0775] Step 10:

[0776] Terminal

[0777] Display the training menu to the user.

[0778] Step 11:

[0779] user

[0780] During or after training, enter your progress (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[0781] Step 12:

[0782] Terminal

[0783] The entered progress data is sent to the server.

[0784] Step 13:

[0785] server

[0786] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[0787] Step 14:

[0788] Generative AI Models

[0789] A new training menu is generated based on the progress data and sent back to the server.

[0790] Step 15:

[0791] server

[0792] Receive new training menus and send them to the user's device.

[0793] Step 16:

[0794] Terminal

[0795] The updated training menu is displayed to the user.

[0796] Step 17:

[0797] server

[0798] Set push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[0799] Step 18:

[0800] server

[0801] The configured push notification is sent to the user's device.

[0802] Step 19:

[0803] Terminal

[0804] Push notifications are displayed to users to encourage them to continue training.

[0805] Example 1

[0806] 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."

[0807] Conventional training programs only offer general menus, making it difficult to automatically generate optimal plans for each user's body type and goals. Furthermore, they lacked functionality for continually updating training menus based on the user's progress, or for encouraging continued training. This made it difficult for many users to continue, and they were unable to achieve effective results.

[0808] 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.

[0809] In this invention, the server includes means for inputting a user's body type information, means for generating body type data based on the body type information using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative AI model based on the body type data and goal information, means for sending push notifications to encourage continuation of training, means for using image data as the user's body type information and estimating body fat percentage and muscle mass using the image analysis technology, and means for creating prompts to input the user's body type data and goal information into the generative AI model. This makes it possible to automatically generate an optimized training menu for each user, continuously update the menu according to progress, and support the continuation of training.

[0810] "Body type information" is information about an individual's physical characteristics, such as a photograph showing the user's height, weight, age, sex, and body type.

[0811] "Image analysis technology" is a technology that uses computer vision and pattern recognition technology to analyze image data and extract specific information.

[0812] "Body shape data" is quantitative data about a user's physical characteristics, such as body fat percentage and muscle mass, generated using image analysis technology.

[0813] "Goal information" refers to the physical goals that the user wants to achieve, such as a target weight or a target body shape.

[0814] A "generative AI model" is an algorithm or system that uses machine learning or artificial intelligence techniques to generate results based on specific input data.

[0815] A "training menu" is a specific training plan created based on the user's body type information and goal information.

[0816] "Push notifications" is a function that allows the server to send training reminders and motivational messages to the user's device.

[0817] A "prompt sentence" is a text sentence that gives specific instructions or questions to the generative AI model based on input data.

[0818] "User progress information" is information about the user's training progress, such as the training items the user has completed and changes in weight.

[0819] This invention is a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information. The system is used by the user through an application, and operates by exchanging information between the server, terminal, and user.

[0820] The server receives the user's body type and goal information, and uses a generative AI model to generate an optimal training menu based on this data. It also updates the training menu according to the user's progress and provides it to the user's device.

[0821] The device transmits the information input by the user to the server, displays the training menu received from the server, and transmits the user's training progress back to the server to support continuous updating of the training menu.

[0822] Specifically, the system works as follows:

[0823] 1. Entering user information

[0824] User: Launches the application and enters the following body type and goal information:

[0825] Body information: photo, height, weight, age, gender

[0826] Goal information: target weight, target body shape

[0827] 2. Data transmission

[0828] Terminal: Temporarily stores the information entered by the user to be sent to the server and then sends it as a data package.

[0829] 3. Generating body shape data through image analysis

[0830] Server: Analyzes the received image data using Python's OpenCV library and generates body shape data such as body fat percentage and muscle mass.

[0831] 4. Creation of training menu

[0832] Server: Creates prompts based on body shape data and goal information, and inputs them into the generative AI model. For example, the prompts are:

[0833] User's body data:

[0834] Height: 175cm

[0835] Weight: 80kg

[0836] Body fat percentage: 20%

[0837] Target Data:

[0838] Target weight: 75kg

[0839] Training Goal: Build muscle and burn fat

[0840] Generate the optimal training menu based on the given data.

[0841] Generative AI model: This generates optimal training regimens, such as a mix of strength and cardio exercises four times a week.

[0842] 5. Provision and display of training menus

[0843] Server: Sends the generated training menu to the user's device.

[0844] Device: Display the received training menu on the app's user interface.

[0845] 6. Monitoring and updating your training progress

[0846] User: Enter progress information into the app during or after training.

[0847] Terminal: Sends the entered progress data to the server.

[0848] Server: Analyzes the received progress data and requests the generative AI model to generate a new training menu.

[0849] Generative AI model: Generates new training menus based on your progress data.

[0850] Server: Sends new training menus to the device, which then displays them to the user.

[0851] 7. Push notifications to keep you on track

[0852] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[0853] Server: Sends the configured push notification to the user's device.

[0854] Device: Receives the push notification and displays it to the user.

[0855] In this way, the system can provide a training menu optimized for each user and provide continuous training support.

[0856] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0857] Step 1:

[0858] User information entry and submission

[0859] User: Start the application and enter their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[0860] Input: Photo, height, weight, age, gender, target weight, target body type

[0861] Output: Input body shape information and target information

[0862] Terminal: Stores the user's input information and prepares it for transmission to the server. Temporarily stores the input data and formats it into a data package.

[0863] Input: Body type and goal information entered by the user

[0864] Data processing: Formatting data (JSON, etc.)

[0865] Output: A formatted data package

[0866] Step 2:

[0867] Generating body shape data through image analysis

[0868] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[0869] Input: Data package sent from the device

[0870] Output: Received data package

[0871] Server: Using Python's OpenCV library, the received image data is analyzed and body shape data such as body fat percentage and muscle mass are generated.

[0872] Input: Received image data

[0873] Data calculation: Image analysis using OpenCV

[0874] Output: Body fat percentage, muscle mass, and other body shape data

[0875] Step 3:

[0876] Creation and provision of training menus

[0877] Server: Creates prompt sentences based on the generated body shape data and goal information, and inputs them into the generative AI model.

[0878] Input: Body shape data, goal information

[0879] Data processing: Prompt sentence creation

[0880] Output: prompt statement

[0881] Generative AI model: Generates the optimal training menu for the user based on the input prompt.

[0882] Input: prompt statement

[0883] Data calculation: Training menu generation

[0884] Output: Generated training menu

[0885] Server: Receives the generated training menu and sends it to the user's device.

[0886] Input: Generated training menu

[0887] Output: Data sent to the user's device

[0888] Terminal: Displays the training menu to the user.

[0889] Input: Training menu sent from the server

[0890] Output: Displayed in the user interface

[0891] Step 4:

[0892] Monitoring training progress and creating and providing new training menus

[0893] User: Enter progress information into the app during or after training.

[0894] Input: Training progress (training items completed, dates, changes in body weight)

[0895] Output: progress information

[0896] Terminal: Sends the entered progress data to the server.

[0897] Input: Progress data from the user

[0898] Output: Data to send to the server

[0899] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[0900] Input: Progress data

[0901] Data calculation: Analysis of progress data

[0902] Output: prompt statement

[0903] Generative AI model: Generates new training menus based on progress data.

[0904] Input: prompt statement

[0905] Data calculation: generating new training menus

[0906] Output: New training menu

[0907] Server: Receives new training menus and sends them to the user's device.

[0908] Enter: New training menu

[0909] Output: Data sent to the user's device

[0910] Device: Display the updated training menu to the user.

[0911] Input: New training menu sent from the server

[0912] Output: Displayed in the user interface

[0913] Step 5:

[0914] Push notifications to keep you training

[0915] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[0916] Input: Progress data

[0917] Data Processing: Push Notification Settings

[0918] Output: Push notification data

[0919] Server: Sends the configured push notification to the user's device.

[0920] Input: Push notification data

[0921] Output: Data sent to the user's device

[0922] Device: Show the push notification to the user.

[0923] Input: Push notification sent from the server

[0924] Output: Displayed in the user interface

[0925] (Application example 1)

[0926] 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."

[0927] The rapid increase in the use of modern self-driving vehicles has led to improved travel efficiency, but there is a lack of systems that utilize travel time to maintain health and fitness. For busy people today, finding time for fitness is particularly challenging, and there is a need for efficient training programs and their ongoing management. The present invention aims to solve this problem by providing a fitness system that can be easily used in self-driving vehicles, enabling users to train efficiently while traveling.

[0928] 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.

[0929] In this invention, the server includes means for inputting body shape information of a user, means for generating body shape data based on the body shape information using image analysis technology, means for inputting user goal information, means for generating an optimal training menu based on the body shape data and goal information using a generative artificial intelligence model, means for providing the training menu to an in-vehicle terminal of an autonomous vehicle, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, and means for displaying the training menu on an in-vehicle display or a smartphone. This enables efficient fitness training even while on the move.

[0930] "Body type information" is data that represents the body type of the user, and includes image data and information such as height and weight.

[0931] "Image analysis technology" is a technology that analyzes image data and extracts useful information, and is particularly used to generate body shape data.

[0932] "Body shape data" is numerical data about a user's body shape generated using image analysis technology, and includes body fat percentage, muscle mass, etc.

[0933] "Goal information" is information relating to the goal that the user wants to achieve, including, for example, a target weight and a target body shape.

[0934] A "generative artificial intelligence model" is a model that uses artificial intelligence to process data, and is particularly used to generate fitness programs.

[0935] A "training menu" is a fitness exercise plan that a user performs, and is generated by a generative artificial intelligence model.

[0936] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for human operation.

[0937] An "in-vehicle terminal" is a device that is installed inside an autonomous vehicle and can display and input various information.

[0938] "Progress" is data showing the results of the user's training, including the training items performed and changes in body shape.

[0939] An "in-vehicle display" is a display device installed inside an autonomous vehicle and is used to display various information.

[0940] A "smartphone" is a mobile information terminal that has multiple computer functions in addition to the functions of a mobile phone.

[0941] The present invention is a system for enabling a user to efficiently engage in fitness activities in an autonomous vehicle. The following hardware and software configurations and data processing are used to implement the present invention.

[0942] System configuration

[0943] 1. Hardware

[0944] Camera systems for autonomous vehicles: These are installed at entrances and seats to collect information.

[0945] In-car device and smartphone: Used to display the training menu and enter progress.

[0946] Server: Responsible for data analysis and running generative artificial intelligence models.

[0947] 2. Software

[0948] Image analysis library (e.g., Python's OpenCV): Analyzes collected image data and generates information about the user's body shape.

[0949] Generative AI model (e.g., PyTorch or TensorFlow): Inputs body type data and goal information to generate an optimal training menu.

[0950] Health monitoring application: Allows users to enter their body information, view training menus, and track their progress.

[0951] Data processing and calculation details

[0952] 1. Image Data Acquisition and Analysis

[0953] The server collects image data in real time from cameras inside the autonomous vehicle.

[0954] Using an image analysis library (OpenCV), the system analyzes the user's body shape information from the collected image data and estimates body fat percentage and muscle mass.

[0955] 2. Creation of training menu

[0956] The server inputs the collected body type data and the user's goal information into the generative artificial intelligence model.

[0957] Using a generative artificial intelligence model (PyTorch or TensorFlow), an optimal training menu is generated based on body shape data and goal information.

[0958] 3. Providing training menus

[0959] The server transmits the generated training menu to the in-vehicle terminal and the smartphone.

[0960] The in-car terminal and smartphone display the training menu to the user.

[0961] 4. Managing progress data and creating new menus

[0962] Users enter their training progress into their smartphone or in-car device.

[0963] The server receives the input progress data and causes the generative artificial intelligence model to generate a new training menu based on the data.

[0964] The server provides new training menus to the in-car terminal and smartphone and displays them to the user.

[0965] Specific examples

[0966] For example, if a 30-year-old male user wants to lose body fat and gain muscle after riding in an autonomous vehicle, the system will operate as follows:

[0967] The server collects body images taken by cameras at the boarding and alighting doors.

[0968] Using an image analysis library (OpenCV), the body fat percentage and weight are analyzed and sent to the server along with the target weight of 75 kg.

[0969] A generative artificial intelligence model (PyTorch or TensorFlow) generates a menu of a mix of strength training and aerobic exercise four times a week and displays it on the in-car device.

[0970] Check the training menu on the in-car display or smartphone and start training while on the move.

[0971] After one week, the training progress is recorded as one completed training session and no weight change is reported.

[0972] The server analyzes the progress data, generates a new training menu, and provides the menu for the next week.

[0973] Prompt Sentence Examples

[0974] 1. "I'm 30 years old, 175cm tall, and weigh 80kg. My goal weight is 75kg. I want to lose body fat and gain muscle mass. Please create a training menu for me, with four sessions per week."

[0975] 2. "I'm a 45-year-old woman with 30% body fat and I want to lose weight while gaining muscle mass. I want to reach my goal weight within two months."

[0976] As a result, it is possible to efficiently train for fitness even while on the move.

[0977] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0978] Step 1:

[0979] After getting into an autonomous vehicle, a user captures a body image using an in-vehicle camera system. The input is video data from the in-vehicle camera, and the output is sent to a server as image data.

[0980] Step 2:

[0981] The server analyzes the received image data using an image analysis library such as OpenCV and generates body shape data such as body fat percentage and muscle mass. The input is the image data, and the output is the analyzed body shape data.

[0982] Step 3:

[0983] A user inputs target body shape information (e.g., target weight, target body shape) into a smartphone or an in-car terminal. The input is the target information from the user, and the output is the target information being sent to a server.

[0984] Step 4:

[0985] The server inputs the generated body shape data and the user's goal information into a generative artificial intelligence model (PyTorch or TensorFlow) to generate an optimal training menu. The input is body shape data and goal information, and the output is an optimal training menu.

[0986] Step 5:

[0987] The server transmits the generated training menu to the in-vehicle terminal and the smartphone. The input is the training menu, and the output is the menu displayed on the terminal.

[0988] Step 6:

[0989] The user performs fitness activities according to the training menu and inputs their progress into a smartphone or in-car device. The input is training progress data, and the output is the progress data being sent to a server.

[0990] Step 7:

[0991] The server analyzes the received progress data and generates a new training menu based on the analysis using a generative artificial intelligence model. The input is the progress data and the output is the new training menu.

[0992] Step 8:

[0993] The server again transmits the generated new training menu to the in-vehicle terminal and the smartphone, and displays it to the user. The input is the new training menu, and the output is the updated menu.

[0994] Step 9:

[0995] The server periodically sends training reminders and motivational messages via push notifications to encourage users to continue training. The input is the training schedule and motivational messages, and the output is notifications displayed on the user's smartphone or in-car device.

[0996] 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.

[0997] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[0998] System Overview

[0999] This system is used by users through an application and mainly provides the following functions.

[1000] 1. Enter and submit your body type and goal information

[1001] 2. Generating body shape data using image analysis technology

[1002] 3. Generating and providing optimal training menus using generative AI models

[1003] 4. Monitoring training progress and creating and providing new training menus

[1004] 5. Recognizing the user's emotional state using an emotion engine

[1005] 6. Adjust your training routine based on your emotional state

[1006] 7. Push notifications to encourage continued training

[1007] Program processing

[1008] The programs in this system operate through the exchange of information between the server, the terminal, and the user.

[1009] 1. User information entry and submission

[1010] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[1011] Terminal: Saves the user's input information and prepares it to be sent to the server.

[1012] 2. Generating body shape data using image analysis technology

[1013] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[1014] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[1015] 3. Creation and provision of optimal training menus

[1016] Server: Input the generated body shape data and goal information into the generative AI model.

[1017] Generative AI model: Generates the optimal training menu for the user based on input data.

[1018] Server: Receives the generated training menu and sends it to the user's device.

[1019] Terminal: Displays the training menu to the user.

[1020] 4. Monitoring training progress and creating and providing new training menus

[1021] User: During or after training, enter progress information (e.g., completed training items, dates of completion, weight changes, etc.) into the application.

[1022] Terminal: Sends the entered progress data to the server.

[1023] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[1024] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[1025] Server: Generates new training menus and sends them to the user's device.

[1026] Device: Display the updated training menu to the user.

[1027] 5. Recognizing emotional states using an emotion engine and adjusting training menus

[1028] User: During training, input their emotional state through the application (e.g., stress, fatigue, pleasure).

[1029] Terminal: Analyzes the emotional state using the emotion engine and sends the results to the server.

[1030] Server: Analyzes the received emotional state data and adjusts the training menu based on the emotional state.

[1031] Generative AI model: Generates a new training menu that reflects the emotional state data and sends it back to the server.

[1032] Server and terminal: Provides users with tailored training menus.

[1033] 6. Push notifications to keep you on track

[1034] Server: Sets push notifications at appropriate times based on the user's training progress and emotional state (e.g., training reminders, motivational messages).

[1035] Server: Sends the configured push notification to the user's device.

[1036] On the device: Push notifications are displayed to encourage users to continue training.

[1037] Specific examples

[1038] For example, if a 25-year-old female user wants to lose body fat and gain muscle, the system works as follows:

[1039] User: Take a photo of their body and enter their height: 160cm, weight: 60kg, and target weight: 55kg.

[1040] Server: Analyzes the received information and estimates body fat percentage to be 25%.

[1041] Generative AI model: Generates a mixed menu of strength training and cardio exercise three times a week based on body data and goals.

[1042] Server and terminal: Provides the generated menu to the user.

[1043] User: After training, enter into the app that their current emotional state is fatigued.

[1044] Emotion engine: Analyzes fatigue state and sends it to the server.

[1045] Generative AI model: Reflects the fatigue state and generates a new menu including relaxing stretches and light aerobic exercise, which is sent back to the server.

[1046] Server and terminal: Provides tailored training menus to users.

[1047] This system is designed to allow users to easily receive personal training at home and continue training continuously, and by taking into account the user's emotional state, it is possible to maximize the effectiveness of the training.

[1048] The processing flow will be explained below.

[1049] Step 1:

[1050] user

[1051] Launch the application and enter your body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[1052] Step 2:

[1053] Terminal

[1054] Save the user's input information and prepare it to be sent to the server.

[1055] Step 3:

[1056] Terminal

[1057] The saved body type information and goal information of the user are transmitted to the server.

[1058] Step 4:

[1059] server

[1060] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[1061] Step 5:

[1062] server

[1063] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[1064] Step 6:

[1065] server

[1066] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[1067] Step 7:

[1068] server

[1069] The generated body shape data and target information are input into the generative AI model.

[1070] Step 8:

[1071] Generative AI Models

[1072] Based on the input data, a training menu optimal for the user is generated.

[1073] Step 9:

[1074] server

[1075] The generated training menu is received and sent to the user's terminal.

[1076] Step 10:

[1077] Terminal

[1078] Display the training menu to the user.

[1079] Step 11:

[1080] user

[1081] During or after training, enter your progress (training items completed, dates performed, weight changes, etc.) into the application.

[1082] Step 12:

[1083] Terminal

[1084] The entered progress data is sent to the server.

[1085] Step 13:

[1086] server

[1087] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[1088] Step 14:

[1089] Generative AI Models

[1090] A new training menu is generated based on the progress data and sent back to the server.

[1091] Step 15:

[1092] server

[1093] A new training menu is generated and sent to the user's device.

[1094] Step 16:

[1095] Terminal

[1096] The updated training menu is displayed to the user.

[1097] Step 17:

[1098] user

[1099] During training, you enter your emotional state (stress, fatigue, pleasure, etc.) into the application.

[1100] Step 18:

[1101] Terminal

[1102] The emotional state is analyzed using an emotion engine and the results are sent to the server.

[1103] Step 19:

[1104] server

[1105] The received emotional state data is analyzed, and a training menu is adjusted based on the emotional state.

[1106] Step 20:

[1107] Generative AI Models

[1108] A new training menu reflecting the emotional state data is generated and sent back to the server.

[1109] Step 21:

[1110] server

[1111] The adjusted training menu is received and sent to the user's device.

[1112] Step 22:

[1113] Terminal

[1114] The adjusted training menu is displayed to the user.

[1115] Step 23:

[1116] server

[1117] Set push notifications at appropriate times based on the user's training progress and emotional state (training reminders, motivational messages).

[1118] Step 24:

[1119] server

[1120] The configured push notification is sent to the user's device.

[1121] Step 25:

[1122] Terminal

[1123] Push notifications are displayed to users to encourage them to continue training.

[1124] Example 2

[1125] 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."

[1126] In modern society, it is important for people to continue training in order to maintain a healthy lifestyle. However, many people find it difficult to create appropriate training menus for themselves, and they often lack the time to continue training. Another issue is that motivation is not maintained because a lack of consideration is given to the user's emotional state during training. Therefore, there is a need for a system that provides a training menu that comprehensively takes into account the user's physique information, goals, training progress, and emotional state, thereby maximizing the effectiveness of training and maintaining motivation to continue training.

[1127] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1128] In this invention, the server includes means for inputting a user's physique information, means for generating physique data using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative artificial intelligence model, means for providing the training menu to a user terminal, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, means for recognizing the user's emotional state, means for adjusting the training menu based on the emotional state, and means for sending push notifications to encourage continuation of training. This makes it possible to provide an optimal training menu and support continuous training by comprehensively considering the user's physique, goals, training progress, and emotional state.

[1129] "User's body type information" is information that indicates the user's physical characteristics, and includes image data and numerical data such as height and weight.

[1130] "Image analysis technology" refers to technology for extracting and analyzing meaningful information from image data, such as methods for estimating body fat percentage and muscle mass.

[1131] "Body shape data" refers to numerical data such as a user's body fat percentage and muscle mass generated using image analysis technology.

[1132] "User goal information" is information indicating the goal, such as weight or body shape, that the user wants to achieve.

[1133] A "generative artificial intelligence model" refers to a machine learning model that generates an optimal training menu based on input data.

[1134] A "training menu" refers to a list of specific exercises and workouts generated based on a user's physical characteristics and goals.

[1135] "User's training progress" is information indicating the content, results, and progress of training that the user has done in the past.

[1136] "Emotional state" refers to the psychological state, such as stress, fatigue, or pleasure, that a user experiences during training.

[1137] "Push notification" refers to a function that sends messages to a user's device to remind and motivate the user to continue their training.

[1138] A "server" is a computer system that receives and analyzes user data, executes AI models, and transmits information to user devices.

[1139] "Terminal" means a device that allows a user to operate an application and input / receive information, including smartphones and tablets.

[1140] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[1141] System Overview

[1142] This system is used by users through an application and provides the following main functions:

[1143] 1. Enter and submit your body type and goal information

[1144] 2. Generating body shape data using image analysis technology

[1145] 3. Generating and providing optimal training menus using generative AI models

[1146] 4. Monitoring training progress and creating and providing new training menus

[1147] 5. Recognizing the user's emotional state using an emotion engine

[1148] 6. Adjust your training routine based on your emotional state

[1149] 7. Push notifications to encourage continued training

[1150] Hardware and software used

[1151] Terminal: A smartphone or tablet is used as a device for users to operate the application. The terminal provides the user interface and transmits data to the server.

[1152] Server: A computer system that receives, analyzes, and stores various data, and executes generative AI models. The server uses a programming language such as Python, an image analysis library such as OpenCV, and an emotion analysis engine.

[1153] Generative AI model: A generative model that generates an optimal training menu based on the user's body type data and goal information. The training menu is optimized using a machine learning algorithm.

[1154] Specific operation of the system

[1155] Enter and submit your body type and goal information

[1156] The user starts the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved on the device.

[1157] The device stores the entered information and sends it to the server as a POST request, often in JSON format.

[1158] Generating body shape data using image analysis technology

[1159] The server receives the user's body type information (image data) and goal information (text data) sent from the terminal.

[1160] The server analyzes the image data using image analysis libraries such as Python's OpenCV, and generates numerical data on body shape, such as body fat percentage and muscle mass, which allows the user to understand their specific body shape.

[1161] Creation and provision of optimal training menus

[1162] The server inputs a prompt sentence into the generative AI model using the generated body shape data and goal information. The following is a specific example.

[1163] Input data: [Height: 160cm, Weight: 60kg, Age: 25, Gender: Female, Target Weight: 55kg, Body Fat Percentage: 25%]

[1164] Emotional state data: [Fatigue: High, Stress: Low, Pleasure: Medium]

[1165] Instructing the generative AI model: Generates a training menu that is optimal for the user, and also adjusts based on their emotional state.

[1166] Based on the input data, the generative AI model generates an optimal training menu for the user, including specific exercises.

[1167] The server receives the generated training menu and transmits it to the user's terminal.

[1168] The device analyzes the training menu and displays it on the user interface.

[1169] Monitor your training progress and generate new workouts

[1170] Users enter their training progress (e.g., completed training items, training dates, weight changes, etc.) into the application and save it on their device.

[1171] The terminal transmits the progress data to the server.

[1172] The server analyzes the progress data and asks the generative AI model to optimize the next training menu. It also generates new prompts based on the progress data and inputs them into the model.

[1173] The generative AI model generates a new training menu and sends it back to the server.

[1174] The server provides a new training menu and sends it to the terminal.

[1175] The device displays the updated training menu on the user interface.

[1176] Recognizing emotional states and adjusting training menus

[1177] During training, users input their emotional state (e.g., stress, fatigue, pleasure) into the application.

[1178] The device uses an emotion engine to analyze the emotional state and transmits the results to the server.

[1179] The server analyzes the emotional state data and inputs new prompts into the generative AI model to adjust the training menu.

[1180] The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server.

[1181] The server and the terminal provide the adjusted training menu to the user.

[1182] Push notifications to keep you training

[1183] The server schedules timely push notifications based on the user's training progress and emotional state, including workout reminders and motivational messages.

[1184] The server sends the configured push notification to the user's device.

[1185] The device receives a push notification and displays it on the user interface to encourage the user to continue training.

[1186] This system allows users to receive the optimal training menu that takes into consideration their physical condition, progress, and emotional state, enabling them to easily receive personal training at home and maintain their health on an ongoing basis.

[1187] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1188] Step 1:

[1189] The user launches the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved in a local database on the device in JSON format. The specific operation is completed by keying in the data into the application's input form and pressing the submit button.

[1190] Input: User's body type and goal information

[1191] Output: Temporarily saved data in JSON format

[1192] Step 2:

[1193] The device prepares to send the entered information to the server. It sends an HTTP POST request with the saved data in a JSON-formatted payload. The HTTP request is then sent to the server. This is done by executing an API call associated with the click event of the submit button.

[1194] Input: Temporarily saved JSON format data

[1195] Output: HTTP POST request to the server

[1196] Step 3:

[1197] The server receives the user's body shape information (image data) and goal information (text data) sent from the device. Using a web framework such as Python's Flask or Django, the server receives the data at an API endpoint and stores it on a disk or in a database.

[1198] Input: JSON format data sent via HTTP POST request

[1199] Output: Body shape and goal information stored on disk and in a database

[1200] Step 4:

[1201] The server uses Python's OpenCV library to generate body shape data from the received image data. This process involves extracting the contours of specific body parts from the image and using algorithms to estimate body fat percentage and muscle mass. Specific operations are achieved by loading the received image data into OpenCV, extracting contours, and applying algorithms.

[1202] Input: Received image data

[1203] Output: Numerical body shape data including body fat percentage and muscle mass

[1204] Step 5:

[1205] The server uses the generated body shape data and goal information to input prompt sentences into the generative AI model. The generative AI model is a pre-trained machine learning model that generates an optimal training menu for the user based on the input data. Specifically, the server converts the body shape data and goal information into a specific format (prompt sentences) and sends them to the generative AI model via an API.

[1206] Input: Body type data and goal information

[1207] Output: Optimal training menu

[1208] Step 6:

[1209] The server receives the generated training menu and sends it to the user's device in JSON format. This data is sent as an HTTP response. The specific operation is to receive the results from the generative AI model and return them in format as an HTTP response.

[1210] Input: Generated training menu

[1211] Output: HTTP response to the user's device

[1212] Step 7:

[1213] The device parses the received training menu and displays it on the user interface. Specifically, it parses the received JSON data and visually displays it to the user in list or calendar format.

[1214] Input: Training menu received from the server

[1215] Output: Training menu displayed in the user interface

[1216] Step 8:

[1217] Users enter their training progress into the application and save it on their device. This includes details such as exercises completed, weight changes, and dates of exercise. Specifically, data is entered and saved on the progress input screen.

[1218] Input: Training progress data

[1219] Output: Progress data saved on the device

[1220] Step 9:

[1221] The device sends the saved progress data to the server in JSON format as an HTTP POST request. The specific operation is to click the Send Progress Data button to execute an API call.

[1222] Input: Progress data stored on the device

[1223] Output: HTTP POST request to the server

[1224] Step 10:

[1225] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu. This is done by generating prompts using the progress data and sending them to the AI ​​model. The specific operation is the process of analyzing the received progress data and generating new prompts.

[1226] Input: Received progress data

[1227] Output: New optimized training menu

[1228] Step 11:

[1229] The generative AI model generates an optimized training menu based on the new progress data and sends it back to the server. The specific operation is the process of analyzing the progress data and generating a training menu based on it.

[1230] Input: Prompt statement reflecting progress data

[1231] Output: New training menu

[1232] Step 12:

[1233] The server receives the new training menu and sends it to the user's terminal. Specifically, it formats the new training menu in JSON format and sends it to the terminal as an HTTP response.

[1234] Enter: New training menu

[1235] Output: HTTP response to the user's device

[1236] Step 13:

[1237] The device parses the updated training menu and displays it in the user interface. The specific operation is to parse the received JSON data and reflect the menu in the user interface.

[1238] Input: New training menu received from the server

[1239] Output: Display of updated training menu

[1240] Step 14:

[1241] While training, users input their emotional state (stress, fatigue, pleasure, etc.) into the app. This data is temporarily stored on the device. Specifically, users input their emotional state using sliders and buttons on the emotion input interface.

[1242] Input: Emotional state data

[1243] Output: Emotion data temporarily stored on the device

[1244] Step 15:

[1245] The device uses the emotion engine to analyze the emotional state and sends the results to the server. Specifically, it calls the emotion analysis API and sends the analysis results to the server in JSON format.

[1246] Input: Temporarily stored emotional state data

[1247] Output: Sending analysis results to the server

[1248] Step 16:

[1249] The server analyzes the received emotional state data and inputs new prompt sentences to the generative AI model to adjust the training menu. Specifically, it creates new prompt sentences based on the emotional data and sends them to the generative AI model.

[1250] Input: Received emotional state data

[1251] Output: New and adjusted training menu

[1252] Step 17:

[1253] The generative AI model generates an adjusted training menu that reflects the emotional state and sends it back to the server. The specific operation is the process of generating an adaptive exercise list using emotional data.

[1254] Input: Prompt sentence reflecting emotional state data

[1255] Output: Tailored training menu

[1256] Step 18:

[1257] The server sends the adjusted training menu to the user's terminal. Specifically, the server formats the generated menu in JSON format and sends it as an HTTP response.

[1258] Enter: a tailored training menu.

[1259] Output: HTTP response to the user's device

[1260] Step 19:

[1261] The device displays the adjusted training menu on the user interface. Specifically, it parses the received JSON data and reflects the menu on the user interface.

[1262] Enter: a tailored training menu.

[1263] Output: Display of adjusted training menu

[1264] Step 20:

[1265] The server schedules push notifications at appropriate times based on the user's training progress and emotional state, allowing training reminders and motivational messages to be sent. Specifically, the server analyzes progress and emotional data and schedules push notifications.

[1266] Input: Progress data and emotional state data

[1267] Output: Configured push notifications

[1268] Step 21:

[1269] The server sends the configured push notification to the user's device. Specifically, the server uses the push notification service to periodically deliver notification messages to the device.

[1270] Input: Configured push notification

[1271] Output: Send push notification to user device

[1272] Step 22:

[1273] The device receives the push notification and displays it in the user interface, providing reminders and motivation to encourage the user to continue training. The specific behavior is to display the received push notification as a pop-up.

[1274] Input: Push notification received from the server

[1275] Output: Push notification displayed in the user interface

[1276] Through the above processing steps, the system provides users with a personalized training menu, maximizing the effectiveness of their training and maintaining continuous motivation.

[1277] (Application example 2)

[1278] 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."

[1279] While conventional training support systems can provide training menus based on the user's physique data and goal information, they do not take into account the user's emotional state, making it difficult to maintain motivation to continue training over the long term. Furthermore, there is a lack of training support in virtual environments, making it difficult to obtain effective feedback, especially when training at home. This has resulted in an insufficient environment for efficient and continuous training.

[1280] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1281] In this invention, the server includes: means for inputting a user's physique information; means for generating physique data using image analysis technology; means for inputting the user's goal information; means for generating an optimal training menu using a generative AI model based on the physique data and goal information in a user-implemented device; means for providing the training menu to a user terminal; means for inputting the user's training progress; means for generating and providing a new training menu based on the progress; means for using a display device to provide training in a virtual environment; means for recognizing the user's emotional state and adjusting the training menu based thereon; and means for providing the adjusted training menu to the display device. This allows the user to be provided with a training menu that takes their emotional state into account, thereby maintaining motivation over the long term. Furthermore, support from a fitness instructor is realized in a virtual environment, enabling effective training even at home.

[1282] "Body type information" is data relating to the physical characteristics of the user, and specific examples include height, weight, age, sex, and image data.

[1283] "Image analysis technology" is a technology for quantifying a user's physical characteristics from acquired image data, and specific examples include estimating body fat percentage and muscle mass.

[1284] "Goal information" is data relating to the purpose or goal of training that the user wishes to achieve, and specific examples include a target weight and body fat percentage.

[1285] A "generative AI model" is an artificial intelligence model that generates specific outputs based on input data, in this context specifically for automatically generating optimal training menus.

[1286] A "training menu" is a plan that lists the specific exercises and training items that a user should do and the order in which they should do them.

[1287] A "user terminal" is an electronic device that is directly operated by the user, and in this system is used to provide training menus and input progress.

[1288] "Progress" is information that refers to the results and current status that a user has achieved in training, and specific examples include completed training items and changes in weight.

[1289] "Display device" means a visual output device used to deliver training in a virtual environment, including, for example, VR goggles and smart glasses.

[1290] "Emotional state" is information that indicates the user's current mental and emotional state, and specific examples include stress, fatigue, and pleasure.

[1291] "Adjustment" refers to the act of changing the content and order of the training menu based on specific conditions or the user's state.

[1292] This invention combines a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information, with an emotion engine. This system has the following specific configuration:

[1293] Overall structure

[1294] This system is used by users through an application and mainly uses the following hardware and software.

[1295] Hardware

[1296] Smartphone: A device on which users run applications and input information about their body shape and training progress.

[1297] VR goggles or smart glasses: display devices for delivering training in a virtual environment.

[1298] software

[1299] Image analysis library (e.g., Python's OpenCV): Software for generating body shape data from acquired images.

[1300] Generative AI model (e.g., neural network model using Keras): Software for generating optimal training menus based on body shape data and goal information.

[1301] Emotion Engine: Software that recognizes the user's emotional state and adjusts the training menu accordingly.

[1302] Processing Overview

[1303] 1. User information entry and submission

[1304] The user launches the smartphone application and enters body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen. The device saves this information and prepares it for transmission to the server. The server uses image analysis technology to generate body type data based on the received body type information and goal information.

[1305] 2. Creation and provision of training menus

[1306] The server inputs the generated body shape data and goal information into the generative AI model to generate an optimal training menu, which is then sent from the server to the user's device and displayed to the user.

[1307] 3. Monitor your training progress and regenerate your training menu

[1308] After completing a workout, the user enters their progress (e.g., completed workout items, workout dates, weight changes, etc.) into the application. This progress data is sent from the device to the server and used to optimize the next workout menu.

[1309] 4. Recognizing emotional states

[1310] Users input their emotional state through the application. The emotion engine analyzes this emotional state and sends the data to the server. Based on this data, the generative AI model generates a new training menu that reflects the emotional state, and the server then provides it to the user's device.

[1311] Specific examples

[1312] For example, if a 30-year-old male user wants to continue their fitness routine at home, the app works as follows: The user uploads an image of their body shape and enters their age, height, weight, and gender via the smartphone app. The server analyzes the image, calculates their body fat percentage, and supplies it to the generative AI model. The AI ​​model then generates an optimal training menu and provides it to the user. The user puts on VR goggles and receives training instructions from a virtual instructor. After training, the user enters their level of fatigue into the app, and the emotion engine analyzes that information and adjusts the next training menu. A new, adjusted training menu is then provided, allowing the user to continue training.

[1313] Prompt Sentence Examples

[1314] The prompt text is entered in the following format: "The user is 30 years old, 175 cm tall, weighs 80 kg, and currently has a body fat percentage of 20%. The user's goal is to increase muscle mass and reduce the body fat percentage to 15%. Please generate the optimal training menu."

[1315] As described above, this system provides an environment where users can perform personalized training at home and continue training sustainably. Furthermore, by taking into account the user's emotional state, efficient and effective training can be achieved.

[1316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1317] Step 1: Enter user information

[1318] The user starts the smartphone app and inputs their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type). The device saves this input data and prepares to send it to the server.

[1319] (Input): User's body type information and goal information

[1320] (Output): The dataset sent to the server

[1321] Step 2: Analyzing the image data

[1322] The server analyzes the image data of the body shape information received from the device using image analysis technology (such as Python's OpenCV), and derives numerical data such as body fat percentage and muscle mass.

[1323] (Input): Image data sent by the user

[1324] (Output): Body shape data as analysis results (e.g., body fat percentage, muscle mass)

[1325] Step 3: Create a training menu

[1326] The server inputs the analyzed body shape data and goal information into a generative AI model to generate an optimal training menu. The generative AI model (using Keras) automatically generates a training menu using a neural network.

[1327] (Input): Body shape data and goal information

[1328] (Output): Generated training menu

[1329] Step 4: Providing training menus

[1330] The server sends the generated training menu to the user's device, which displays the received training menu to the user and prepares to start training in the virtual environment.

[1331] (Input): Generated training menu

[1332] (Output): Training menu displayed to the user

[1333] Step 5: Enter your training progress

[1334] After completing a workout, the user uses a smartphone app to input progress information (e.g., completed workout items, workout dates, weight changes). The device saves this progress data and sends it to the server.

[1335] (Input): Training progress data

[1336] (Output): Progress dataset sent to the server

[1337] Step 6: Analyze progress data and regenerate menus

[1338] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data. The generative AI model then regenerates a new training menu based on the analysis results and sends it back to the server.

[1339] (Input): Training progress data

[1340] (Output): New training menu

[1341] Step 7: Input and analysis of emotional states

[1342] Users input their emotional state (e.g., stress, fatigue, pleasure) through the app during or after training. The device then analyzes the emotional state using an emotion engine and sends the results to the server.

[1343] (Input): Emotional state data

[1344] (Output): Parsed emotion data

[1345] Step 8: Adjust the menu with emotional data

[1346] The server adjusts the training menu according to the emotional state based on the received emotional state data. The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server. The adjusted training menu is then provided to the user's device.

[1347] (Input): Emotional state data

[1348] (Output): Adjusted training menu

[1349] Step 9: Remind me to continue the task

[1350] The server sets push notifications (e.g., training reminders, motivational messages) at appropriate times based on the user's training progress and emotional state. The server sends the set push notifications to the user's device, and the device displays the push notifications to the user.

[1351] (Input): Training progress data and emotional state data

[1352] (Output): Push notification displayed to the user

[1353] 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.

[1354] 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.

[1355] 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.

[1356] [Third embodiment]

[1357] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1358] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1359] 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).

[1360] 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.

[1361] 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.

[1362] 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).

[1363] 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. 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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."

[1369] This invention is a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information. Specific embodiments of this system will be described below.

[1370] System Overview

[1371] This system is used by users through an application and mainly provides the following functions.

[1372] 1. Enter and submit your body type and goal information

[1373] 2. Generating body shape data using image analysis technology

[1374] 3. Generating and providing optimal training menus using generative AI models

[1375] 4. Monitoring training progress and creating and providing new training menus

[1376] 5. Send push notifications to encourage continued training

[1377] Program processing

[1378] The system's programs operate through the exchange of information between the server, terminals, and users.

[1379] 1. User information entry and submission

[1380] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[1381] Terminal: Saves the user's input information and prepares it to be sent to the server.

[1382] 2. Generating body shape data using image analysis technology

[1383] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[1384] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[1385] 3. Creation and provision of optimal training menus

[1386] Server: Input the generated body shape data and goal information into the generative AI model.

[1387] Generative AI model: Generates the optimal training menu for the user based on input data.

[1388] Server: Receives the generated training menu and sends it to the user's device.

[1389] Terminal: Displays the training menu to the user.

[1390] 4. Monitoring training progress and creating and providing new training menus

[1391] User: During or after training, enter progress information (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[1392] Terminal: Sends the entered progress data to the server.

[1393] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[1394] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[1395] Server: Receives new training menus and sends them to the user's device.

[1396] Device: Display the updated training menu to the user.

[1397] 5. Push notifications to keep you on track

[1398] Server: Sets push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[1399] Server: Sends the configured push notification to the user's device.

[1400] On the device: Push notifications are displayed to encourage users to continue training.

[1401] Specific examples

[1402] For example, if a 30-year-old male user wants to lose body fat and gain muscle, the system works as follows:

[1403] User: Take a photo of their body and enter their height: 175cm, weight: 80kg, and target weight: 75kg.

[1404] Server: Analyzes the received information and estimates the body fat percentage to be 20%.

[1405] Generative AI model: Generates a mixed workout menu of strength training and cardio exercise four times a week based on body data and goals.

[1406] Server and terminal: Provides the generated menu to the user.

[1407] User: After one week, the progress report states that one workout was completed and no weight change was observed.

[1408] Server and generative AI model: Generates new menus and provides next week's menu with slight intensity adjustments.

[1409] As described above, this system is designed to allow users to easily receive personal training at home and continue training on an ongoing basis.

[1410] The processing flow will be explained below.

[1411] Step 1:

[1412] user

[1413] Launch the application and enter your body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[1414] Step 2:

[1415] Terminal

[1416] Save the user's input information and prepare it to be sent to the server.

[1417] Step 3:

[1418] Terminal

[1419] The saved body type information and goal information of the user are transmitted to the server.

[1420] Step 4:

[1421] server

[1422] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[1423] Step 5:

[1424] server

[1425] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[1426] Step 6:

[1427] server

[1428] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[1429] Step 7:

[1430] server

[1431] The generated body shape data and target information are input into the generative AI model.

[1432] Step 8:

[1433] Generative AI Models

[1434] Based on the input data, a training menu optimal for the user is generated.

[1435] Step 9:

[1436] server

[1437] The generated training menu is received and sent to the user's terminal.

[1438] Step 10:

[1439] Terminal

[1440] Display the training menu to the user.

[1441] Step 11:

[1442] user

[1443] During or after training, enter your progress (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[1444] Step 12:

[1445] Terminal

[1446] The entered progress data is sent to the server.

[1447] Step 13:

[1448] server

[1449] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[1450] Step 14:

[1451] Generative AI Models

[1452] A new training menu is generated based on the progress data and sent back to the server.

[1453] Step 15:

[1454] server

[1455] Receive new training menus and send them to the user's device.

[1456] Step 16:

[1457] Terminal

[1458] The updated training menu is displayed to the user.

[1459] Step 17:

[1460] server

[1461] Set push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[1462] Step 18:

[1463] server

[1464] The configured push notification is sent to the user's device.

[1465] Step 19:

[1466] Terminal

[1467] Push notifications are displayed to users to encourage them to continue training.

[1468] Example 1

[1469] 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."

[1470] Conventional training programs only offer general menus, making it difficult to automatically generate optimal plans for each user's body type and goals. Furthermore, they lacked functionality for continually updating training menus based on the user's progress, or for encouraging continued training. This made it difficult for many users to continue, and they were unable to achieve effective results.

[1471] 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.

[1472] In this invention, the server includes means for inputting a user's body type information, means for generating body type data based on the body type information using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative AI model based on the body type data and goal information, means for sending push notifications to encourage continuation of training, means for using image data as the user's body type information and estimating body fat percentage and muscle mass using the image analysis technology, and means for creating prompts to input the user's body type data and goal information into the generative AI model. This makes it possible to automatically generate an optimized training menu for each user, continuously update the menu according to progress, and support the continuation of training.

[1473] "Body type information" is information about an individual's physical characteristics, such as a photograph showing the user's height, weight, age, sex, and body type.

[1474] "Image analysis technology" is a technology that uses computer vision and pattern recognition technology to analyze image data and extract specific information.

[1475] "Body shape data" is quantitative data about a user's physical characteristics, such as body fat percentage and muscle mass, generated using image analysis technology.

[1476] "Goal information" refers to the physical goals that the user wants to achieve, such as a target weight or a target body shape.

[1477] A "generative AI model" is an algorithm or system that uses machine learning or artificial intelligence techniques to generate results based on specific input data.

[1478] A "training menu" is a specific training plan created based on the user's body type information and goal information.

[1479] "Push notifications" is a function that allows the server to send training reminders and motivational messages to the user's device.

[1480] A "prompt sentence" is a text sentence that gives specific instructions or questions to the generative AI model based on input data.

[1481] "User progress information" is information about the user's training progress, such as the training items the user has completed and changes in weight.

[1482] This invention is a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information. The system is used by the user through an application, and operates by exchanging information between the server, terminal, and user.

[1483] The server receives the user's body type and goal information, and uses a generative AI model to generate an optimal training menu based on this data. It also updates the training menu according to the user's progress and provides it to the user's device.

[1484] The device transmits the information input by the user to the server, displays the training menu received from the server, and transmits the user's training progress back to the server to support continuous updating of the training menu.

[1485] Specifically, the system works as follows:

[1486] 1. Entering user information

[1487] User: Launches the application and enters the following body type and goal information:

[1488] Body information: photo, height, weight, age, gender

[1489] Goal information: target weight, target body shape

[1490] 2. Data transmission

[1491] Terminal: Temporarily stores the information entered by the user to be sent to the server and then sends it as a data package.

[1492] 3. Generating body shape data through image analysis

[1493] Server: Analyzes the received image data using Python's OpenCV library and generates body shape data such as body fat percentage and muscle mass.

[1494] 4. Creation of training menu

[1495] Server: Creates prompts based on body shape data and goal information, and inputs them into the generative AI model. For example, the prompts are:

[1496] User's body data:

[1497] Height: 175cm

[1498] Weight: 80kg

[1499] Body fat percentage: 20%

[1500] Target Data:

[1501] Target weight: 75kg

[1502] Training Goal: Build muscle and burn fat

[1503] Generate the optimal training menu based on the given data.

[1504] Generative AI model: This generates optimal training regimens, such as a mix of strength and cardio exercises four times a week.

[1505] 5. Provision and display of training menus

[1506] Server: Sends the generated training menu to the user's device.

[1507] Device: Display the received training menu on the app's user interface.

[1508] 6. Monitoring and updating your training progress

[1509] User: Enter progress information into the app during or after training.

[1510] Terminal: Sends the entered progress data to the server.

[1511] Server: Analyzes the received progress data and requests the generative AI model to generate a new training menu.

[1512] Generative AI model: Generates new training menus based on your progress data.

[1513] Server: Sends new training menus to the device, which then displays them to the user.

[1514] 7. Push notifications to keep you on track

[1515] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[1516] Server: Sends the configured push notification to the user's device.

[1517] Device: Receives the push notification and displays it to the user.

[1518] In this way, the system can provide a training menu optimized for each user and provide continuous training support.

[1519] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1520] Step 1:

[1521] User information entry and submission

[1522] User: Start the application and enter their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[1523] Input: Photo, height, weight, age, gender, target weight, target body type

[1524] Output: Input body shape information and target information

[1525] Terminal: Stores the user's input information and prepares it for transmission to the server. Temporarily stores the input data and formats it into a data package.

[1526] Input: Body type and goal information entered by the user

[1527] Data processing: Formatting data (JSON, etc.)

[1528] Output: A formatted data package

[1529] Step 2:

[1530] Generating body shape data through image analysis

[1531] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[1532] Input: Data package sent from the device

[1533] Output: Received data package

[1534] Server: Using Python's OpenCV library, the received image data is analyzed and body shape data such as body fat percentage and muscle mass are generated.

[1535] Input: Received image data

[1536] Data calculation: Image analysis using OpenCV

[1537] Output: Body fat percentage, muscle mass, and other body shape data

[1538] Step 3:

[1539] Creation and provision of training menus

[1540] Server: Creates prompt sentences based on the generated body shape data and goal information, and inputs them into the generative AI model.

[1541] Input: Body shape data, goal information

[1542] Data processing: Prompt sentence creation

[1543] Output: prompt statement

[1544] Generative AI model: Generates the optimal training menu for the user based on the input prompt.

[1545] Input: prompt statement

[1546] Data calculation: Training menu generation

[1547] Output: Generated training menu

[1548] Server: Receives the generated training menu and sends it to the user's device.

[1549] Input: Generated training menu

[1550] Output: Data sent to the user's device

[1551] Terminal: Displays the training menu to the user.

[1552] Input: Training menu sent from the server

[1553] Output: Displayed in the user interface

[1554] Step 4:

[1555] Monitoring training progress and creating and providing new training menus

[1556] User: Enter progress information into the app during or after training.

[1557] Input: Training progress (training items completed, dates, changes in body weight)

[1558] Output: progress information

[1559] Terminal: Sends the entered progress data to the server.

[1560] Input: Progress data from the user

[1561] Output: Data to send to the server

[1562] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[1563] Input: Progress data

[1564] Data calculation: Analysis of progress data

[1565] Output: prompt statement

[1566] Generative AI model: Generates new training menus based on progress data.

[1567] Input: prompt statement

[1568] Data calculation: generating new training menus

[1569] Output: New training menu

[1570] Server: Receives new training menus and sends them to the user's device.

[1571] Enter: New training menu

[1572] Output: Data sent to the user's device

[1573] Device: Display the updated training menu to the user.

[1574] Input: New training menu sent from the server

[1575] Output: Displayed in the user interface

[1576] Step 5:

[1577] Push notifications to keep you training

[1578] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[1579] Input: Progress data

[1580] Data Processing: Push Notification Settings

[1581] Output: Push notification data

[1582] Server: Sends the configured push notification to the user's device.

[1583] Input: Push notification data

[1584] Output: Data sent to the user's device

[1585] Device: Show the push notification to the user.

[1586] Input: Push notification sent from the server

[1587] Output: Displayed in the user interface

[1588] (Application example 1)

[1589] 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."

[1590] The rapid increase in the use of modern self-driving vehicles has led to improved travel efficiency, but there is a lack of systems that utilize travel time to maintain health and fitness. For busy people today, finding time for fitness is particularly challenging, and there is a need for efficient training programs and their ongoing management. The present invention aims to solve this problem by providing a fitness system that can be easily used in self-driving vehicles, enabling users to train efficiently while traveling.

[1591] 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.

[1592] In this invention, the server includes means for inputting body shape information of a user, means for generating body shape data based on the body shape information using image analysis technology, means for inputting user goal information, means for generating an optimal training menu based on the body shape data and goal information using a generative artificial intelligence model, means for providing the training menu to an in-vehicle terminal of an autonomous vehicle, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, and means for displaying the training menu on an in-vehicle display or a smartphone. This enables efficient fitness training even while on the move.

[1593] "Body type information" is data that represents the body type of the user, and includes image data and information such as height and weight.

[1594] "Image analysis technology" is a technology that analyzes image data and extracts useful information, and is particularly used to generate body shape data.

[1595] "Body shape data" is numerical data about a user's body shape generated using image analysis technology, and includes body fat percentage, muscle mass, etc.

[1596] "Goal information" is information relating to the goal that the user wants to achieve, including, for example, a target weight and a target body shape.

[1597] A "generative artificial intelligence model" is a model that uses artificial intelligence to process data, and is particularly used to generate fitness programs.

[1598] A "training menu" is a fitness exercise plan that a user performs, and is generated by a generative artificial intelligence model.

[1599] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for human operation.

[1600] An "in-vehicle terminal" is a device that is installed inside an autonomous vehicle and can display and input various information.

[1601] "Progress" is data showing the results of the user's training, including the training items performed and changes in body shape.

[1602] An "in-vehicle display" is a display device installed inside an autonomous vehicle and is used to display various information.

[1603] A "smartphone" is a mobile information terminal that has multiple computer functions in addition to the functions of a mobile phone.

[1604] The present invention is a system for enabling a user to efficiently engage in fitness activities in an autonomous vehicle. The following hardware and software configurations and data processing are used to implement the present invention.

[1605] System configuration

[1606] 1. Hardware

[1607] Camera systems for autonomous vehicles: These are installed at entrances and seats to collect information.

[1608] In-car device and smartphone: Used to display the training menu and enter progress.

[1609] Server: Responsible for data analysis and running generative artificial intelligence models.

[1610] 2. Software

[1611] Image analysis library (e.g., Python's OpenCV): Analyzes collected image data and generates information about the user's body shape.

[1612] Generative AI model (e.g., PyTorch or TensorFlow): Inputs body type data and goal information to generate an optimal training menu.

[1613] Health monitoring application: Allows users to enter their body information, view training menus, and track their progress.

[1614] Data processing and calculation details

[1615] 1. Image Data Acquisition and Analysis

[1616] The server collects image data in real time from cameras inside the autonomous vehicle.

[1617] Using an image analysis library (OpenCV), the system analyzes the user's body shape information from the collected image data and estimates body fat percentage and muscle mass.

[1618] 2. Creation of training menu

[1619] The server inputs the collected body type data and the user's goal information into the generative artificial intelligence model.

[1620] Using a generative artificial intelligence model (PyTorch or TensorFlow), an optimal training menu is generated based on body shape data and goal information.

[1621] 3. Providing training menus

[1622] The server transmits the generated training menu to the in-vehicle terminal and the smartphone.

[1623] The in-car terminal and smartphone display the training menu to the user.

[1624] 4. Managing progress data and creating new menus

[1625] Users enter their training progress into their smartphone or in-car device.

[1626] The server receives the input progress data and causes the generative artificial intelligence model to generate a new training menu based on the data.

[1627] The server provides new training menus to the in-car terminal and smartphone and displays them to the user.

[1628] Specific examples

[1629] For example, if a 30-year-old male user wants to lose body fat and gain muscle after riding in an autonomous vehicle, the system will operate as follows:

[1630] The server collects body images taken by cameras at the boarding and alighting doors.

[1631] Using an image analysis library (OpenCV), the body fat percentage and weight are analyzed and sent to the server along with the target weight of 75 kg.

[1632] A generative artificial intelligence model (PyTorch or TensorFlow) generates a menu of a mix of strength training and aerobic exercise four times a week and displays it on the in-car device.

[1633] Check the training menu on the in-car display or smartphone and start training while on the move.

[1634] After one week, the training progress is recorded as one completed training session and no weight change is reported.

[1635] The server analyzes the progress data, generates a new training menu, and provides the menu for the next week.

[1636] Prompt Sentence Examples

[1637] 1. "I'm 30 years old, 175cm tall, and weigh 80kg. My goal weight is 75kg. I want to lose body fat and gain muscle mass. Please create a training menu for me, with four sessions per week."

[1638] 2. "I'm a 45-year-old woman with 30% body fat and I want to lose weight while gaining muscle mass. I want to reach my goal weight within two months."

[1639] As a result, it is possible to efficiently train for fitness even while on the move.

[1640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1641] Step 1:

[1642] After getting into an autonomous vehicle, a user captures a body image using an in-vehicle camera system. The input is video data from the in-vehicle camera, and the output is sent to a server as image data.

[1643] Step 2:

[1644] The server analyzes the received image data using an image analysis library such as OpenCV and generates body shape data such as body fat percentage and muscle mass. The input is the image data, and the output is the analyzed body shape data.

[1645] Step 3:

[1646] A user inputs target body shape information (e.g., target weight, target body shape) into a smartphone or an in-car terminal. The input is the target information from the user, and the output is the target information being sent to a server.

[1647] Step 4:

[1648] The server inputs the generated body shape data and the user's goal information into a generative artificial intelligence model (PyTorch or TensorFlow) to generate an optimal training menu. The input is body shape data and goal information, and the output is an optimal training menu.

[1649] Step 5:

[1650] The server transmits the generated training menu to the in-vehicle terminal and the smartphone. The input is the training menu, and the output is the menu displayed on the terminal.

[1651] Step 6:

[1652] The user performs fitness activities according to the training menu and inputs their progress into a smartphone or in-car device. The input is training progress data, and the output is the progress data being sent to a server.

[1653] Step 7:

[1654] The server analyzes the received progress data and generates a new training menu based on the analysis using a generative artificial intelligence model. The input is the progress data and the output is the new training menu.

[1655] Step 8:

[1656] The server again transmits the generated new training menu to the in-vehicle terminal and the smartphone, and displays it to the user. The input is the new training menu, and the output is the updated menu.

[1657] Step 9:

[1658] The server periodically sends training reminders and motivational messages via push notifications to encourage users to continue training. The input is the training schedule and motivational messages, and the output is notifications displayed on the user's smartphone or in-car device.

[1659] 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.

[1660] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[1661] System Overview

[1662] This system is used by users through an application and mainly provides the following functions.

[1663] 1. Enter and submit your body type and goal information

[1664] 2. Generating body shape data using image analysis technology

[1665] 3. Generating and providing optimal training menus using generative AI models

[1666] 4. Monitoring training progress and creating and providing new training menus

[1667] 5. Recognizing the user's emotional state using an emotion engine

[1668] 6. Adjust your training routine based on your emotional state

[1669] 7. Push notifications to encourage continued training

[1670] Program processing

[1671] The programs in this system operate through the exchange of information between the server, the terminal, and the user.

[1672] 1. User information entry and submission

[1673] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[1674] Terminal: Saves the user's input information and prepares it to be sent to the server.

[1675] 2. Generating body shape data using image analysis technology

[1676] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[1677] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[1678] 3. Creation and provision of optimal training menus

[1679] Server: Input the generated body shape data and goal information into the generative AI model.

[1680] Generative AI model: Generates the optimal training menu for the user based on input data.

[1681] Server: Receives the generated training menu and sends it to the user's device.

[1682] Terminal: Displays the training menu to the user.

[1683] 4. Monitoring training progress and creating and providing new training menus

[1684] User: During or after training, enter progress information (e.g., completed training items, dates of completion, weight changes, etc.) into the application.

[1685] Terminal: Sends the entered progress data to the server.

[1686] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[1687] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[1688] Server: Generates new training menus and sends them to the user's device.

[1689] Device: Display the updated training menu to the user.

[1690] 5. Recognizing emotional states using an emotion engine and adjusting training menus

[1691] User: During training, input their emotional state through the application (e.g., stress, fatigue, pleasure).

[1692] Terminal: Analyzes the emotional state using the emotion engine and sends the results to the server.

[1693] Server: Analyzes the received emotional state data and adjusts the training menu based on the emotional state.

[1694] Generative AI model: Generates a new training menu that reflects the emotional state data and sends it back to the server.

[1695] Server and terminal: Provides users with tailored training menus.

[1696] 6. Push notifications to keep you on track

[1697] Server: Sets push notifications at appropriate times based on the user's training progress and emotional state (e.g., training reminders, motivational messages).

[1698] Server: Sends the configured push notification to the user's device.

[1699] On the device: Push notifications are displayed to encourage users to continue training.

[1700] Specific examples

[1701] For example, if a 25-year-old female user wants to lose body fat and gain muscle, the system works as follows:

[1702] User: Take a photo of their body and enter their height: 160cm, weight: 60kg, and target weight: 55kg.

[1703] Server: Analyzes the received information and estimates body fat percentage to be 25%.

[1704] Generative AI model: Generates a mixed menu of strength training and cardio exercise three times a week based on body data and goals.

[1705] Server and terminal: Provides the generated menu to the user.

[1706] User: After training, enter into the app that their current emotional state is fatigued.

[1707] Emotion engine: Analyzes fatigue state and sends it to the server.

[1708] Generative AI model: Reflects the fatigue state and generates a new menu including relaxing stretches and light aerobic exercise, which is sent back to the server.

[1709] Server and terminal: Provides tailored training menus to users.

[1710] This system is designed to allow users to easily receive personal training at home and continue training continuously, and by taking into account the user's emotional state, it is possible to maximize the effectiveness of the training.

[1711] The processing flow will be explained below.

[1712] Step 1:

[1713] user

[1714] Launch the application and enter your body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[1715] Step 2:

[1716] Terminal

[1717] Save the user's input information and prepare it to be sent to the server.

[1718] Step 3:

[1719] Terminal

[1720] The saved body type information and goal information of the user are transmitted to the server.

[1721] Step 4:

[1722] server

[1723] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[1724] Step 5:

[1725] server

[1726] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[1727] Step 6:

[1728] server

[1729] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[1730] Step 7:

[1731] server

[1732] The generated body shape data and target information are input into the generative AI model.

[1733] Step 8:

[1734] Generative AI Models

[1735] Based on the input data, a training menu optimal for the user is generated.

[1736] Step 9:

[1737] server

[1738] The generated training menu is received and sent to the user's terminal.

[1739] Step 10:

[1740] Terminal

[1741] Display the training menu to the user.

[1742] Step 11:

[1743] user

[1744] During or after training, enter your progress (training items completed, dates performed, weight changes, etc.) into the application.

[1745] Step 12:

[1746] Terminal

[1747] The entered progress data is sent to the server.

[1748] Step 13:

[1749] server

[1750] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[1751] Step 14:

[1752] Generative AI Models

[1753] A new training menu is generated based on the progress data and sent back to the server.

[1754] Step 15:

[1755] server

[1756] A new training menu is generated and sent to the user's device.

[1757] Step 16:

[1758] Terminal

[1759] The updated training menu is displayed to the user.

[1760] Step 17:

[1761] user

[1762] During training, you enter your emotional state (stress, fatigue, pleasure, etc.) into the application.

[1763] Step 18:

[1764] Terminal

[1765] The emotional state is analyzed using an emotion engine and the results are sent to the server.

[1766] Step 19:

[1767] server

[1768] The received emotional state data is analyzed, and a training menu is adjusted based on the emotional state.

[1769] Step 20:

[1770] Generative AI Models

[1771] A new training menu reflecting the emotional state data is generated and sent back to the server.

[1772] Step 21:

[1773] server

[1774] The adjusted training menu is received and sent to the user's device.

[1775] Step 22:

[1776] Terminal

[1777] The adjusted training menu is displayed to the user.

[1778] Step 23:

[1779] server

[1780] Set push notifications at appropriate times based on the user's training progress and emotional state (training reminders, motivational messages).

[1781] Step 24:

[1782] server

[1783] The configured push notification is sent to the user's device.

[1784] Step 25:

[1785] Terminal

[1786] Push notifications are displayed to users to encourage them to continue training.

[1787] Example 2

[1788] 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."

[1789] In modern society, it is important for people to continue training in order to maintain a healthy lifestyle. However, many people find it difficult to create appropriate training menus for themselves, and they often lack the time to continue training. Another issue is that motivation is not maintained because a lack of consideration is given to the user's emotional state during training. Therefore, there is a need for a system that provides a training menu that comprehensively takes into account the user's physique information, goals, training progress, and emotional state, thereby maximizing the effectiveness of training and maintaining motivation to continue training.

[1790] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1791] In this invention, the server includes means for inputting a user's physique information, means for generating physique data using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative artificial intelligence model, means for providing the training menu to a user terminal, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, means for recognizing the user's emotional state, means for adjusting the training menu based on the emotional state, and means for sending push notifications to encourage continuation of training. This makes it possible to provide an optimal training menu and support continuous training by comprehensively considering the user's physique, goals, training progress, and emotional state.

[1792] "User's body type information" is information that indicates the user's physical characteristics, and includes image data and numerical data such as height and weight.

[1793] "Image analysis technology" refers to technology for extracting and analyzing meaningful information from image data, such as methods for estimating body fat percentage and muscle mass.

[1794] "Body shape data" refers to numerical data such as a user's body fat percentage and muscle mass generated using image analysis technology.

[1795] "User goal information" is information indicating the goal, such as weight or body shape, that the user wants to achieve.

[1796] A "generative artificial intelligence model" refers to a machine learning model that generates an optimal training menu based on input data.

[1797] A "training menu" refers to a list of specific exercises and workouts generated based on a user's physical characteristics and goals.

[1798] "User's training progress" is information indicating the content, results, and progress of training that the user has done in the past.

[1799] "Emotional state" refers to the psychological state, such as stress, fatigue, or pleasure, that a user experiences during training.

[1800] "Push notification" refers to a function that sends messages to a user's device to remind and motivate the user to continue their training.

[1801] A "server" is a computer system that receives and analyzes user data, executes AI models, and transmits information to user devices.

[1802] "Terminal" means a device that allows a user to operate an application and input / receive information, including smartphones and tablets.

[1803] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[1804] System Overview

[1805] This system is used by users through an application and provides the following main functions:

[1806] 1. Enter and submit your body type and goal information

[1807] 2. Generating body shape data using image analysis technology

[1808] 3. Generating and providing optimal training menus using generative AI models

[1809] 4. Monitoring training progress and creating and providing new training menus

[1810] 5. Recognizing the user's emotional state using an emotion engine

[1811] 6. Adjust your training routine based on your emotional state

[1812] 7. Push notifications to encourage continued training

[1813] Hardware and software used

[1814] Terminal: A smartphone or tablet is used as a device for users to operate the application. The terminal provides the user interface and transmits data to the server.

[1815] Server: A computer system that receives, analyzes, and stores various data, and executes generative AI models. The server uses a programming language such as Python, an image analysis library such as OpenCV, and an emotion analysis engine.

[1816] Generative AI model: A generative model that generates an optimal training menu based on the user's body type data and goal information. The training menu is optimized using a machine learning algorithm.

[1817] Specific operation of the system

[1818] Enter and submit your body type and goal information

[1819] The user starts the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved on the device.

[1820] The device stores the entered information and sends it to the server as a POST request, often in JSON format.

[1821] Generating body shape data using image analysis technology

[1822] The server receives the user's body type information (image data) and goal information (text data) sent from the terminal.

[1823] The server analyzes the image data using image analysis libraries such as Python's OpenCV, and generates numerical data on body shape, such as body fat percentage and muscle mass, which allows the user to understand their specific body shape.

[1824] Creation and provision of optimal training menus

[1825] The server inputs a prompt sentence into the generative AI model using the generated body shape data and goal information. The following is a specific example.

[1826] Input data: [Height: 160cm, Weight: 60kg, Age: 25, Gender: Female, Target Weight: 55kg, Body Fat Percentage: 25%]

[1827] Emotional state data: [Fatigue: High, Stress: Low, Pleasure: Medium]

[1828] Instructing the generative AI model: Generates a training menu that is optimal for the user, and also adjusts based on their emotional state.

[1829] Based on the input data, the generative AI model generates an optimal training menu for the user, including specific exercises.

[1830] The server receives the generated training menu and transmits it to the user's terminal.

[1831] The device analyzes the training menu and displays it on the user interface.

[1832] Monitor your training progress and generate new workouts

[1833] Users enter their training progress (e.g., completed training items, training dates, weight changes, etc.) into the application and save it on their device.

[1834] The terminal transmits the progress data to the server.

[1835] The server analyzes the progress data and asks the generative AI model to optimize the next training menu. It also generates new prompts based on the progress data and inputs them into the model.

[1836] The generative AI model generates a new training menu and sends it back to the server.

[1837] The server provides a new training menu and sends it to the terminal.

[1838] The device displays the updated training menu on the user interface.

[1839] Recognizing emotional states and adjusting training menus

[1840] During training, users input their emotional state (e.g., stress, fatigue, pleasure) into the application.

[1841] The device uses an emotion engine to analyze the emotional state and transmits the results to the server.

[1842] The server analyzes the emotional state data and inputs new prompts into the generative AI model to adjust the training menu.

[1843] The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server.

[1844] The server and the terminal provide the adjusted training menu to the user.

[1845] Push notifications to keep you training

[1846] The server schedules timely push notifications based on the user's training progress and emotional state, including workout reminders and motivational messages.

[1847] The server sends the configured push notification to the user's device.

[1848] The device receives a push notification and displays it on the user interface to encourage the user to continue training.

[1849] This system allows users to receive the optimal training menu that takes into consideration their physical condition, progress, and emotional state, enabling them to easily receive personal training at home and maintain their health on an ongoing basis.

[1850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1851] Step 1:

[1852] The user launches the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved in a local database on the device in JSON format. The specific operation is completed by keying in the data into the application's input form and pressing the submit button.

[1853] Input: User's body type and goal information

[1854] Output: Temporarily saved data in JSON format

[1855] Step 2:

[1856] The device prepares to send the entered information to the server. It sends an HTTP POST request with the saved data in a JSON-formatted payload. The HTTP request is then sent to the server. This is done by executing an API call associated with the click event of the submit button.

[1857] Input: Temporarily saved JSON format data

[1858] Output: HTTP POST request to the server

[1859] Step 3:

[1860] The server receives the user's body shape information (image data) and goal information (text data) sent from the device. Using a web framework such as Python's Flask or Django, the server receives the data at an API endpoint and stores it on a disk or in a database.

[1861] Input: JSON format data sent via HTTP POST request

[1862] Output: Body shape and goal information stored on disk and in a database

[1863] Step 4:

[1864] The server uses Python's OpenCV library to generate body shape data from the received image data. This process involves extracting the contours of specific body parts from the image and using algorithms to estimate body fat percentage and muscle mass. Specific operations are achieved by loading the received image data into OpenCV, extracting contours, and applying algorithms.

[1865] Input: Received image data

[1866] Output: Numerical body shape data including body fat percentage and muscle mass

[1867] Step 5:

[1868] The server uses the generated body shape data and goal information to input prompt sentences into the generative AI model. The generative AI model is a pre-trained machine learning model that generates an optimal training menu for the user based on the input data. Specifically, the server converts the body shape data and goal information into a specific format (prompt sentences) and sends them to the generative AI model via an API.

[1869] Input: Body type data and goal information

[1870] Output: Optimal training menu

[1871] Step 6:

[1872] The server receives the generated training menu and sends it to the user's device in JSON format. This data is sent as an HTTP response. The specific operation is to receive the results from the generative AI model and return them in format as an HTTP response.

[1873] Input: Generated training menu

[1874] Output: HTTP response to the user's device

[1875] Step 7:

[1876] The device parses the received training menu and displays it on the user interface. Specifically, it parses the received JSON data and visually displays it to the user in list or calendar format.

[1877] Input: Training menu received from the server

[1878] Output: Training menu displayed in the user interface

[1879] Step 8:

[1880] Users enter their training progress into the application and save it on their device. This includes details such as exercises completed, weight changes, and dates of exercise. Specifically, data is entered and saved on the progress input screen.

[1881] Input: Training progress data

[1882] Output: Progress data saved on the device

[1883] Step 9:

[1884] The device sends the saved progress data to the server in JSON format as an HTTP POST request. The specific operation is to click the Send Progress Data button to execute an API call.

[1885] Input: Progress data stored on the device

[1886] Output: HTTP POST request to the server

[1887] Step 10:

[1888] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu. This is done by generating prompts using the progress data and sending them to the AI ​​model. The specific operation is the process of analyzing the received progress data and generating new prompts.

[1889] Input: Received progress data

[1890] Output: New optimized training menu

[1891] Step 11:

[1892] The generative AI model generates an optimized training menu based on the new progress data and sends it back to the server. The specific operation is the process of analyzing the progress data and generating a training menu based on it.

[1893] Input: Prompt statement reflecting progress data

[1894] Output: New training menu

[1895] Step 12:

[1896] The server receives the new training menu and sends it to the user's terminal. Specifically, it formats the new training menu in JSON format and sends it to the terminal as an HTTP response.

[1897] Enter: New training menu

[1898] Output: HTTP response to the user's device

[1899] Step 13:

[1900] The device parses the updated training menu and displays it in the user interface. The specific operation is to parse the received JSON data and reflect the menu in the user interface.

[1901] Input: New training menu received from the server

[1902] Output: Display of updated training menu

[1903] Step 14:

[1904] While training, users input their emotional state (stress, fatigue, pleasure, etc.) into the app. This data is temporarily stored on the device. Specifically, users input their emotional state using sliders and buttons on the emotion input interface.

[1905] Input: Emotional state data

[1906] Output: Emotion data temporarily stored on the device

[1907] Step 15:

[1908] The device uses the emotion engine to analyze the emotional state and sends the results to the server. Specifically, it calls the emotion analysis API and sends the analysis results to the server in JSON format.

[1909] Input: Temporarily stored emotional state data

[1910] Output: Sending analysis results to the server

[1911] Step 16:

[1912] The server analyzes the received emotional state data and inputs new prompt sentences to the generative AI model to adjust the training menu. Specifically, it creates new prompt sentences based on the emotional data and sends them to the generative AI model.

[1913] Input: Received emotional state data

[1914] Output: New and adjusted training menu

[1915] Step 17:

[1916] The generative AI model generates an adjusted training menu that reflects the emotional state and sends it back to the server. The specific operation is the process of generating an adaptive exercise list using emotional data.

[1917] Input: Prompt sentence reflecting emotional state data

[1918] Output: Tailored training menu

[1919] Step 18:

[1920] The server sends the adjusted training menu to the user's terminal. Specifically, the server formats the generated menu in JSON format and sends it as an HTTP response.

[1921] Enter: a tailored training menu.

[1922] Output: HTTP response to the user's device

[1923] Step 19:

[1924] The device displays the adjusted training menu on the user interface. Specifically, it parses the received JSON data and reflects the menu on the user interface.

[1925] Enter: a tailored training menu.

[1926] Output: Display of adjusted training menu

[1927] Step 20:

[1928] The server schedules push notifications at appropriate times based on the user's training progress and emotional state, allowing training reminders and motivational messages to be sent. Specifically, the server analyzes progress and emotional data and schedules push notifications.

[1929] Input: Progress data and emotional state data

[1930] Output: Configured push notifications

[1931] Step 21:

[1932] The server sends the configured push notification to the user's device. Specifically, the server uses the push notification service to periodically deliver notification messages to the device.

[1933] Input: Configured push notification

[1934] Output: Send push notification to user device

[1935] Step 22:

[1936] The device receives the push notification and displays it in the user interface, providing reminders and motivation to encourage the user to continue training. The specific behavior is to display the received push notification as a pop-up.

[1937] Input: Push notification received from the server

[1938] Output: Push notification displayed in the user interface

[1939] Through the above processing steps, the system provides users with a personalized training menu, maximizing the effectiveness of their training and maintaining continuous motivation.

[1940] (Application example 2)

[1941] 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."

[1942] While conventional training support systems can provide training menus based on the user's physique data and goal information, they do not take into account the user's emotional state, making it difficult to maintain motivation to continue training over the long term. Furthermore, there is a lack of training support in virtual environments, making it difficult to obtain effective feedback, especially when training at home. This has resulted in an insufficient environment for efficient and continuous training.

[1943] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1944] In this invention, the server includes: means for inputting a user's physique information; means for generating physique data using image analysis technology; means for inputting the user's goal information; means for generating an optimal training menu using a generative AI model based on the physique data and goal information in a user-implemented device; means for providing the training menu to a user terminal; means for inputting the user's training progress; means for generating and providing a new training menu based on the progress; means for using a display device to provide training in a virtual environment; means for recognizing the user's emotional state and adjusting the training menu based thereon; and means for providing the adjusted training menu to the display device. This allows the user to be provided with a training menu that takes their emotional state into account, thereby maintaining motivation over the long term. Furthermore, support from a fitness instructor is realized in a virtual environment, enabling effective training even at home.

[1945] "Body type information" is data relating to the physical characteristics of the user, and specific examples include height, weight, age, sex, and image data.

[1946] "Image analysis technology" is a technology for quantifying a user's physical characteristics from acquired image data, and specific examples include estimating body fat percentage and muscle mass.

[1947] "Goal information" is data relating to the purpose or goal of training that the user wishes to achieve, and specific examples include a target weight and body fat percentage.

[1948] A "generative AI model" is an artificial intelligence model that generates specific outputs based on input data, in this context specifically for automatically generating optimal training menus.

[1949] A "training menu" is a plan that lists the specific exercises and training items that a user should do and the order in which they should do them.

[1950] A "user terminal" is an electronic device that is directly operated by the user, and in this system is used to provide training menus and input progress.

[1951] "Progress" is information that refers to the results and current status that a user has achieved in training, and specific examples include completed training items and changes in weight.

[1952] "Display device" means a visual output device used to deliver training in a virtual environment, including, for example, VR goggles and smart glasses.

[1953] "Emotional state" is information that indicates the user's current mental and emotional state, and specific examples include stress, fatigue, and pleasure.

[1954] "Adjustment" refers to the act of changing the content and order of the training menu based on specific conditions or the user's state.

[1955] This invention combines a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information, with an emotion engine. This system has the following specific configuration:

[1956] Overall structure

[1957] This system is used by users through an application and mainly uses the following hardware and software.

[1958] Hardware

[1959] Smartphone: A device on which users run applications and input information about their body shape and training progress.

[1960] VR goggles or smart glasses: display devices for delivering training in a virtual environment.

[1961] software

[1962] Image analysis library (e.g., Python's OpenCV): Software for generating body shape data from acquired images.

[1963] Generative AI model (e.g., neural network model using Keras): Software for generating optimal training menus based on body shape data and goal information.

[1964] Emotion Engine: Software that recognizes the user's emotional state and adjusts the training menu accordingly.

[1965] Processing Overview

[1966] 1. User information entry and submission

[1967] The user launches the smartphone application and enters body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen. The device saves this information and prepares it for transmission to the server. The server uses image analysis technology to generate body type data based on the received body type information and goal information.

[1968] 2. Creation and provision of training menus

[1969] The server inputs the generated body shape data and goal information into the generative AI model to generate an optimal training menu, which is then sent from the server to the user's device and displayed to the user.

[1970] 3. Monitor your training progress and regenerate your training menu

[1971] After completing a workout, the user enters their progress (e.g., completed workout items, workout dates, weight changes, etc.) into the application. This progress data is sent from the device to the server and used to optimize the next workout menu.

[1972] 4. Recognizing emotional states

[1973] Users input their emotional state through the application. The emotion engine analyzes this emotional state and sends the data to the server. Based on this data, the generative AI model generates a new training menu that reflects the emotional state, and the server then provides it to the user's device.

[1974] Specific examples

[1975] For example, if a 30-year-old male user wants to continue their fitness routine at home, the app works as follows: The user uploads an image of their body shape and enters their age, height, weight, and gender via the smartphone app. The server analyzes the image, calculates their body fat percentage, and supplies it to the generative AI model. The AI ​​model then generates an optimal training menu and provides it to the user. The user puts on VR goggles and receives training instructions from a virtual instructor. After training, the user enters their level of fatigue into the app, and the emotion engine analyzes that information and adjusts the next training menu. A new, adjusted training menu is then provided, allowing the user to continue training.

[1976] Prompt Sentence Examples

[1977] The prompt text is entered in the following format: "The user is 30 years old, 175 cm tall, weighs 80 kg, and currently has a body fat percentage of 20%. The user's goal is to increase muscle mass and reduce the body fat percentage to 15%. Please generate the optimal training menu."

[1978] As described above, this system provides an environment where users can perform personalized training at home and continue training sustainably. Furthermore, by taking into account the user's emotional state, efficient and effective training can be achieved.

[1979] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1980] Step 1: Enter user information

[1981] The user starts the smartphone app and inputs their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type). The device saves this input data and prepares to send it to the server.

[1982] (Input): User's body type information and goal information

[1983] (Output): The dataset sent to the server

[1984] Step 2: Analyzing the image data

[1985] The server analyzes the image data of the body shape information received from the device using image analysis technology (such as Python's OpenCV), and derives numerical data such as body fat percentage and muscle mass.

[1986] (Input): Image data sent by the user

[1987] (Output): Body shape data as analysis results (e.g., body fat percentage, muscle mass)

[1988] Step 3: Create a training menu

[1989] The server inputs the analyzed body shape data and goal information into a generative AI model to generate an optimal training menu. The generative AI model (using Keras) automatically generates the training menu using a neural network.

[1990] (Input): Body shape data and goal information

[1991] (Output): Generated training menu

[1992] Step 4: Providing training menus

[1993] The server sends the generated training menu to the user's device, which displays the received training menu to the user and prepares to start training in the virtual environment.

[1994] (Input): Generated training menu

[1995] (Output): Training menu displayed to the user

[1996] Step 5: Enter your training progress

[1997] After completing a workout, the user uses a smartphone app to input progress information (e.g., completed workout items, workout dates, weight changes). The device saves this progress data and sends it to the server.

[1998] (Input): Training progress data

[1999] (Output): Progress dataset sent to the server

[2000] Step 6: Analyze progress data and regenerate menus

[2001] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data. The generative AI model then regenerates a new training menu based on the analysis results and sends it back to the server.

[2002] (Input): Training progress data

[2003] (Output): New training menu

[2004] Step 7: Input and analysis of emotional states

[2005] Users input their emotional state (e.g., stress, fatigue, pleasure) through the app during or after training. The device then analyzes the emotional state using an emotion engine and sends the results to the server.

[2006] (Input): Emotional state data

[2007] (Output): Parsed emotion data

[2008] Step 8: Adjust the menu with emotional data

[2009] The server adjusts the training menu according to the emotional state based on the received emotional state data. The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server. The adjusted training menu is then provided to the user's device.

[2010] (Input): Emotional state data

[2011] (Output): Adjusted training menu

[2012] Step 9: Remind me to continue the task

[2013] The server sets push notifications (e.g., training reminders, motivational messages) at appropriate times based on the user's training progress and emotional state. The server sends the set push notifications to the user's device, and the device displays the push notifications to the user.

[2014] (Input): Training progress data and emotional state data

[2015] (Output): Push notification displayed to the user

[2016] 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.

[2017] 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.

[2018] 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.

[2019] [Fourth embodiment]

[2020] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2021] 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.

[2022] 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).

[2023] 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.

[2024] 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.

[2025] 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).

[2026] 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. 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.

[2027] 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.

[2028] 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.

[2029] 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.

[2030] 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.

[2031] 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.

[2032] 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."

[2033] This invention is a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information. Specific embodiments of this system will be described below.

[2034] System Overview

[2035] This system is used by users through an application and mainly provides the following functions.

[2036] 1. Enter and submit your body type and goal information

[2037] 2. Generating body shape data using image analysis technology

[2038] 3. Generating and providing optimal training menus using generative AI models

[2039] 4. Monitoring training progress and creating and providing new training menus

[2040] 5. Send push notifications to encourage continued training

[2041] Program processing

[2042] The system's programs operate through the exchange of information between the server, terminals, and users.

[2043] 1. User information entry and submission

[2044] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[2045] Terminal: Saves the user's input information and prepares it to be sent to the server.

[2046] 2. Generating body shape data using image analysis technology

[2047] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[2048] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[2049] 3. Creation and provision of optimal training menus

[2050] Server: Input the generated body shape data and goal information into the generative AI model.

[2051] Generative AI model: Generates the optimal training menu for the user based on input data.

[2052] Server: Receives the generated training menu and sends it to the user's device.

[2053] Terminal: Displays the training menu to the user.

[2054] 4. Monitoring training progress and creating and providing new training menus

[2055] User: During or after training, enter progress information (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[2056] Terminal: Sends the entered progress data to the server.

[2057] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[2058] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[2059] Server: Receives new training menus and sends them to the user's device.

[2060] Device: Display the updated training menu to the user.

[2061] 5. Push notifications to keep you on track

[2062] Server: Sets push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[2063] Server: Sends the configured push notification to the user's device.

[2064] On the device: Push notifications are displayed to encourage users to continue training.

[2065] Specific examples

[2066] For example, if a 30-year-old male user wants to lose body fat and gain muscle, the system works as follows:

[2067] User: Take a photo of their body and enter their height: 175cm, weight: 80kg, and target weight: 75kg.

[2068] Server: Analyzes the received information and estimates the body fat percentage to be 20%.

[2069] Generative AI model: Generates a mixed workout menu of strength training and cardio exercise four times a week based on body data and goals.

[2070] Server and terminal: Provides the generated menu to the user.

[2071] User: After one week, the progress report states that one workout was completed and no weight change was observed.

[2072] Server and generative AI model: Generates new menus and provides next week's menu with slight intensity adjustments.

[2073] As described above, this system is designed to allow users to easily receive personal training at home and continue training on an ongoing basis.

[2074] The processing flow will be explained below.

[2075] Step 1:

[2076] user

[2077] Launch the application and enter your body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[2078] Step 2:

[2079] Terminal

[2080] Save the user's input information and prepare it to be sent to the server.

[2081] Step 3:

[2082] Terminal

[2083] The saved body type information and goal information of the user are transmitted to the server.

[2084] Step 4:

[2085] server

[2086] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[2087] Step 5:

[2088] server

[2089] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[2090] Step 6:

[2091] server

[2092] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[2093] Step 7:

[2094] server

[2095] The generated body shape data and target information are input into the generative AI model.

[2096] Step 8:

[2097] Generative AI Models

[2098] Based on the input data, a training menu optimal for the user is generated.

[2099] Step 9:

[2100] server

[2101] The generated training menu is received and sent to the user's terminal.

[2102] Step 10:

[2103] Terminal

[2104] Display the training menu to the user.

[2105] Step 11:

[2106] user

[2107] During or after training, enter your progress (e.g., completed training items, dates of training, changes in body weight, etc.) into the application.

[2108] Step 12:

[2109] Terminal

[2110] The entered progress data is sent to the server.

[2111] Step 13:

[2112] server

[2113] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[2114] Step 14:

[2115] Generative AI Models

[2116] A new training menu is generated based on the progress data and sent back to the server.

[2117] Step 15:

[2118] server

[2119] Receive new training menus and send them to the user's device.

[2120] Step 16:

[2121] Terminal

[2122] The updated training menu is displayed to the user.

[2123] Step 17:

[2124] server

[2125] Set push notifications at appropriate times based on the user's training progress (e.g., training reminders, motivational messages).

[2126] Step 18:

[2127] server

[2128] The configured push notification is sent to the user's device.

[2129] Step 19:

[2130] Terminal

[2131] Push notifications are displayed to users to encourage them to continue training.

[2132] Example 1

[2133] 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."

[2134] Conventional training programs only offer general menus, making it difficult to automatically generate optimal plans for each user's body type and goals. Furthermore, they lacked functionality for continually updating training menus based on the user's progress, or for encouraging continued training. This made it difficult for many users to continue, and they were unable to achieve effective results.

[2135] 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.

[2136] In this invention, the server includes means for inputting a user's body type information, means for generating body type data based on the body type information using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative AI model based on the body type data and goal information, means for sending push notifications to encourage continuation of training, means for using image data as the user's body type information and estimating body fat percentage and muscle mass using the image analysis technology, and means for creating prompts to input the user's body type data and goal information into the generative AI model. This makes it possible to automatically generate an optimized training menu for each user, continuously update the menu according to progress, and support the continuation of training.

[2137] "Body type information" is information about an individual's physical characteristics, such as a photograph showing the user's height, weight, age, sex, and body type.

[2138] "Image analysis technology" is a technology that uses computer vision and pattern recognition technology to analyze image data and extract specific information.

[2139] "Body shape data" is quantitative data about a user's physical characteristics, such as body fat percentage and muscle mass, generated using image analysis technology.

[2140] "Goal information" refers to the physical goals that the user wants to achieve, such as a target weight or a target body shape.

[2141] A "generative AI model" is an algorithm or system that uses machine learning or artificial intelligence techniques to generate results based on specific input data.

[2142] A "training menu" is a specific training plan created based on the user's body type information and goal information.

[2143] "Push notifications" is a function that allows the server to send training reminders and motivational messages to the user's device.

[2144] A "prompt sentence" is a text sentence that gives specific instructions or questions to the generative AI model based on input data.

[2145] "User progress information" is information about the user's training progress, such as the training items the user has completed and changes in weight.

[2146] This invention is a system that automatically generates and provides optimal training menus using a generative AI model based on the user's physique information and goal information. The system is used by the user through an application, and operates by exchanging information between the server, terminal, and user.

[2147] The server receives the user's body type and goal information, and uses a generative AI model to generate an optimal training menu based on this data. It also updates the training menu according to the user's progress and provides it to the user's device.

[2148] The device transmits the information input by the user to the server, displays the training menu received from the server, and transmits the user's training progress back to the server to support continuous updating of the training menu.

[2149] Specifically, the system works as follows:

[2150] 1. Entering user information

[2151] User: Launches the application and enters the following body type and goal information:

[2152] Body information: photo, height, weight, age, gender

[2153] Goal information: target weight, target body shape

[2154] 2. Data transmission

[2155] Terminal: Temporarily stores the information entered by the user to be sent to the server and then sends it as a data package.

[2156] 3. Generating body shape data through image analysis

[2157] Server: Analyzes the received image data using Python's OpenCV library and generates body shape data such as body fat percentage and muscle mass.

[2158] 4. Creation of training menu

[2159] Server: Creates prompts based on body shape data and goal information, and inputs them into the generative AI model. For example, the prompts are:

[2160] User's body data:

[2161] Height: 175cm

[2162] Weight: 80kg

[2163] Body fat percentage: 20%

[2164] Target Data:

[2165] Target weight: 75kg

[2166] Training Goal: Build muscle and burn fat

[2167] Generate the optimal training menu based on the given data.

[2168] Generative AI model: This generates optimal training regimens, such as a mix of strength and cardio exercises four times a week.

[2169] 5. Provision and display of training menus

[2170] Server: Sends the generated training menu to the user's device.

[2171] Device: Display the received training menu on the app's user interface.

[2172] 6. Monitoring and updating your training progress

[2173] User: Enter progress information into the app during or after training.

[2174] Terminal: Sends the entered progress data to the server.

[2175] Server: Analyzes the received progress data and requests the generative AI model to generate a new training menu.

[2176] Generative AI model: Generates new training menus based on your progress data.

[2177] Server: Sends new training menus to the device, which then displays them to the user.

[2178] 7. Push notifications to keep you on track

[2179] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[2180] Server: Sends the configured push notification to the user's device.

[2181] Device: Receives the push notification and displays it to the user.

[2182] In this way, the system can provide a training menu optimized for each user and provide continuous training support.

[2183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2184] Step 1:

[2185] User information entry and submission

[2186] User: Start the application and enter their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[2187] Input: Photo, height, weight, age, gender, target weight, target body type

[2188] Output: Input body shape information and target information

[2189] Terminal: Stores the user's input information and prepares it for transmission to the server. Temporarily stores the input data and formats it into a data package.

[2190] Input: Body type and goal information entered by the user

[2191] Data processing: Formatting data (JSON, etc.)

[2192] Output: A formatted data package

[2193] Step 2:

[2194] Generating body shape data through image analysis

[2195] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[2196] Input: Data package sent from the device

[2197] Output: Received data package

[2198] Server: Using Python's OpenCV library, the received image data is analyzed and body shape data such as body fat percentage and muscle mass are generated.

[2199] Input: Received image data

[2200] Data calculation: Image analysis using OpenCV

[2201] Output: Body fat percentage, muscle mass, and other body shape data

[2202] Step 3:

[2203] Creation and provision of training menus

[2204] Server: Creates prompt sentences based on the generated body shape data and goal information, and inputs them into the generative AI model.

[2205] Input: Body shape data, goal information

[2206] Data processing: Prompt sentence creation

[2207] Output: prompt statement

[2208] Generative AI model: Generates the optimal training menu for the user based on the input prompt.

[2209] Input: prompt statement

[2210] Data calculation: Training menu generation

[2211] Output: Generated training menu

[2212] Server: Receives the generated training menu and sends it to the user's device.

[2213] Input: Generated training menu

[2214] Output: Data sent to the user's device

[2215] Terminal: Displays the training menu to the user.

[2216] Input: Training menu sent from the server

[2217] Output: Displayed in the user interface

[2218] Step 4:

[2219] Monitoring training progress and creating and providing new training menus

[2220] User: Enter progress information into the app during or after training.

[2221] Input: Training progress (training items completed, dates, changes in body weight)

[2222] Output: progress information

[2223] Terminal: Sends the entered progress data to the server.

[2224] Input: Progress data from the user

[2225] Output: Data to send to the server

[2226] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[2227] Input: Progress data

[2228] Data calculation: Analysis of progress data

[2229] Output: prompt statement

[2230] Generative AI model: Generates new training menus based on progress data.

[2231] Input: prompt statement

[2232] Data calculation: generating new training menus

[2233] Output: New training menu

[2234] Server: Receives new training menus and sends them to the user's device.

[2235] Enter: New training menu

[2236] Output: Data sent to the user's device

[2237] Device: Display the updated training menu to the user.

[2238] Input: New training menu sent from the server

[2239] Output: Displayed in the user interface

[2240] Step 5:

[2241] Push notifications to keep you training

[2242] Server: Based on the user's training progress, set push notifications such as training reminders and motivational messages at appropriate times.

[2243] Input: Progress data

[2244] Data Processing: Push Notification Settings

[2245] Output: Push notification data

[2246] Server: Sends the configured push notification to the user's device.

[2247] Input: Push notification data

[2248] Output: Data sent to the user's device

[2249] Device: Show the push notification to the user.

[2250] Input: Push notification sent from the server

[2251] Output: Displayed in the user interface

[2252] (Application example 1)

[2253] 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."

[2254] The rapid increase in the use of modern self-driving vehicles has led to improved travel efficiency, but there is a lack of systems that utilize travel time to maintain health and fitness. For busy people today, finding time for fitness is particularly challenging, and there is a need for efficient training programs and their ongoing management. The present invention aims to solve this problem by providing a fitness system that can be easily used in self-driving vehicles, enabling users to train efficiently while traveling.

[2255] 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.

[2256] In this invention, the server includes means for inputting body shape information of a user, means for generating body shape data based on the body shape information using image analysis technology, means for inputting user goal information, means for generating an optimal training menu based on the body shape data and goal information using a generative artificial intelligence model, means for providing the training menu to an in-vehicle terminal of an autonomous vehicle, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, and means for displaying the training menu on an in-vehicle display or a smartphone. This enables efficient fitness training even while on the move.

[2257] "Body type information" is data that represents the body type of the user, and includes image data and information such as height and weight.

[2258] "Image analysis technology" is a technology that analyzes image data and extracts useful information, and is particularly used to generate body shape data.

[2259] "Body shape data" is numerical data about a user's body shape generated using image analysis technology, and includes body fat percentage, muscle mass, etc.

[2260] "Goal information" is information relating to the goal that the user wants to achieve, including, for example, a target weight and a target body shape.

[2261] A "generative artificial intelligence model" is a model that uses artificial intelligence to process data, and is particularly used to generate fitness programs.

[2262] A "training menu" is a fitness exercise plan that a user performs, and is generated by a generative artificial intelligence model.

[2263] An "autonomous vehicle" is a vehicle that can drive autonomously without the need for human operation.

[2264] An "in-vehicle terminal" is a device that is installed inside an autonomous vehicle and can display and input various information.

[2265] "Progress" is data showing the results of the user's training, including the training items performed and changes in body shape.

[2266] An "in-vehicle display" is a display device installed inside an autonomous vehicle and is used to display various information.

[2267] A "smartphone" is a mobile information terminal that has multiple computer functions in addition to the functions of a mobile phone.

[2268] The present invention is a system for enabling a user to efficiently engage in fitness activities in an autonomous vehicle. The following hardware and software configurations and data processing are used to implement the present invention.

[2269] System configuration

[2270] 1. Hardware

[2271] Camera systems for autonomous vehicles: These are installed at entrances and seats to collect information.

[2272] In-car device and smartphone: Used to display the training menu and enter progress.

[2273] Server: Responsible for data analysis and running generative artificial intelligence models.

[2274] 2. Software

[2275] Image analysis library (e.g., Python's OpenCV): Analyzes collected image data and generates information about the user's body shape.

[2276] Generative AI model (e.g., PyTorch or TensorFlow): Inputs body type data and goal information to generate an optimal training menu.

[2277] Health monitoring application: Allows users to enter their body information, view training menus, and track their progress.

[2278] Data processing and calculation details

[2279] 1. Image Data Acquisition and Analysis

[2280] The server collects image data in real time from cameras inside the autonomous vehicle.

[2281] Using an image analysis library (OpenCV), the system analyzes the user's body shape information from the collected image data and estimates body fat percentage and muscle mass.

[2282] 2. Creation of training menu

[2283] The server inputs the collected body type data and the user's goal information into the generative artificial intelligence model.

[2284] Using a generative artificial intelligence model (PyTorch or TensorFlow), an optimal training menu is generated based on body shape data and goal information.

[2285] 3. Providing training menus

[2286] The server transmits the generated training menu to the in-vehicle terminal and the smartphone.

[2287] The in-car terminal and smartphone display the training menu to the user.

[2288] 4. Managing progress data and creating new menus

[2289] Users enter their training progress into their smartphone or in-car device.

[2290] The server receives the input progress data and causes the generative artificial intelligence model to generate a new training menu based on the data.

[2291] The server provides new training menus to the in-car terminal and smartphone and displays them to the user.

[2292] Specific examples

[2293] For example, if a 30-year-old male user wants to lose body fat and gain muscle after riding in an autonomous vehicle, the system will operate as follows:

[2294] The server collects body images taken by cameras at the boarding and alighting doors.

[2295] Using an image analysis library (OpenCV), the body fat percentage and weight are analyzed and sent to the server along with the target weight of 75 kg.

[2296] A generative artificial intelligence model (PyTorch or TensorFlow) generates a menu of a mix of strength training and aerobic exercise four times a week and displays it on the in-car device.

[2297] Check the training menu on the in-car display or smartphone and start training while on the move.

[2298] After one week, the training progress is recorded as one completed training session and no weight change is reported.

[2299] The server analyzes the progress data, generates a new training menu, and provides the menu for the next week.

[2300] Prompt Sentence Examples

[2301] 1. "I'm 30 years old, 175cm tall, and weigh 80kg. My goal weight is 75kg. I want to lose body fat and gain muscle mass. Please create a training menu for me, with four sessions per week."

[2302] 2. "I'm a 45-year-old woman with 30% body fat and I want to lose weight while gaining muscle mass. I want to reach my goal weight within two months."

[2303] As a result, it is possible to efficiently train for fitness even while on the move.

[2304] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2305] Step 1:

[2306] After getting into an autonomous vehicle, a user captures a body image using an in-vehicle camera system. The input is video data from the in-vehicle camera, and the output is sent to a server as image data.

[2307] Step 2:

[2308] The server analyzes the received image data using an image analysis library such as OpenCV and generates body shape data such as body fat percentage and muscle mass. The input is the image data, and the output is the analyzed body shape data.

[2309] Step 3:

[2310] A user inputs target body shape information (e.g., target weight, target body shape) into a smartphone or an in-car terminal. The input is the target information from the user, and the output is the target information being sent to a server.

[2311] Step 4:

[2312] The server inputs the generated body shape data and the user's goal information into a generative artificial intelligence model (PyTorch or TensorFlow) to generate an optimal training menu. The input is body shape data and goal information, and the output is an optimal training menu.

[2313] Step 5:

[2314] The server transmits the generated training menu to the in-vehicle terminal and the smartphone. The input is the training menu, and the output is the menu displayed on the terminal.

[2315] Step 6:

[2316] The user performs fitness activities according to the training menu and inputs their progress into a smartphone or in-car device. The input is training progress data, and the output is the progress data being sent to a server.

[2317] Step 7:

[2318] The server analyzes the received progress data and generates a new training menu based on the analysis using a generative artificial intelligence model. The input is the progress data and the output is the new training menu.

[2319] Step 8:

[2320] The server again transmits the generated new training menu to the in-vehicle terminal and the smartphone, and displays it to the user. The input is the new training menu, and the output is the updated menu.

[2321] Step 9:

[2322] The server periodically sends training reminders and motivational messages via push notifications to encourage users to continue training. The input is the training schedule and motivational messages, and the output is notifications displayed on the user's smartphone or in-car device.

[2323] 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.

[2324] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[2325] System Overview

[2326] This system is used by users through an application and mainly provides the following functions.

[2327] 1. Enter and submit your body type and goal information

[2328] 2. Generating body shape data using image analysis technology

[2329] 3. Generating and providing optimal training menus using generative AI models

[2330] 4. Monitoring training progress and creating and providing new training menus

[2331] 5. Recognizing the user's emotional state using an emotion engine

[2332] 6. Adjust your training routine based on your emotional state

[2333] 7. Push notifications to encourage continued training

[2334] Program processing

[2335] The programs in this system operate through the exchange of information between the server, the terminal, and the user.

[2336] 1. User information entry and submission

[2337] User: Start the application and enter their body type information (e.g., photo, height, weight, age, gender) and goal information (e.g., target weight, target body type) on the initial setup screen.

[2338] Terminal: Saves the user's input information and prepares it to be sent to the server.

[2339] 2. Generating body shape data using image analysis technology

[2340] Server: Receives the user's body shape information (image) and goal information (text data) sent from the device.

[2341] Server: Using an image analysis library such as Python's OpenCV, the received image data is analyzed to generate numerical data such as body fat percentage and muscle mass.

[2342] 3. Creation and provision of optimal training menus

[2343] Server: Input the generated body shape data and goal information into the generative AI model.

[2344] Generative AI model: Generates the optimal training menu for the user based on input data.

[2345] Server: Receives the generated training menu and sends it to the user's device.

[2346] Terminal: Displays the training menu to the user.

[2347] 4. Monitoring training progress and creating and providing new training menus

[2348] User: During or after training, enter progress information (e.g., completed training items, dates of completion, weight changes, etc.) into the application.

[2349] Terminal: Sends the entered progress data to the server.

[2350] Server: Analyzes the received progress data and requests the generative AI model to optimize the next training menu based on that data.

[2351] Generative AI model: Generates a new training menu based on the progress data and sends it back to the server.

[2352] Server: Generates new training menus and sends them to the user's device.

[2353] Device: Display the updated training menu to the user.

[2354] 5. Recognizing emotional states using an emotion engine and adjusting training menus

[2355] User: During training, input their emotional state through the application (e.g., stress, fatigue, pleasure).

[2356] Terminal: Analyzes the emotional state using the emotion engine and sends the results to the server.

[2357] Server: Analyzes the received emotional state data and adjusts the training menu based on the emotional state.

[2358] Generative AI model: Generates a new training menu that reflects the emotional state data and sends it back to the server.

[2359] Server and terminal: Provides users with tailored training menus.

[2360] 6. Push notifications to keep you on track

[2361] Server: Sets push notifications at appropriate times based on the user's training progress and emotional state (e.g., training reminders, motivational messages).

[2362] Server: Sends the configured push notification to the user's device.

[2363] On the device: Push notifications are displayed to encourage users to continue training.

[2364] Specific examples

[2365] For example, if a 25-year-old female user wants to lose body fat and gain muscle, the system works as follows:

[2366] User: Take a photo of their body and enter their height: 160cm, weight: 60kg, and target weight: 55kg.

[2367] Server: Analyzes the received information and estimates body fat percentage to be 25%.

[2368] Generative AI model: Generates a mixed menu of strength training and cardio exercise three times a week based on body data and goals.

[2369] Server and terminal: Provides the generated menu to the user.

[2370] User: After training, enter into the app that their current emotional state is fatigued.

[2371] Emotion engine: Analyzes fatigue state and sends it to the server.

[2372] Generative AI model: Reflects the fatigue state and generates a new menu including relaxing stretches and light aerobic exercise, which is sent back to the server.

[2373] Server and terminal: Provides tailored training menus to users.

[2374] This system is designed to allow users to easily receive personal training at home and continue training continuously, and by taking into account the user's emotional state, it is possible to maximize the effectiveness of the training.

[2375] The processing flow will be explained below.

[2376] Step 1:

[2377] user

[2378] Launch the application and enter your body type information (photo, height, weight, age, gender) and goal information (target weight, target body type) on the initial setup screen.

[2379] Step 2:

[2380] Terminal

[2381] Save the user's input information and prepare it to be sent to the server.

[2382] Step 3:

[2383] Terminal

[2384] The saved body type information and goal information of the user are transmitted to the server.

[2385] Step 4:

[2386] server

[2387] The user's body shape information (image) and goal information (text data) sent from the terminal are received.

[2388] Step 5:

[2389] server

[2390] The received image data is analyzed using an image analysis library such as Python's OpenCV to generate the user's body shape data (body fat percentage and muscle mass).

[2391] Step 6:

[2392] server

[2393] The received goal information (target weight, target body shape) is analyzed and converted into numerical data.

[2394] Step 7:

[2395] server

[2396] The generated body shape data and target information are input into the generative AI model.

[2397] Step 8:

[2398] Generative AI Models

[2399] Based on the input data, a training menu optimal for the user is generated.

[2400] Step 9:

[2401] server

[2402] The generated training menu is received and sent to the user's terminal.

[2403] Step 10:

[2404] Terminal

[2405] Display the training menu to the user.

[2406] Step 11:

[2407] user

[2408] During or after training, enter your progress (training items completed, dates performed, weight changes, etc.) into the application.

[2409] Step 12:

[2410] Terminal

[2411] The entered progress data is sent to the server.

[2412] Step 13:

[2413] server

[2414] The received progress data is analyzed and the generative AI model is asked to optimize the next training menu based on that data.

[2415] Step 14:

[2416] Generative AI Models

[2417] A new training menu is generated based on the progress data and sent back to the server.

[2418] Step 15:

[2419] server

[2420] A new training menu is generated and sent to the user's device.

[2421] Step 16:

[2422] Terminal

[2423] The updated training menu is displayed to the user.

[2424] Step 17:

[2425] user

[2426] During training, you enter your emotional state (stress, fatigue, pleasure, etc.) into the application.

[2427] Step 18:

[2428] Terminal

[2429] The emotional state is analyzed using an emotion engine and the results are sent to the server.

[2430] Step 19:

[2431] server

[2432] The received emotional state data is analyzed, and a training menu is adjusted based on the emotional state.

[2433] Step 20:

[2434] Generative AI Models

[2435] A new training menu reflecting the emotional state data is generated and sent back to the server.

[2436] Step 21:

[2437] server

[2438] The adjusted training menu is received and sent to the user's device.

[2439] Step 22:

[2440] Terminal

[2441] The adjusted training menu is displayed to the user.

[2442] Step 23:

[2443] server

[2444] Set push notifications at appropriate times based on the user's training progress and emotional state (training reminders, motivational messages).

[2445] Step 24:

[2446] server

[2447] The configured push notification is sent to the user's device.

[2448] Step 25:

[2449] Terminal

[2450] Push notifications are displayed to users to encourage them to continue training.

[2451] Example 2

[2452] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2453] In modern society, it is important for people to continue training in order to maintain a healthy lifestyle. However, many people find it difficult to create appropriate training menus for themselves, and they often lack the time to continue training. Another issue is that motivation is not maintained because a lack of consideration is given to the user's emotional state during training. Therefore, there is a need for a system that provides a training menu that comprehensively takes into account the user's physique information, goals, training progress, and emotional state, thereby maximizing the effectiveness of training and maintaining motivation to continue training.

[2454] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2455] In this invention, the server includes means for inputting a user's physique information, means for generating physique data using image analysis technology, means for inputting the user's goal information, means for generating an optimal training menu using a generative artificial intelligence model, means for providing the training menu to a user terminal, means for inputting the user's training progress, means for generating and providing a new training menu based on the progress, means for recognizing the user's emotional state, means for adjusting the training menu based on the emotional state, and means for sending push notifications to encourage continuation of training. This makes it possible to provide an optimal training menu and support continuous training by comprehensively considering the user's physique, goals, training progress, and emotional state.

[2456] "User's body type information" is information that indicates the user's physical characteristics, and includes image data and numerical data such as height and weight.

[2457] "Image analysis technology" refers to technology for extracting and analyzing meaningful information from image data, such as methods for estimating body fat percentage and muscle mass.

[2458] "Body shape data" refers to numerical data such as a user's body fat percentage and muscle mass generated using image analysis technology.

[2459] "User goal information" is information indicating the goal, such as weight or body shape, that the user wants to achieve.

[2460] A "generative artificial intelligence model" refers to a machine learning model that generates an optimal training menu based on input data.

[2461] A "training menu" refers to a list of specific exercises and workouts generated based on a user's physical characteristics and goals.

[2462] "User's training progress" is information indicating the content, results, and progress of training that the user has done in the past.

[2463] "Emotional state" refers to the psychological state, such as stress, fatigue, or pleasure, that a user experiences during training.

[2464] "Push notification" refers to a function that sends messages to a user's device to remind and motivate the user to continue their training.

[2465] A "server" is a computer system that receives and analyzes user data, executes AI models, and transmits information to user devices.

[2466] "Terminal" means a device that allows a user to operate an application and input / receive information, including smartphones and tablets.

[2467] This invention combines a system that automatically generates and provides an optimal training menu using a generative AI model based on a user's physique information and goal information, with an emotion engine that recognizes the user's emotional state. Specific embodiments of this system are described below.

[2468] System Overview

[2469] This system is used by users through an application and provides the following main functions:

[2470] 1. Enter and submit your body type and goal information

[2471] 2. Generating body shape data using image analysis technology

[2472] 3. Generating and providing optimal training menus using generative AI models

[2473] 4. Monitoring training progress and creating and providing new training menus

[2474] 5. Recognizing the user's emotional state using an emotion engine

[2475] 6. Adjust your training routine based on your emotional state

[2476] 7. Push notifications to encourage continued training

[2477] Hardware and software used

[2478] Terminal: A smartphone or tablet is used as a device for users to operate the application. The terminal provides the user interface and transmits data to the server.

[2479] Server: A computer system that receives, analyzes, and stores various data, and executes generative AI models. The server uses a programming language such as Python, an image analysis library such as OpenCV, and an emotion analysis engine.

[2480] Generative AI model: A generative model that generates an optimal training menu based on the user's body type data and goal information. The training menu is optimized using a machine learning algorithm.

[2481] Specific operation of the system

[2482] Enter and submit your body type and goal information

[2483] The user starts the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved on the device.

[2484] The device stores the entered information and sends it to the server as a POST request, often in JSON format.

[2485] Generating body shape data using image analysis technology

[2486] The server receives the user's body type information (image data) and goal information (text data) sent from the terminal.

[2487] The server analyzes the image data using image analysis libraries such as Python's OpenCV, and generates numerical data on body shape, such as body fat percentage and muscle mass, which allows the user to understand their specific body shape.

[2488] Creation and provision of optimal training menus

[2489] The server inputs a prompt sentence into the generative AI model using the generated body shape data and goal information. The following is a specific example.

[2490] Input data: [Height: 160cm, Weight: 60kg, Age: 25, Gender: Female, Target Weight: 55kg, Body Fat Percentage: 25%]

[2491] Emotional state data: [Fatigue: High, Stress: Low, Pleasure: Medium]

[2492] Instructing the generative AI model: Generates a training menu that is optimal for the user, and also adjusts based on their emotional state.

[2493] Based on the input data, the generative AI model generates an optimal training menu for the user, including specific exercises.

[2494] The server receives the generated training menu and transmits it to the user's terminal.

[2495] The device analyzes the training menu and displays it on the user interface.

[2496] Monitor your training progress and generate new workouts

[2497] Users enter their training progress (e.g., completed training items, training dates, weight changes, etc.) into the application and save it on their device.

[2498] The terminal transmits the progress data to the server.

[2499] The server analyzes the progress data and asks the generative AI model to optimize the next training menu. It also generates new prompts based on the progress data and inputs them into the model.

[2500] The generative AI model generates a new training menu and sends it back to the server.

[2501] The server provides a new training menu and sends it to the terminal.

[2502] The device displays the updated training menu on the user interface.

[2503] Recognizing emotional states and adjusting training menus

[2504] During training, users input their emotional state (e.g., stress, fatigue, pleasure) into the application.

[2505] The device uses an emotion engine to analyze the emotional state and transmits the results to the server.

[2506] The server analyzes the emotional state data and inputs new prompts into the generative AI model to adjust the training menu.

[2507] The generative AI model generates a new training menu that reflects the emotional state data and sends it back to the server.

[2508] The server and the terminal provide the adjusted training menu to the user.

[2509] Push notifications to keep you training

[2510] The server schedules timely push notifications based on the user's training progress and emotional state, including workout reminders and motivational messages.

[2511] The server sends the configured push notification to the user's device.

[2512] The device receives a push notification and displays it on the user interface to encourage the user to continue training.

[2513] This system allows users to receive the optimal training menu that takes into consideration their physical condition, progress, and emotional state, enabling them to easily receive personal training at home and maintain their health on an ongoing basis.

[2514] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2515] Step 1:

[2516] The user launches the application and enters their body type information (photo, height, weight, age, gender) and goal information (target weight, target body type). This input data is temporarily saved in a local database on the device in JSON format. The specific operation is completed by keying in the data into the application's input form and pressing the submit button.

[2517] Input: User's body type and goal information

[2518] Output: Temporarily saved data in JSON format

[2519] Step 2:

[2520] The device prepares to send the entered information to the server. It sends an HTTP POST request with the saved data in a JSON-formatted payload. The HTTP request is then sent to the server. This is done by executing an API call associated with the click event of the submit button.

[2521] Input: Temporarily saved JSON format data

[2522] Output: HTTP POST request to the server

[2523] Step 3:

[2524] The server receives the user's body shape information (image data) and goal information (text data) sent from the device. Using a web framework such as Python's Flask or Django, the server receives the data at an API endpoint and stores it on a disk or in a database.

[2525] Input: JSON format data sent via HTTP POST request

[2526] Output: Body shape and goal information stored on disk and in a database

[2527] Step 4:

[2528] The server uses Python's OpenCV library to generate body shape data from the received image data. This process involves extracting the contours of specific body parts from the image and using algorithms to estimate body fat percentage and muscle mass. Specific operations are achieved by loading the received image data into OpenCV, extracting contours, and applying algorithms.

[2529] Input: Received image data

[2530] Output: Numerical body shape data including body fat percentage and muscle mass

[2531] Step 5:

[2532] The server uses the generated body shape data and goal information to input prompt sentences into the generative AI model. The generative AI model is a pre-trained machine learning model that generates an optimal training menu for the user based on the input data. Specifically, the server converts the body shape data and goal information into a specific format (prompt sentences) and sends them to the generative AI model via an API.

[2533] Input: Body type data and goal information

[2534] Output: Optimal training menu

[2535] Step 6:

[2536] The server receives the generated training menu and sends it to the user's device in JSON format. This data is sent as an HTTP response. The specific operation is to receive the results from the generative AI model and return them in format as an HTTP response.

[2537] Input: Generated training menu

[2538] Output: HTTP response to the user's device

[2539] Step 7:

[2540] The device parses the received training menu and displays it on the user interface. Specifically, it parses the received JSON data and visually displays it to the user in list or calendar format.

[2541] Input: Training menu received from the server

[2542] Output: Training menu displayed in the user interface

[2543] Step 8:

[2544] Users enter their training progress into the application and save it on their device. This includes details such as exercises completed, weight changes, and dates of exercise. Specifically, data is entered and saved on the progress input screen.

[2545] Input: Training progress data

[2546] Output: Progress data saved on the device

[2547] Step 9:

[2548] The device sends the saved progress data to the server in JSON format as an HTTP POST request. The specific operation is to click the Send Progress Data button to execute an API call.

[2549] Input: Progress data stored on the device

[2550] Output: HTTP POST request to the server

[2551] Step 10:

[2552] The server analyzes the received progress data and requests the generative AI model to optimize the next training menu. This is done by generating prompts using the progress data and sending them to the AI ​​model. The specific operation is the process of analyzing the received progress data and generating new prompts.

[2553] Input: Received progress data

[2554] Output: New optimized training menu

[2555] Step 11:

[2556] The generative AI model generates an optimized training menu based on the new progress data and sends it back to the server. The specific operation is the process of analyzing the progress data and generating a training menu based on it.

[2557] Input: Prompt statement reflecting progress data

[2558] Output: New training menu

[2559] Step 12:

[2560] The server receives the new training menu and sends it to the user's terminal. Specifically, it formats the new training menu in JSON format and sends it to the terminal as an HTTP response.

[2561] Enter: New training menu

[2562] Output: HTTP response to the user's device

[2563] Step 13:

[2564] The device parses the updated training menu and displays it in the user interface. The specific operation is to parse the received JSON data and reflect the menu in the user interface.

[2565] Input: New training menu received from the server

[2566] Output: Display of updated training menu

[2567] Step 14:

[2568] While training, users input their emotional state (stress, fatigue, pleasure, etc.) into the app. This data is temporarily stored on the device. Specifically, users input their emotional state using sliders and buttons on the emotion input interface.

[2569] Input: Emotional state data

[2570] Output: Emotion data temporarily stored on the device

[2571] Step 15:

[2572] The device uses the emotion engine to analyze the emotional state and sends the results to the server. Specifically, it calls the emotion analysis API and sends the analysis results to the server in JSON format.

[2573] Input: Temporarily stored emotional state data

[2574] Output: Sending analysis results to the server

[2575] Step 16:

[2576] The server analyzes the received emotional state data and inputs new prompt sentences to the generative AI model to adjust the training menu. Specifically, it creates new prompt sentences based on the emotional data and sends them to the generative AI model.

[2577] Input: Received emotional state data

[2578] Output: New and adjusted training menu

[2579] Step 17:

[2580] The generative AI model generates an adjusted training menu that reflects the emotional state and sends it back to the server. The specific operation is the process of generating an adaptive exercise list using emotional data.

[2581] Input: Prompt sentence reflecting emotional state data

[2582] Output: Tailored training menu

[2583] Step 18:

[2584] The server sends the adjusted training menu to the user's terminal. Specifically, the server formats the generated menu in JSON format and sends it as an HTTP response.

[2585] Enter: a tailored training menu.

[2586] Output: HTTP response to the user's device

[2587] Step 19:

[2588] The device displays the adjusted training menu on the user interface. Specifically, it parses the received JSON data and reflects the menu on the user interface.

[2589] Enter: a tailored training menu.

[2590] Output: Display of adjusted training menu

[2591] Step 20:

[2592] The server schedules push notifications at appropriate times based on the user's training progress and emotional state, allowing training reminders and motivational messages to be sent. Specifically, the server analyzes progress and emotional data and schedules push notifications.

[2593] Input: Progress data and emotional state data

[2594] Output: Configured push notifications

[2595] Step 21:

[2596] The server sends the configured push notification to the user's device. Specifically, the server uses the push notification service to periodically deliver notification messages to the device.

[2597] Input: Configured push notification

[2598] Output: Send push notification to user device

[2599] Step 22:

[2600] The device receives the push notification and displays it in the user interface, providing reminders and motivation to encourage the user to continue training. The specific behavior is to display the received push notification as a pop-up.

[2601] Input: Push notification received from the server

[2602] Output: Push notification displayed in the user interface

[2603] Through the above processing steps, the system provides users with a personalized training menu, maximizing the effectiveness of their training and maintaining continuous motivation.

[2604] (Application example 2)

[2605] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2606] While conventional training support systems can provide training menus based on the user's physique data and goal information, they do not take into account the user's emotional state, making it difficult to maintain motivation to continue training over the long term. Furthermore, there is a lack of training support in virtual environments, making it difficult to obtain effective feedback, especially when training at home. This has resulted in an insufficient environment for efficient and continuous training.

[2607] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2608] In this invention, the server includes: means for inputting a user's physique information; means for generating physique data using image analysis technology; means for inputting the user's goal information; means for generating an optimal training menu using a generative AI model based on the physique data and goal information in a user-implemented device; means for providing the training menu to a user terminal; means for inputting the user's training progress; means for generating and providing a new training menu based on the progress; means for using a display device to provide training in a virtual environment; means for recognizing the user's emotional state and adjusting the training menu based thereon; and means for providing the adjusted training menu to the display device. This allows the user to be provided with a training menu that takes their emotional state into account, thereby maintaining motivation over the long term. Furthermore, support from a fitness instructor is realized in a virtual environment, enabling effective training even at home.

[2609] "Body type information" is data relating to the physical characteristics of the user, and specific examples include height, weight, age, sex, and image data.

[2610] "Image analysis technology" is a technology for quantifying a user's physical characteristics from acquired image data, and specific examples include estimating body fat percentage and muscle mass.

[2611] "Goal information" is data relating to the purpose or goal of training that the user wishes to achieve, and specific examples include a target weight and body fat percentage.

[2612] A "generative AI model" is an artificial intelligence model that generates specific outputs based on input data, in this context specifically for automatically generating optimal training menus.

[2613] A "training menu" is a plan that lists the specific exercises and training items that a user should do and the order in which they should do them.

[2614] A "user terminal" is an electronic device that is directly operated by the user, and in this system is used to provide training menus and input progress.

[2615] "Progress" is information that re...

Claims

1. A means for inputting user's body type information; means for generating body shape data based on the body shape information using image analysis technology; a means for inputting user goal information; means for generating an optimal training menu using a generative artificial intelligence model based on the body type data and target information; means for providing the training menu to a user terminal; a means for inputting the user's training progress; A means for generating and providing a new training menu based on the progress. A system including:

2. The system according to claim 1 , further comprising means for sending a push notification to the user to encourage the user to continue training.

3. The system according to claim 1 , further comprising means for using image data as the user's body type information and estimating the body fat percentage and muscle mass using the image analysis technology.

Images