System

Abstract

A system is provided.SOLUTION: A system includes a means for receiving an image of a target body shape and performing image analysis, a means for generating an optimal training menu on the basis of an image analysis result, a means for receiving a video in which a user is performing training in real time and generating a correction instruction of a training form, and a means for formulating a training plan in a gap time on the basis of schedule information of the user.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 Japan, rising medical costs as the population ages are putting pressure on the national budget. Furthermore, the working population is expected to shrink due to the declining birthrate and aging population, making extending the nation's healthy life expectancy a priority. However, traditional health management methods make it difficult to provide optimal training instruction and dietary management tailored to individual needs. Furthermore, because individual health management systems exist in isolation, there is a lack of community-based motivation and mental health improvement. Therefore, there is a need for a system that can provide optimal training menus for individuals, appropriate dietary management, and motivation-boosting through community activities, all in one. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following system. First, it includes a means for receiving images of the desired body shape and performing image analysis. It provides a means for generating an optimal training menu based on the results of this analysis. Next, it provides a means for receiving video of the user training in real time and generating instructions for correcting the training form. It also includes a means for formulating a training plan for spare time based on the user's schedule information.

[0006] The system also includes a means for receiving images of meals taken by the user and performing image analysis. It also provides a means for calculating calories based on the results of this image analysis and a means for generating optimal menus that take the user's likes and dislikes into consideration. It also provides a means for matching users with similar body types and hobbies. Finally, it provides a means for planning and notifying training sessions and events for matched users. In this way, a system is realized that provides comprehensive health support to individuals.

[0007] "Image analysis" is a technology that extracts specific information from image data and analyzes and understands its content.

[0008] A "training menu" is a plan of exercises and training that a user should perform in order to achieve a specific desired body shape.

[0009] "Real-time" refers to processing and responding to current events immediately.

[0010] "Training form" refers to the posture and movements of the body when training.

[0011] "Schedule information" is information that indicates the time allocation of the user's daily activities and plans.

[0012] "Calculating calories" refers to calculating the amount of energy contained in food or meals as a numerical value.

[0013] "Menu" refers to the plan and contents of a day's meals.

[0014] "Matching" refers to pairing people who share common goals or interests.

[0015] A "training session" is an event where multiple users gather together to train together.

[0016] "Event notification" refers to informing a user about a particular event or activity. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that develops optimal training menus for individual users, manages dietary habits, and supports community activities. This system consists of three main components: a server, a terminal, and users.

[0039] Training menu planning / guidance

[0040] server:

[0041] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[0042] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[0043] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[0044] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[0045] Device:

[0046] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[0047] User:

[0048] Image transmission: Send an image of the desired body shape from your device to the server.

[0049] Training implementation: Training is carried out according to instructions from the server.

[0050] Dietary management

[0051] server:

[0052] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[0053] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[0054] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history.

[0055] Device:

[0056] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[0057] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[0058] User:

[0059] Food photography: Take a photo of your food and send it to the server from your device.

[0060] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[0061] community

[0062] server:

[0063] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[0064] Event planning module: Plans and announces training sessions and events between matched users.

[0065] Device:

[0066] Community Participation Module: Users can view community information and participate in events.

[0067] Event notification module: Notifies the user of event information sent from the server.

[0068] User:

[0069] Community participation: Become interested in the events you are notified about and participate through the app.

[0070] Socialize: Attend events and connect with other users.

[0071] Specific examples

[0072] 1. Training menu planning / guidance:

[0073] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[0074] When the user starts training, the smartphone camera sends the video to the server in real time, and the form check module generates appropriate form correction instructions and gives them to the user.

[0075] 2. Dietary Management:

[0076] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[0077] Based on the user's likes and dislikes and past eating history, the server suggests a menu for the next meal and displays it on the device.

[0078] 3. Community:

[0079] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[0080] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[0081] The processing flow will be explained below.

[0082] Training menu planning / guidance

[0083] Step 1:

[0084] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[0085] Step 2:

[0086] The image reception and analysis module on the server receives the images and extracts body shape features using an image analysis model.

[0087] Step 3:

[0088] The server's menu generation module generates the optimal training menu for the user based on the results of image analysis.

[0089] Step 4:

[0090] The server transmits the generated training menu to the terminal and displays it to the user.

[0091] Step 5:

[0092] The user starts training and transmits images to the server in real time via the device's camera.

[0093] Step 6:

[0094] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the user's training form.

[0095] Step 7:

[0096] The server sends the generated correction instructions to the terminal and displays them to the user, who then corrects the training form according to the instructions.

[0097] Step 8:

[0098] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[0099] Dietary management

[0100] Step 1:

[0101] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[0102] Step 2:

[0103] The server's food image analysis module receives the image and uses image analysis models to recognize the food content, identifying the type and quantity of food.

[0104] Step 3:

[0105] The server's calorie calculation module calculates the calories of each food item based on the results of image analysis.

[0106] Step 4:

[0107] The server generates advice for the next meal based on the calorie calculation results, and creates menu suggestions that take into account the user's preferences and past meal history.

[0108] Step 5:

[0109] The server generates a menu suggestion, which is sent to the terminal and displayed to the user. The user then checks the menu and selects their next meal.

[0110] community

[0111] Step 1:

[0112] The server's user matching module analyzes the user's desired body type and hobbies and preferences, and performs matching based on this.

[0113] Step 2:

[0114] The server's event planning module plans training sessions and events based on the matching results.

[0115] Step 3:

[0116] The server generates event information planned by the user and sends it to the terminal, notifying the user of events that match their interests.

[0117] Step 4:

[0118] An event notification module of the terminal receives the event information sent from the server and notifies the user of the event information.

[0119] Step 5:

[0120] The user checks the notification content and registers to participate in events of interest.

[0121] Step 6:

[0122] On the day of the event, users will participate in training sessions and offline meetups at designated locations or online to deepen their interactions with other users.

[0123] Example 1

[0124] 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."

[0125] In today's busy lifestyles, it is difficult to develop optimal training programs for individual users, manage their diets, and support community activities. Conventional systems lack the advanced analytical capabilities to address individual needs or the ability to provide real-time feedback. This makes it difficult for users to self-manage and maintain motivation. The present invention aims to solve these challenges and support users in maintaining their health and building communities.

[0126] 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.

[0127] In this invention, the server includes means for receiving images of a desired body shape and analyzing the images using a machine learning model, means for generating an optimal training menu using a genetic algorithm based on the image analysis results, means for receiving video of a user performing a workout in real time and generating training form correction instructions using posture analysis technology, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents using image recognition technology, means for calculating calories by referencing a food composition database based on the image analysis results, means for generating an optimal menu taking into account the user's likes and dislikes using a recommendation algorithm, means for matching users with similar desired body shapes and hobbies and preferences using a clustering algorithm, and means for planning and notifying training sessions and events for matched users. This enables the provision of training menus tailored to individual user needs, appropriate dietary management, and support for community activities.

[0128] "Image analysis" is a technology that processes image data to understand and recognize its contents.

[0129] A "machine learning model" is a collection of algorithms that learn from large amounts of data and perform specific tasks automatically.

[0130] A "genetic algorithm" is a computational method for finding optimal solutions by imitating the evolutionary process of living organisms.

[0131] "Posture analysis technology" is a technology that analyzes a person's body movements and poses and identifies their posture.

[0132] The "Food Composition Database" is a database that systematically organizes and provides nutritional information on various foods.

[0133] A "recommendation algorithm" is an algorithm that analyzes user preferences and behavioral history to make optimal suggestions to individual users.

[0134] A "clustering algorithm" is a method for grouping data based on similarity.

[0135] "Real-time" refers to data processing and transmission occurring almost simultaneously with the real time axis.

[0136] A "training menu" is a collection of movements or exercises designed to achieve a specific goal or objective.

[0137] "Schedule information" is information including plans and timetables set by the user.

[0138] "Meal contents" refers to the types and amounts of ingredients and dishes consumed by the user.

[0139] "Calorie calculation" is a calculation to calculate the amount of energy contained in food.

[0140] "Matching" refers to linking multiple elements (e.g., users) based on specific conditions.

[0141] "Event notification" is the act of communicating information to interested parties about a particular occurrence or activity.

[0142] The present invention is a system that develops optimal training menus for individual users, manages their diet, and supports community activities. To implement this system, the following specific hardware and software are required.

[0143] Training menu planning / guidance

[0144] server:

[0145] Image reception and analysis module: The server receives an image of the user's desired body shape and performs image analysis using a machine learning model (e.g., TensorFlow). This analysis extracts body shape features (such as muscle distribution and fat distribution).

[0146] Menu generation module: The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[0147] Form check module: The server receives real-time video of the user training and uses posture analysis technology (e.g., OpenPose) to check whether the training is being performed with proper form, generating correction instructions as necessary.

[0148] Schedule management module: The server creates a training plan that utilizes the user's free time based on the user's schedule information.

[0149] Device:

[0150] Training module: The user uses the device's camera to transmit images of themselves training to the server, and receives real-time guidance on their form. The module also displays training menus and correction instructions sent from the server.

[0151] User:

[0152] Image transmission: The user sends an image of the desired body shape from their smartphone to the server. For example, they can take a photo of a fitness model and send it.

[0153] Training implementation: The user implements the training according to the instructions from the server.

[0154] Dietary management

[0155] server:

[0156] Food image analysis module: The server receives food images taken by the user and analyzes the food contents using image recognition technology (e.g., ResNet). This analysis identifies the foods contained in the meal and their amounts.

[0157] Calorie calculation module: The server calculates calories based on the image analysis results and references a food composition database (e.g., USDA food composition database).

[0158] Menu suggestion module: The server uses a recommendation algorithm (e.g., collaborative filtering) to generate an optimal menu, taking into account the user's likes and dislikes and dietary history.

[0159] Device:

[0160] Meal Recording Module: The user takes a photo of the meal and sends it to the server.

[0161] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[0162] User:

[0163] Food photography: A user takes a photo of their meal with their smartphone and sends it to the server from the device. For example, they take a photo of their lunch or dinner.

[0164] Menu confirmation: The user checks the menu suggestions from the server and selects the appropriate meal.

[0165] Community Activities

[0166] server:

[0167] User matching module: The server uses a clustering algorithm (e.g., K-Means) to match users with similar desired body types and hobbies and preferences.

[0168] Event planning module: The server plans training sessions and events for matched users and notifies them of the information.

[0169] Device:

[0170] Community participation module: Users can check community information and participate in events.

[0171] Event notification module: Notifies the user of event information sent from the server.

[0172] User:

[0173] Community participation: Users are interested in events they are notified about and participate through the app, for example, by attending a monthly training session.

[0174] Socialize: Users attend events, interact with other users, and train together.

[0175] Specific examples

[0176] 1. Training menu planning / guidance:

[0177] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server then analyzes the image using TensorFlow and generates an optimal training menu.

[0178] When the user starts training, the smartphone camera sends images to the server in real time, and the form check module using OpenPose generates appropriate form correction instructions and provides them to the user.

[0179] 2. Dietary Management:

[0180] A user takes a photo of their lunch salad and steak and sends it to the server, which analyzes the image using ResNet and calculates the calories of each food item from the USDA Food Composition Database.

[0181] The server uses collaborative filtering to suggest the next meal menu based on the user's likes and dislikes and past eating history, and displays it on the device.

[0182] 3. Community Activities:

[0183] The server uses clustering to match users with common goals and hobbies, and then plans and notifies them of monthly training sessions.

[0184] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[0185] Prompt Sentence Examples

[0186] "How can I send you an image of the body shape I'm aiming for?"

[0187] "I want to make sure my form is correct during my workouts. How can I do that?"

[0188] "I'd like you to calculate the calories in today's lunch. I took a photo and sent it to you."

[0189] "I would like to participate in events where I can interact with people who share the same hobbies."

[0190] The above is a specific embodiment of the present invention. This system makes it possible to provide training menus tailored to the needs of individual users, manage their diet appropriately, and support community activities.

[0191] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0192] Training menu planning / guidance

[0193] Step 1:

[0194] The user takes a picture of the body shape they are aiming for with their smartphone and sends it to the server using a dedicated app. The input is the image of the body shape acquired by the user, and the output is the result of sending the image data to the server.

[0195] Step 2:

[0196] The server receives the images and performs image analysis using a machine learning model (TensorFlow). The input is the received image data, and the output is data that extracts body shape features. This analysis allows for the acquisition of body shape features such as muscle distribution and fat distribution.

[0197] Step 3:

[0198] The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The input is the extracted body shape feature data, and the output is an optimized training menu. The menu includes the required exercises, their intensity, frequency, etc.

[0199] Step 4:

[0200] The user starts training and sends the training video to the server in real time using the smartphone camera. The input is the video data during training, and the output is the video transmission result to the server.

[0201] Step 5:

[0202] The server analyzes the video received in real time and uses posture analysis technology such as OpenPose to check whether the correct form is being maintained. The input is real-time video data, and the output is the evaluation result of the form appropriateness. Instructions for correcting the form are generated as needed.

[0203] Step 6:

[0204] The server generates form correction instructions, which are sent to the terminal and displayed to the user. The input is the form correction instruction data, and the output is the display result on the user's terminal. The user performs training according to these instructions.

[0205] Dietary management

[0206] Step 1:

[0207] The user takes a photo of their meal with their smartphone and sends it to the server using a dedicated app. The input is the image data of the meal, and the output is the result of sending the image data to the server.

[0208] Step 2:

[0209] The server receives the food images and performs image analysis using image recognition techniques such as ResNet. The input is the received image data, and the output is the identified foods and their quantities.

[0210] Step 3:

[0211] The server calculates calories based on the image analysis results by checking against the food composition database (USDA food composition database). The input is the identified food and its quantity data, and the output is the calculated calorie value.

[0212] Step 4:

[0213] The server uses a collaborative filtering algorithm to generate a menu for the next meal, taking into account the user's likes and dislikes and dietary history. The input is the user's dietary history and likes and dislikes, and the output is the generated menu.

[0214] Step 5:

[0215] The server sends the generated menu to the user's device and suggests the next meal. The input is the generated menu data, and the output is the display result on the user's device. The user selects an appropriate meal based on the suggestions.

[0216] Community Activities

[0217] Step 1:

[0218] The server analyzes the user's desired body type and hobbies and preferences, and matches similar users using a clustering algorithm (K-Means). The input is the user's goals and preference data, and the output is the matching results.

[0219] Step 2:

[0220] The server plans training sessions and events for matched users and notifies them of the information. The input is the matching result data, and the output is the planned event information data.

[0221] Step 3:

[0222] The server sends planned event information to users' terminals and encourages them to participate in the event. The input is event information data, and the output is the notification result sent to the user terminal.

[0223] Step 4:

[0224] The user checks the event information displayed on the terminal and registers to participate in the events they are interested in. The input is the event information data, and the output is the registration result.

[0225] Step 5:

[0226] On the day of the event, users participate in community activities with other users and deepen their interactions. The input is event participation information, and the output is interaction experience points and feedback.

[0227] (Application example 1)

[0228] 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."

[0229] Conventional training support systems have had the problem of making it difficult to create training menus tailored to each user's physical condition and goals, and of not being able to check or correct form in real time. Furthermore, when it comes to dietary management, calorie calculations and menu suggestions are time-consuming, and measures to address these issues are insufficient. Furthermore, there was a lack of mechanisms to encourage interaction between users with common goals or hobbies or to participate in events, making it difficult to maintain motivation.

[0230] 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.

[0231] In this invention, the server includes: means for receiving images of the desired body shape and analyzing the images; means for generating an optimal training menu based on the image analysis results; means for receiving video of the user's training in real time and generating training form correction instructions; means for formulating a training plan for spare time based on the user's schedule information; means for the user to take images of their meals and send them to the server, which then analyzes the images and calculates calories; and means for matching users with common goals and planning and notifying them of training events inside and outside the store. This enables the formulation of optimal training menus tailored to each user's individual goals, real-time form checks, and smooth calorie management and menu suggestions. Furthermore, it encourages interaction and event participation among users with common goals and hobbies, helping to maintain motivation.

[0232] 1. "Body shape image" is an image that visually shows the ideal body shape that the user is aiming for.

[0233] 2. "Image analysis" is the process of analyzing transmitted image data and extracting necessary information from its contents.

[0234] 3. "Training Menu" means a schedule of exercises and activities required for the user to achieve the desired body shape.

[0235] 4. "Video" refers to video data of a user performing training.

[0236] 5. "Form correction instructions" refers to real-time instruction provided to help users adopt the correct exercise posture.

[0237] 6. "Schedule information" is data that represents a user's daily activities and free time.

[0238] 7. "Spare time" refers to a period of time in a user's schedule when they can engage in an activity even for a short period of time.

[0239] 8. "Meal images" are photographs of food taken by the user.

[0240] 9. "Calorie counting" is the process of calculating the amount of energy intake based on the contents of a meal.

[0241] 10. "Menu suggestion" is a suggestion for the next meal that takes into account the user's preferences and nutritional balance.

[0242] 11. A "common goal" is a training or health-related objective shared by multiple users.

[0243] 12. "Matching" is the process of identifying and pairing or grouping users with common goals or interests.

[0244] 13. A "Training Event" is an opportunity for users with similar goals to come together and exercise together.

[0245] 14. "Notification" means a communication method used to inform users about training events or important information.

[0246] The system of the present invention is designed to provide users with personalized training menus, support dietary management, and promote community activities. The system consists of three main components: a server, a terminal, and users.

[0247] Training menu planning / guidance

[0248] server:

[0249] The server performs the following functions:

[0250] "Image Reception and Analysis Module": Receives images of the user's desired body shape and performs image analysis. This analysis uses software such as the image analysis library "OpenCV." The analysis results are used to extract the characteristics of the user's ideal body shape.

[0251] "Menu generation module": Generates an optimal training menu based on the image analysis results. This uses a generative AI model (e.g., GPT-4).

[0252] "Form Check Module": This module receives real-time video footage of the user training, checks whether the training is being performed with proper form, and generates correction instructions as necessary. This process uses the real-time video processing library "Kinesis Video Streams."

[0253] "Schedule Management Module": Based on the user's schedule information, it creates a training plan that utilizes their free time.

[0254] Device:

[0255] The device is equipped with the following features:

[0256] "Training module": The user uses the device's camera to send images to the server while training, and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[0257] User:

[0258] The user performs the following actions:

[0259] "Send image": Send an image of the desired body shape from your device to the server.

[0260] "Training": Training is carried out according to instructions from the server.

[0261] Dietary management

[0262] server:

[0263] The server supports the following features:

[0264] "Meal Image Analysis Module": Receives meal images taken by the user and performs image analysis. This analysis uses "Tesseract OCR" to identify the foods contained in the meal and their amounts.

[0265] "Calorie Calculation Module": Calculates the calorie content of food based on the results of image analysis. Uses a dedicated calorie calculation API.

[0266] "Menu suggestion module": Suggests the menu for the next meal, taking into account the user's likes and dislikes and eating history.

[0267] Device:

[0268] The device will be equipped with the following features:

[0269] "Meal Recording Module": The user takes a photo of what they have eaten and sends it to the server.

[0270] "Menu display module": Displays the menu sent from the server to the user and suggests the next meal.

[0271] User:

[0272] The user performs the following actions:

[0273] "Photo of food": Take a photo of your meal and send it from your device to the server.

[0274] "Confirm Menu": Check the menu suggestions from the server and select an appropriate meal.

[0275] community

[0276] server:

[0277] The server provides the following functions:

[0278] "User Matching Module": Matches users with common goals.

[0279] "Event Planning Module": Plans and announces training sessions and events between matched users. Data management uses "MySQL" and "Django."

[0280] Device:

[0281] The device will be equipped with the following features:

[0282] "Community Participation Module": Users check community information and participate in events.

[0283] "Event notification module": Notifies the user of event information sent from the server.

[0284] User:

[0285] The user performs the following actions:

[0286] "Community participation": Become interested in a notified event and participate through the app.

[0287] "Interact": Participate in events and deepen your interactions with other users.

[0288] Prompt Sentence Examples

[0289] 1. Training menu generation

[0290] "Upload an image of the body shape you want to achieve. After analyzing it, the system will suggest the optimal training menu."

[0291] 2. Real-time form checking

[0292] "Please record your training with a camera and send it to us. We will check your form in real time and provide appropriate guidance."

[0293] 3. Dietary Management

[0294] "Take a photo of the food you ate today and upload it. We'll analyze the calories and give you suggestions for your next meal."

[0295] 4. Community Support

[0296] "We will be organizing events for members with common goals. Please check the announcements if you would like to participate."

[0297] The above is a specific embodiment for carrying out the present invention, which makes it possible to provide training guidance and dietary management that is optimized for each individual user, and also to increase motivation through community activities.

[0298] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0299] Step 1:

[0300] The user takes a picture of the body shape they are aiming for using their smartphone and sends it from the device to the server.

[0301] Input: Body image

[0302] Data processing: Image data stored on the device is uploaded to the server via the device's application.

[0303] Output: The body image is sent to the server.

[0304] Step 2:

[0305] The server's image reception and analysis module analyzes the received body shape image.

[0306] Input: Body image

[0307] Data processing: Image features are extracted using the OpenCV library to identify ideal body shape properties.

[0308] Output: Body shape characteristic data is obtained as the analysis result.

[0309] Step 3:

[0310] The server's menu generation module generates an optimal training menu based on the image analysis results.

[0311] Input: Body shape feature data

[0312] Data processing: Using a generative AI model (e.g., GPT-4), a training menu is generated based on the user's goals and current physical condition.

[0313] Output: Customized training menu

[0314] Step 4:

[0315] The user begins training, takes a video of themselves using their smartphone camera, and sends it to the server in real time from the device.

[0316] Input: Video of training

[0317] Data processing: Real-time video data is acquired using the device's camera function.

[0318] Output: Live video is sent to the server.

[0319] Step 5:

[0320] The server's form check module analyzes the real-time video and generates instructions for correcting training form.

[0321] Input: Live footage of training

[0322] Data Processing: Using Kinesis Video Streams and OpenCV, we analyze the user's posture and determine the proper form.

[0323] Output: Form correction instructions

[0324] Step 6:

[0325] The server's instructions are sent to the terminal and displayed on the user's terminal.

[0326] Input: Form correction instructions

[0327] Data processing: Transfer instruction data to the terminal.

[0328] Output: Form correction instructions are displayed on the terminal.

[0329] Step 7:

[0330] The user takes a photo of the meal and sends it to the server from the device.

[0331] Input: Food image

[0332] Data processing: Photo data stored on the device is uploaded to the server via the app.

[0333] Output: The food image is sent to the server.

[0334] Step 8:

[0335] The server's food image analysis module analyzes the received food image and calculates calories.

[0336] Input: Food image

[0337] Data processing: Identify food items in the image using Tesseract OCR and calculate calories using a dedicated API.

[0338] Output: Calorie data of meals

[0339] Step 9:

[0340] The server's menu suggestion module considers calorie data and the user's preferences to suggest a menu for the next meal.

[0341] Input: Calorie data, user preference data

[0342] Data processing: Generates an optimal menu list based on past meal history and preference data.

[0343] Output: Suggested menu

[0344] Step 10:

[0345] The server matches users with common goals and organizes and announces training events.

[0346] Input: User goal data

[0347] Data Processing: Using Django framework and MySQL database to match user information and plan training events.

[0348] Output: Event notification data

[0349] Step 11:

[0350] The server sends the event notification data to the terminal, which displays the notification to the user.

[0351] Input: Event notification data

[0352] Data processing: Send notification data to the device.

[0353] Output: An event notification is displayed on the user's terminal.

[0354] The above is a specific processing flow of the system of the present invention, which provides optimized support to individual users.

[0355] 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.

[0356] This system creates optimal training menus for individual users, manages their diet, and supports community activities. It also incorporates an emotion engine that recognizes the user's emotional state, enabling these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and users.

[0357] Training menu planning / guidance

[0358] server:

[0359] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[0360] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[0361] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[0362] Emotion engine: Analyzes the user's facial expressions and voice to recognize their emotional state, and uses that information to appropriately adjust the content of training guidance and support.

[0363] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[0364] Device:

[0365] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The server also displays training menus, correction instructions, and emotional support messages.

[0366] User:

[0367] Image transmission: Send an image of the desired body shape from your device to the server.

[0368] Training: Train according to instructions and encouraging messages from the server.

[0369] Dietary management

[0370] server:

[0371] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[0372] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[0373] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history. In addition, an emotion engine analyzes the user's emotional state during meal recording and, based on the results, suggests menus that are adapted to the user's psychological state.

[0374] Device:

[0375] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[0376] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[0377] User:

[0378] Food photography: Take a photo of your food and send it to the server from your device.

[0379] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[0380] community

[0381] server:

[0382] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[0383] Event planning module: Plans and announces training sessions and events between matched users.

[0384] Emotion Engine: Recognizes the emotions of each user during communication between users and appropriately supports interactions within the community based on the results.

[0385] Device:

[0386] Community Participation Module: Users can view community information and participate in events.

[0387] Event notification module: Notifies the user of event information sent from the server.

[0388] User:

[0389] Community participation: Become interested in the events you are notified about and participate through the app.

[0390] Socialize: Attend events and connect with other users.

[0391] Specific examples

[0392] 1. Training menu planning / guidance:

[0393] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[0394] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[0395] 2. Dietary Management:

[0396] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[0397] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[0398] 3. Community:

[0399] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[0400] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[0401] The processing flow will be explained below.

[0402] Training menu planning / guidance

[0403] Step 1:

[0404] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[0405] Step 2:

[0406] The server's image reception and analysis module analyzes the received images and extracts body shape characteristics from the analysis results.

[0407] Step 3:

[0408] The menu generation module of the server generates an optimal training menu based on the image analysis results.

[0409] Step 4:

[0410] The server transmits the generated training menu to the terminal, and the user confirms the displayed menu.

[0411] Step 5:

[0412] The user starts training and sends real-time video to the server via the device's camera.

[0413] Step 6:

[0414] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the training form. The emotion engine also recognizes the user's emotions from the video and audio.

[0415] Step 7:

[0416] The server generates correction instructions and sends cheering messages based on the user's emotional state to the terminal, which the user confirms. The user then continues to correct their training form accordingly.

[0417] Step 8:

[0418] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[0419] Dietary management

[0420] Step 1:

[0421] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[0422] Step 2:

[0423] The server's food image analysis module receives the image and performs image analysis to identify the type and amount of food.

[0424] Step 3:

[0425] The server's calorie calculation module calculates the calories of each food item based on the image analysis results.

[0426] Step 4:

[0427] The server takes into account the calorie calculation results, the user's preferences, and past meal history, and then uses an emotion engine to analyze the user's emotional state when recording their meals, and based on the results, generates a menu that is adapted to the user's psychological state.

[0428] Step 5:

[0429] The server sends the generated menu suggestions to the terminal, and the user checks the displayed menu. The user selects an appropriate meal and then follows the instructions.

[0430] community

[0431] Step 1:

[0432] The server's user matching module analyzes users' desired body type, hobbies, thoughts, and emotional state, and matches users with many commonalities.

[0433] Step 2:

[0434] The server's event planning module plans training sessions and events for matched users. The emotion engine determines the user's emotional state and notifies them of events at the optimal time.

[0435] Step 3:

[0436] The server sends the generated event information to the terminal and notifies the user, who then checks the notification content.

[0437] Step 4:

[0438] A user applies to participate in an event that they are interested in. The device sends the participation request to the server.

[0439] Step 5:

[0440] On the day of the event, users participate in the event at a designated location or online. The server's emotion engine monitors the user's emotional state during the event in real time and generates feedback to support interaction.

[0441] Step 6:

[0442] The server generates feedback and sends it to the terminal, where the user receives it. This deepens interaction with other users and increases motivation for training.

[0443] Example 2

[0444] 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."

[0445] Conventional training and diet management systems struggle to provide optimal guidance and support tailored to individual users' goals and emotional states. Furthermore, they lack emotional support for communication and collaborative training, making it difficult to maintain motivation. This results in a lack of continuous health management and community building for users.

[0446] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of a desired body shape and performing image analysis, means for generating an optimal training menu based on the image analysis results, means for receiving video of a user performing training in real time and generating instructions for correcting the user's training form, means for analyzing the user's emotional state in real time and generating an emotional support message, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents, means for calculating calories based on the image analysis results, means for analyzing the user's emotional state and generating an optimal menu based on the analyzed results, means for matching users with similar desired body shapes and hobbies, means for planning and notifying training sessions and events for matched users, and means for recognizing emotions during communication between users and providing emotional support for interaction. This makes it possible to provide optimal training and dietary management for each user, and further realize support for community activities and emotional motivation maintenance.

[0447] "Image reception and analysis module" refers to the device or software that receives images of the desired body shape and performs image analysis.

[0448] A "menu generation module" refers to a device or software that generates an optimal training menu based on the results of image analysis, taking into account the user's goals and current physical condition.

[0449] A "form check module" refers to a device or software that receives video of a user performing training in real time and generates instructions for correcting the training form.

[0450] An "emotion engine" refers to a device or software that analyzes a user's facial expressions and voice in real time, recognizes their emotional state, and generates cheering messages and other information based on that information.

[0451] A "schedule management module" refers to a device or software that creates a training plan for spare time based on the user's schedule information.

[0452] A "meal image analysis module" refers to a device or software that receives images of meals taken by users and performs image analysis of the meal contents.

[0453] A "calorie calculation module" refers to a device or software that calculates the calories of a meal based on the results of image analysis.

[0454] A "menu suggestion module" refers to a device or software that generates an optimal menu taking into account the user's emotional state and eating history.

[0455] A "user matching module" refers to a device or software that matches users with similar body types and hobbies.

[0456] An "event planning module" refers to a device or software that plans and notifies training sessions and events between matched users.

[0457] "Community participation module" refers to a device or software that provides a function for users to check community information and participate in events.

[0458] An "event notification module" refers to a device or software that notifies a user of event information sent from a server.

[0459] "Training implementation module" refers to a device or software that provides a function that allows a user to use the device's camera to send images to a server while training and receive form guidance in real time.

[0460] A "meal record module" refers to a device or software that provides the function of allowing a user to take a photo of what they have eaten and send it to a server.

[0461] A "menu display module" refers to a device or software that displays the menu sent from the server to the user and suggests the next meal.

[0462] The present invention is a system for efficiently managing the health of each user. This system consists of three main elements: a server, a terminal, and a user, and realizes the invention through the following configuration and operation.

[0463] server

[0464] The server uses multiple dedicated modules to support users in training, dietary management, and community activities.

[0465] 1. Image reception and analysis module

[0466] The server receives images of the user's desired body shape and performs image analysis. Specifically, it uses image analysis software (e.g., OpenCV) to extract body shape characteristics. Based on this information, it creates a training menu, which will be described later.

[0467] 2. Menu Generation Module

[0468] Based on the results of image analysis, the server generates an optimal training menu that takes into account the user's goals and current physical condition. For example, it creates a program that combines strength training three times a week and aerobic exercise twice a week and provides it to each individual user.

[0469] 3. Form Check Module

[0470] The server receives real-time video footage sent from the user's device while they are training. Using video analysis technology, it checks the user's form and generates necessary correction instructions. For example, if the user's posture is poor, it sends a message saying, "Straighten your back."

[0471] 4. Emotion Engine

[0472] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state. Using technologies such as Google Cloud Vision API and Microsoft Azure Emotion API, the server then uses this information to appropriately tailor training instructions and support messages.

[0473] 5. Schedule Management Module

[0474] The server creates a training plan that utilizes the user's free time based on the user's schedule information, making it possible to provide a training plan that the user can continue without straining themselves.

[0475] 6. Food Image Analysis Module

[0476] The server receives the image of the meal taken by the user and performs image analysis using OpenCV etc. to identify the ingredients and their amounts, and calculates the calories based on this information.

[0477] 7. Calorie Counting Module

[0478] The server calculates the calories of the meal based on the image analysis results, allowing the user to accurately grasp the calorie intake of their food.

[0479] 8. Menu suggestion module

[0480] The server analyzes the user's eating history and emotional state to suggest optimal meals. For example, it generates a meal plan using ingredients that have a relaxing effect for a stressed user.

[0481] 9. User Matching Module

[0482] The server matches users with similar body types, hobbies, and ways of thinking. This module allows users to find others who share the same goals and work together to achieve their goals.

[0483] 10. Event Planning Module

[0484] The server plans and notifies training sessions and events between matched users, thereby promoting interaction between users.

[0485] 11. Communication Support

[0486] The server recognizes emotions during communication between users and supports interactions based on those emotions. For example, it provides appropriate interaction support through emotion analysis during an event.

[0487] Terminal

[0488] A terminal refers to a device or software that communicates with a server through user operation and provides various information.

[0489] 1. Training Implementation Module

[0490] When a user starts training, the device's camera activates and transmits the video in real time to the server, which then displays the training menu, form instructions, and encouraging messages.

[0491] 2. Food Record Module

[0492] It provides a function that allows users to take a photo of what they have eaten and send it to the server.

[0493] 3. Community Participation Module

[0494] It provides users with the ability to check community information and participate in events.

[0495] User

[0496] Users can use this system to manage their own health. Specific operations include sending images of their desired body shape, doing training, taking photos of meals, and participating in the community.

[0497] Specific examples

[0498] 1. Training menu planning / guidance:

[0499] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[0500] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[0501] 2. Dietary Management:

[0502] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[0503] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[0504] 3. Community:

[0505] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[0506] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[0507] Example prompt for a generative AI model:

[0508] Develop a system that generates an optimal training menu based on images of the user's desired physique, checks their form in real time, and provides cheering messages based on their emotional state. The system receives images from the user, analyzes them to create a specific training menu, analyzes footage of the training session to generate instructions for correcting their form, and uses an emotion engine to provide appropriate cheering messages.

[0509] The above is the "Mode for Carrying Out the Invention."

[0510] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0511] Training menu planning / guidance

[0512] server

[0513] Step 1:

[0514] The server receives an image of a desired body type from the user.

[0515] Specific behavior:

[0516] The user takes a photo of the fitness model with their smartphone and sends it to the server via the app.

[0517] Input: An image of the body type the user is aiming for.

[0518] Output: Receiving image data.

[0519] Step 2:

[0520] The server analyzes the received images using image analysis software (e.g., OpenCV) and extracts body shape features.

[0521] Specific behavior:

[0522] The server reads the received images using OpenCV and analyzes specific features (muscle shape and fat distribution).

[0523] Input: Image data.

[0524] Output: Analyzed body feature data.

[0525] Step 3:

[0526] The server generates an optimal training menu based on the results of the image analysis.

[0527] Specific behavior:

[0528] Based on the analysis results, the server creates a menu that combines three sessions of strength training and two sessions of aerobic exercise per week.

[0529] Input: Body shape feature data.

[0530] Output: Training menu.

[0531] Terminal

[0532] Step 1:

[0533] When a user starts training, the device's camera is used to send images to the server in real time.

[0534] Specific behavior:

[0535] When the user launches the app and presses the "Start Training" button, the camera activates and the video is sent to the server.

[0536] Input: User training start signal.

[0537] Output: Real-time video data transmission.

[0538] server

[0539] Step 4:

[0540] The server analyzes the received video and checks the user's training form.

[0541] Specific behavior:

[0542] The server uses video analysis technology to analyze the user's actions in real time and evaluate whether they are correct.

[0543] Input: Real-time video data.

[0544] Output: Form check results.

[0545] Step 5:

[0546] The server generates correction instructions if the user's form is incorrect.

[0547] Specific behavior:

[0548] When the server detects improper form, it generates correction instructions such as "Stand up a little straighter."

[0549] Input: Form check result.

[0550] Output: Form correction instructions.

[0551] Step 6:

[0552] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[0553] Specific behavior:

[0554] The server performs emotion analysis using the Google Cloud Vision API and Microsoft Azure Emotion API.

[0555] Input: Real-time video and audio data.

[0556] Output: Emotional state data.

[0557] Step 7:

[0558] The server appropriately adjusts the cheering message based on the emotional state.

[0559] Specific behavior:

[0560] The server sends a message of encouragement saying "Keep it up!" to a user who is feeling unmotivated.

[0561] Input: Emotional state data.

[0562] Output: A message of encouragement.

[0563] Dietary management

[0564] User

[0565] Step 1:

[0566] The user takes a photo of the meal with their smartphone and sends it to the server.

[0567] Specific behavior:

[0568] The user takes a photo of their lunch salad and steak using the app and hits send.

[0569] Input: food photos.

[0570] Output: Sending food image data.

[0571] server

[0572] Step 2:

[0573] The server analyzes the received meal images using image analysis software (e.g., OpenCV) to identify the ingredients and their quantities.

[0574] Specific behavior:

[0575] The server analyzes the food image and identifies the type of vegetables in the salad and the gram weight of the steak.

[0576] Input: Food image data.

[0577] Output: Parsed ingredient data.

[0578] Step 3:

[0579] The server calculates the calories of the meal based on the analysis results.

[0580] Specific behavior:

[0581] The server calculates the calories based on the amount of ingredients specified and displays 500 kcal.

[0582] Input: Parsed ingredient data.

[0583] Output: Calorie calculation results.

[0584] Step 4:

[0585] The server analyzes the user's emotional state in real time and suggests a menu that suits their psychological state.

[0586] Specific behavior:

[0587] The server suggests a relaxing dinner to users who are feeling stressed.

[0588] Input: Emotional state data.

[0589] Output: Menu suggestions.

[0590] community

[0591] server

[0592] Step 1:

[0593] The server matches users with similar body types, hobbies, and ways of thinking.

[0594] Specific behavior:

[0595] The server compares the registered user information and notifies the user that "we have found users with similar goals to you."

[0596] Input: User profile data.

[0597] Output: Matching results.

[0598] Step 2:

[0599] The server plans and notifies training sessions and events between matched users.

[0600] Specific behavior:

[0601] The server announces, "The next training event is next Saturday."

[0602] Input: Matching results.

[0603] Output: Event notification.

[0604] Step 3:

[0605] The server recognizes emotions during communication between users and provides emotion-based interaction support.

[0606] Specific behavior:

[0607] The server analyzes the emotional state and generates messages during the event such as "You're having fun! Let's talk more!"

[0608] Input: Real-time emotion data.

[0609] Output: AC support message.

[0610] User

[0611] Step 1:

[0612] The user becomes interested in the event and participates through the app.

[0613] Specific behavior:

[0614] The user opens the app and presses the event participation button.

[0615] Input: User's willingness to attend the event.

[0616] Output: Event registration.

[0617] Step 2:

[0618] Users can participate in events and interact with other users.

[0619] Specific behavior:

[0620] Users can talk with other participants at the event venue and exchange messages using social networking features.

[0621] Input: User interactions.

[0622] Output: Promoting interaction.

[0623] The above are the specific processing steps of the program of this system.

[0624] (Application example 2)

[0625] 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."

[0626] Conventional training menu planning and diet management systems face challenges in that they are unable to adequately respond to users' emotional states and individual schedules. Furthermore, real-time training guidance and diet management are difficult, making it difficult for users to maintain a consistent fitness plan. Furthermore, in community activities, there is a lack of mechanisms to effectively support interactions between users. To solve these challenges, it is necessary to recognize users' emotional states and provide individually optimized guidance and management.

[0627] 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.

[0628] In this invention, the server includes means for receiving images of the target body shape and analyzing the images, means for generating an optimal training menu based on the image analysis results, means for receiving video of the user's training in real time and generating training form correction instructions, means for formulating a training plan for spare time based on the user's schedule information, means for providing training in a virtual reality environment or an augmented reality environment, means for providing form guidance using a real-time haptic device, and means for analyzing the user's emotional state and adjusting the training instruction content and support messages based on the user's emotions. This enables the provision of a consistent fitness plan tailored to each user's emotional state and real-time, effective training guidance. It also appropriately supports communication between users, revitalizing the fitness community.

[0629] The "image of the desired body type" is image data showing the ideal body type that the user desires.

[0630] "Image analysis" is the process of extracting and analyzing features from received image data.

[0631] A "training menu" is a series of exercise programs designed to help a user achieve their goals.

[0632] "Real-time video" refers to current video data while the user is working out.

[0633] "Instructions for correcting training form" refers to providing guidance and suggestions for correction to maintain proper exercise form.

[0634] "Schedule information" is data relating to the user's plans and timetable.

[0635] A "spare time training plan" is a training plan that utilizes the user's free time.

[0636] A "virtual reality environment" is a virtual training environment that a user experiences through a VR device.

[0637] An "augmented reality environment" is a training environment that uses AR technology to overlay digital information onto the real environment.

[0638] A "haptic device" is a device that provides tactile feedback, allowing users to physically feel the feedback during training.

[0639] "Emotional state" refers to the user's emotional and psychological state, and is used to provide appropriate guidance and support by analyzing it.

[0640] "Image analysis of food content" is the process of analyzing photos of meals taken by users to identify the foods and amounts included.

[0641] "Calorie calculation" refers to calculating the total calorie content of a meal based on the results of image analysis.

[0642] A "menu" is a meal plan suggested based on the user's nutritional balance and preferences.

[0643] "User likes and dislikes" is information about foods that a user likes and dislikes.

[0644] "Matching" is the process of connecting users who share common goals or interests.

[0645] "Training sessions and events" are activities or sessions where users come together to share common experiences.

[0646] "Communication support" means helping users to interact with each other in an enjoyable and effective way.

[0647] This invention is a system that supports users in formulating optimal training menus, managing their diet, and participating in community activities, and it combines an emotion engine that recognizes the user's emotional state to enable these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and a user.

[0648] Training menu planning / guidance

[0649] 1. Server:

[0650] The server receives images of the desired body shape and performs image analysis. This analysis uses TensorFlow and PIL. As a result of the image analysis, the user's body characteristics are extracted, and an optimal training menu is generated based on this information. This information is materialized by the "menu generation module." Furthermore, real-time video of the user training is received, and instructions for correcting training form are generated using the form check module. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. Based on this information, training instructions and encouraging messages are appropriately adjusted. The user's schedule information is also stored on the server, and a training plan that makes effective use of spare time is formulated by the "schedule management module."

[0651] 2. Terminal:

[0652] Users can experience a virtual training environment using smart glasses or a head-mounted display. During training, the user's movements are transmitted in real time to a server via the smart glasses' camera, and form guidance and correction instructions are displayed. A haptic device provides physical guidance on form during training. In addition, cheering messages and instructional content are customized based on an emotion engine and provided to the user.

[0653] Dietary management

[0654] 1. Server:

[0655] The server receives images of meals taken by the user and performs image analysis. This analysis uses a meal image analysis module and a machine learning model to identify foods and their portions. Based on the analysis results, calorie calculations are performed and the results are derived by the calorie calculation module. Furthermore, the server generates an optimal menu taking into account the user's likes and dislikes, dietary history, and emotional state. This information is provided to the user by the "menu suggestion module."

[0656] 2. Terminal:

[0657] The user uses the smart glasses to take photos of their meals and send them to the server. The meal record module records the user's meal contents, and the menu display module displays appropriate menu suggestions to the user.

[0658] community

[0659] 1. Server:

[0660] The user matching module matches users with similar body types and hobbies. The event planning module plans and notifies users of training sessions and events for matched users. The emotion engine recognizes the emotional state of users when they communicate with each other and appropriately supports their interactions.

[0661] 2. Terminal:

[0662] Users can receive event notifications and participate in virtual training sessions, interact with other users in virtual or augmented reality environments, and be supported by an emotion engine.

[0663] Specific examples

[0664] 1. Training menu planning:

[0665] The user takes a photo of the fitness model with the smart glasses and sends it to the server. The server analyzes the image and generates a training menu. The user then begins training, and the video is sent in real time via the smart glasses' camera. The form check module analyzes the user's form, and appropriate guidance is provided via the haptic device.

[0666] 2. Dietary Management:

[0667] A user takes a photo of their lunch salad and steak using smart glasses and sends it to the server. Image analysis is performed to calculate the calories of each food item. The user's emotional state is also analyzed, and a menu appropriate to their psychological state is suggested. For example, if a user is feeling stressed, a menu using ingredients with a relaxing effect will be suggested.

[0668] 3. Community:

[0669] The server matches users with common goals and hobbies, plans monthly training sessions, and notifies them. Users receive the notifications, participate in events they are interested in, and interact with other users. The emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[0670] Prompt Sentence Examples

[0671] "Analyze images of your fitness goals and generate the optimal training menu."

[0672] "Analyzes user video feeds, recognizes real-time emotional states, and generates supportive messages"

[0673] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0674] Step 1:

[0675] The user uses smart glasses or a head-mounted display to take an image of the desired body shape and sends the image to the server via the terminal.

[0676] Input: Image data of the desired body shape

[0677] Output: The image is sent to the server

[0678] Step 2:

[0679] The server inputs the received image data into the image analysis module and performs image analysis using TensorFlow and PIL. This analysis extracts the features of the user's target body shape.

[0680] Input: Image data of the desired body shape

[0681] Data processing: Resize and normalize the image to 128x128 pixels.

[0682] Data computation: Feature extraction with TensorFlow model

[0683] Output: Feature data of target body shape

[0684] Step 3:

[0685] The server generates an optimal training menu using a menu generation module based on the results of the image analysis.

[0686] Input: Feature data of target body shape

[0687] Data calculation: Applying an algorithm to generate training menus based on feature values

[0688] Output: Training menu data

[0689] Step 4:

[0690] When the user starts training, the server receives the user's video in real time from the terminal and generates appropriate form correction instructions using a form check module.

[0691] Input: Real-time video data of the user

[0692] Data processing: Processing video data in real time and analyzing training form

[0693] Data calculations: Applying algorithms to evaluate the suitability of a form

[0694] Output: Form correction instruction data

[0695] Step 5:

[0696] The server uses an emotion engine to analyze the user's facial expressions and voice in real time to recognize their emotional state, and then adjusts the training instructions and cheering messages accordingly.

[0697] Input: User's facial expression data and voice data

[0698] Data processing: Input facial expression data and voice data into the emotion analysis model

[0699] Data Computing: Recognizing Emotional States with Sentiment Analysis Models

[0700] Output: Emotional state data and cheering message

[0701] Step 6:

[0702] The terminal displays to the user training menus, form correction instructions, and emotional support messages sent from the server.

[0703] Input: Training menu, form correction instructions, support messages

[0704] Output: Training menu, form correction instructions, and cheering messages are displayed on the device.

[0705] Step 7:

[0706] The user takes an image of their meal through the smart glasses and sends the image to the server.

[0707] Input: Food image data

[0708] Output: The image is sent to the server

[0709] Step 8:

[0710] The server uses a meal image analysis module to analyze the received meal images to identify foods and their portions.

[0711] Input: Food image data

[0712] Data processing: Inputting images into the analysis model

[0713] Data Computation: Food Identification and Quantity Calculation Using Image Analysis Models

[0714] Output: Food data and quantity data

[0715] Step 9:

[0716] The server uses a calorie calculation module to calculate calories based on the identified food data and amount data.

[0717] Input: Food data and quantity data

[0718] Data calculation: Apply calorie calculation algorithm

[0719] Output: Calorie data

[0720] Step 10:

[0721] The server takes into account the user's likes and dislikes, eating history, and emotional state and uses a menu suggestion module to generate an optimal menu.

[0722] Input: User likes and dislikes, food history, and emotional state data

[0723] Data calculation: Apply menu generation algorithm

[0724] Output: Menu data

[0725] Step 11:

[0726] The terminal displays the menu suggestions sent from the server to the user and makes suggestions for the next meal.

[0727] Input: Menu data

[0728] Output: Menu data is displayed on the terminal.

[0729] Step 12:

[0730] The server uses a user matching module to match users with similar body types and hobby preferences.

[0731] Input: User's body type data and hobby data

[0732] Data calculation: Apply matching algorithm

[0733] Output: Matching result data

[0734] Step 13:

[0735] The server plans and notifies training sessions and events for matched users.

[0736] Input: Matching result data

[0737] Output: Training session and event notification data

[0738] Step 14:

[0739] The terminal notifies the user of training sessions and events sent from the server.

[0740] Input: Training session and event notification data

[0741] Output: Training session and event notifications appear on your device

[0742] Step 15:

[0743] Users participate in virtual training sessions and events, and the server analyzes their emotional state during communication and provides appropriate interaction support.

[0744] Input: User emotion data

[0745] Data calculation: Applying emotional state analysis algorithms

[0746] Output: AC support data

[0747] 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.

[0748] 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.

[0749] 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.

[0750] [Second embodiment]

[0751] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0752] 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.

[0753] 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).

[0754] 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.

[0755] 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.

[0756] 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).

[0757] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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."

[0763] This invention is a system that develops optimal training menus for individual users, manages dietary habits, and supports community activities. This system consists of three main components: a server, a terminal, and users.

[0764] Training menu planning / guidance

[0765] server:

[0766] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[0767] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[0768] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[0769] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[0770] Device:

[0771] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[0772] User:

[0773] Image transmission: Send an image of the desired body shape from your device to the server.

[0774] Training implementation: Training is carried out according to instructions from the server.

[0775] Dietary management

[0776] server:

[0777] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[0778] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[0779] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history.

[0780] Device:

[0781] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[0782] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[0783] User:

[0784] Food photography: Take a photo of your food and send it to the server from your device.

[0785] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[0786] community

[0787] server:

[0788] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[0789] Event planning module: Plans and announces training sessions and events between matched users.

[0790] Device:

[0791] Community Participation Module: Users can view community information and participate in events.

[0792] Event notification module: Notifies the user of event information sent from the server.

[0793] User:

[0794] Community participation: Become interested in the events you are notified about and participate through the app.

[0795] Socialize: Attend events and connect with other users.

[0796] Specific examples

[0797] 1. Training menu planning / guidance:

[0798] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[0799] When the user starts training, the smartphone camera sends the video to the server in real time, and the form check module generates appropriate form correction instructions and gives them to the user.

[0800] 2. Dietary Management:

[0801] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[0802] Based on the user's likes and dislikes and past eating history, the server suggests a menu for the next meal and displays it on the device.

[0803] 3. Community:

[0804] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[0805] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[0806] The processing flow will be explained below.

[0807] Training menu planning / guidance

[0808] Step 1:

[0809] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[0810] Step 2:

[0811] The image reception and analysis module on the server receives the images and extracts body shape features using an image analysis model.

[0812] Step 3:

[0813] The server's menu generation module generates the optimal training menu for the user based on the results of image analysis.

[0814] Step 4:

[0815] The server transmits the generated training menu to the terminal and displays it to the user.

[0816] Step 5:

[0817] The user starts training and transmits images to the server in real time via the device's camera.

[0818] Step 6:

[0819] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the user's training form.

[0820] Step 7:

[0821] The server sends the generated correction instructions to the terminal and displays them to the user, who then corrects the training form according to the instructions.

[0822] Step 8:

[0823] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[0824] Dietary management

[0825] Step 1:

[0826] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[0827] Step 2:

[0828] The server's food image analysis module receives the image and uses image analysis models to recognize the food content, identifying the type and quantity of food.

[0829] Step 3:

[0830] The server's calorie calculation module calculates the calories of each food item based on the results of image analysis.

[0831] Step 4:

[0832] The server generates advice for the next meal based on the calorie calculation results, and creates menu suggestions that take into account the user's preferences and past meal history.

[0833] Step 5:

[0834] The server generates a menu suggestion, which is sent to the terminal and displayed to the user. The user then checks the menu and selects their next meal.

[0835] community

[0836] Step 1:

[0837] The server's user matching module analyzes the user's desired body type and hobbies and preferences, and performs matching based on this.

[0838] Step 2:

[0839] The server's event planning module plans training sessions and events based on the matching results.

[0840] Step 3:

[0841] The server generates event information planned by the user and sends it to the terminal, notifying the user of events that match their interests.

[0842] Step 4:

[0843] An event notification module of the terminal receives the event information sent from the server and notifies the user of the event information.

[0844] Step 5:

[0845] The user checks the notification content and registers to participate in events of interest.

[0846] Step 6:

[0847] On the day of the event, users will participate in training sessions and offline meetups at designated locations or online to deepen their interactions with other users.

[0848] Example 1

[0849] 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."

[0850] In today's busy lifestyles, it is difficult to develop optimal training programs for individual users, manage their diets, and support community activities. Conventional systems lack the advanced analytical capabilities to address individual needs or the ability to provide real-time feedback. This makes it difficult for users to self-manage and maintain motivation. The present invention aims to solve these challenges and support users in maintaining their health and building communities.

[0851] 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.

[0852] In this invention, the server includes means for receiving images of a desired body shape and analyzing the images using a machine learning model, means for generating an optimal training menu using a genetic algorithm based on the image analysis results, means for receiving video of a user performing a workout in real time and generating training form correction instructions using posture analysis technology, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents using image recognition technology, means for calculating calories by referencing a food composition database based on the image analysis results, means for generating an optimal menu taking into account the user's likes and dislikes using a recommendation algorithm, means for matching users with similar desired body shapes and hobbies and preferences using a clustering algorithm, and means for planning and notifying training sessions and events for matched users. This enables the provision of training menus tailored to individual user needs, appropriate dietary management, and support for community activities.

[0853] "Image analysis" is a technology that processes image data to understand and recognize its contents.

[0854] A "machine learning model" is a collection of algorithms that learn from large amounts of data and perform specific tasks automatically.

[0855] A "genetic algorithm" is a computational method for finding optimal solutions by imitating the evolutionary process of living organisms.

[0856] "Posture analysis technology" is a technology that analyzes a person's body movements and poses and identifies their posture.

[0857] The "Food Composition Database" is a database that systematically organizes and provides nutritional information on various foods.

[0858] A "recommendation algorithm" is an algorithm that analyzes user preferences and behavioral history to make optimal suggestions to individual users.

[0859] A "clustering algorithm" is a method for grouping data based on similarity.

[0860] "Real-time" refers to data processing and transmission occurring almost simultaneously with the real time axis.

[0861] A "training menu" is a collection of movements or exercises designed to achieve a specific goal or objective.

[0862] "Schedule information" is information including plans and timetables set by the user.

[0863] "Meal contents" refers to the types and amounts of ingredients and dishes consumed by the user.

[0864] "Calorie calculation" is a calculation to calculate the amount of energy contained in food.

[0865] "Matching" refers to linking multiple elements (e.g., users) based on specific conditions.

[0866] "Event notification" is the act of communicating information to interested parties about a particular occurrence or activity.

[0867] The present invention is a system that develops optimal training menus for individual users, manages their diet, and supports community activities. To implement this system, the following specific hardware and software are required.

[0868] Training menu planning / guidance

[0869] server:

[0870] Image reception and analysis module: The server receives an image of the user's desired body shape and performs image analysis using a machine learning model (e.g., TensorFlow). This analysis extracts body shape features (such as muscle distribution and fat distribution).

[0871] Menu generation module: The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[0872] Form check module: The server receives real-time video of the user training and uses posture analysis technology (e.g., OpenPose) to check whether the training is being performed with proper form, generating correction instructions as necessary.

[0873] Schedule management module: The server creates a training plan that utilizes the user's free time based on the user's schedule information.

[0874] Device:

[0875] Training module: The user uses the device's camera to transmit images of themselves training to the server, and receives real-time guidance on their form. The module also displays training menus and correction instructions sent from the server.

[0876] User:

[0877] Image transmission: The user sends an image of the desired body shape from their smartphone to the server. For example, they can take a photo of a fitness model and send it.

[0878] Training implementation: The user implements the training according to the instructions from the server.

[0879] Dietary management

[0880] server:

[0881] Food image analysis module: The server receives food images taken by the user and analyzes the food contents using image recognition technology (e.g., ResNet). This analysis identifies the foods contained in the meal and their amounts.

[0882] Calorie calculation module: The server calculates calories based on the image analysis results and references a food composition database (e.g., USDA food composition database).

[0883] Menu suggestion module: The server uses a recommendation algorithm (e.g., collaborative filtering) to generate an optimal menu, taking into account the user's likes and dislikes and dietary history.

[0884] Device:

[0885] Meal Recording Module: The user takes a photo of the meal and sends it to the server.

[0886] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[0887] User:

[0888] Food photography: A user takes a photo of their meal with their smartphone and sends it to the server from the device. For example, they take a photo of their lunch or dinner.

[0889] Menu confirmation: The user checks the menu suggestions from the server and selects the appropriate meal.

[0890] Community Activities

[0891] server:

[0892] User matching module: The server uses a clustering algorithm (e.g., K-Means) to match users with similar desired body types and hobbies and preferences.

[0893] Event planning module: The server plans training sessions and events for matched users and notifies them of the information.

[0894] Device:

[0895] Community participation module: Users can check community information and participate in events.

[0896] Event notification module: Notifies the user of event information sent from the server.

[0897] User:

[0898] Community participation: Users are interested in events they are notified about and participate through the app, for example, by attending a monthly training session.

[0899] Socialize: Users attend events, interact with other users, and train together.

[0900] Specific examples

[0901] 1. Training menu planning / guidance:

[0902] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server then analyzes the image using TensorFlow and generates an optimal training menu.

[0903] When the user starts training, the smartphone camera sends images to the server in real time, and the form check module using OpenPose generates appropriate form correction instructions and provides them to the user.

[0904] 2. Dietary Management:

[0905] A user takes a photo of their lunch salad and steak and sends it to the server, which analyzes the image using ResNet and calculates the calories of each food item from the USDA Food Composition Database.

[0906] The server uses collaborative filtering to suggest the next meal menu based on the user's likes and dislikes and past eating history, and displays it on the device.

[0907] 3. Community Activities:

[0908] The server uses clustering to match users with common goals and hobbies, and then plans and notifies them of monthly training sessions.

[0909] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[0910] Prompt Sentence Examples

[0911] "How can I send you an image of the body shape I'm aiming for?"

[0912] "I want to make sure my form is correct during my workouts. How can I do that?"

[0913] "I'd like you to calculate the calories in today's lunch. I took a photo and sent it to you."

[0914] "I would like to participate in events where I can interact with people who share the same hobbies."

[0915] The above is a specific embodiment of the present invention. This system makes it possible to provide training menus tailored to the needs of individual users, manage their diet appropriately, and support community activities.

[0916] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0917] Training menu planning / guidance

[0918] Step 1:

[0919] The user takes a picture of the body shape they are aiming for with their smartphone and sends it to the server using a dedicated app. The input is the image of the body shape acquired by the user, and the output is the result of sending the image data to the server.

[0920] Step 2:

[0921] The server receives the images and performs image analysis using a machine learning model (TensorFlow). The input is the received image data, and the output is data that extracts body shape features. This analysis allows for the acquisition of body shape features such as muscle distribution and fat distribution.

[0922] Step 3:

[0923] The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The input is the extracted body shape feature data, and the output is an optimized training menu. The menu includes the required exercises, their intensity, frequency, etc.

[0924] Step 4:

[0925] The user starts training and sends the training video to the server in real time using the smartphone camera. The input is the video data during training, and the output is the video transmission result to the server.

[0926] Step 5:

[0927] The server analyzes the video received in real time and uses posture analysis technology such as OpenPose to check whether the correct form is being maintained. The input is real-time video data, and the output is the evaluation result of the form appropriateness. Instructions for correcting the form are generated as needed.

[0928] Step 6:

[0929] The server generates form correction instructions, which are sent to the terminal and displayed to the user. The input is the form correction instruction data, and the output is the display result on the user's terminal. The user performs training according to these instructions.

[0930] Dietary management

[0931] Step 1:

[0932] The user takes a photo of their meal with their smartphone and sends it to the server using a dedicated app. The input is the image data of the meal, and the output is the result of sending the image data to the server.

[0933] Step 2:

[0934] The server receives the food images and performs image analysis using image recognition techniques such as ResNet. The input is the received image data, and the output is the identified foods and their quantities.

[0935] Step 3:

[0936] The server calculates calories based on the image analysis results by checking against the food composition database (USDA food composition database). The input is the identified food and its quantity data, and the output is the calculated calorie value.

[0937] Step 4:

[0938] The server uses a collaborative filtering algorithm to generate a menu for the next meal, taking into account the user's likes and dislikes and dietary history. The input is the user's dietary history and likes and dislikes, and the output is the generated menu.

[0939] Step 5:

[0940] The server sends the generated menu to the user's device and suggests the next meal. The input is the generated menu data, and the output is the display result on the user's device. The user selects an appropriate meal based on the suggestions.

[0941] Community Activities

[0942] Step 1:

[0943] The server analyzes the user's desired body type and hobbies and preferences, and matches similar users using a clustering algorithm (K-Means). The input is the user's goals and preference data, and the output is the matching results.

[0944] Step 2:

[0945] The server plans training sessions and events for matched users and notifies them of the information. The input is the matching result data, and the output is the planned event information data.

[0946] Step 3:

[0947] The server sends planned event information to users' terminals and encourages them to participate in the event. The input is event information data, and the output is the notification result sent to the user terminal.

[0948] Step 4:

[0949] The user checks the event information displayed on the terminal and registers to participate in the events they are interested in. The input is the event information data, and the output is the registration result.

[0950] Step 5:

[0951] On the day of the event, users participate in community activities with other users and deepen their interactions. The input is event participation information, and the output is interaction experience points and feedback.

[0952] (Application example 1)

[0953] 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."

[0954] Conventional training support systems have had the problem of making it difficult to create training menus tailored to each user's physical condition and goals, and of not being able to check or correct form in real time. Furthermore, when it comes to dietary management, calorie calculations and menu suggestions are time-consuming, and measures to address these issues are insufficient. Furthermore, there was a lack of mechanisms to encourage interaction between users with common goals or hobbies or to participate in events, making it difficult to maintain motivation.

[0955] 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.

[0956] In this invention, the server includes: means for receiving images of the desired body shape and analyzing the images; means for generating an optimal training menu based on the image analysis results; means for receiving video of the user's training in real time and generating training form correction instructions; means for formulating a training plan for spare time based on the user's schedule information; means for the user to take images of their meals and send them to the server, which then analyzes the images and calculates calories; and means for matching users with common goals and planning and notifying them of training events inside and outside the store. This enables the formulation of optimal training menus tailored to each user's individual goals, real-time form checks, and smooth calorie management and menu suggestions. Furthermore, it encourages interaction and event participation among users with common goals and hobbies, helping to maintain motivation.

[0957] 1. "Body shape image" is an image that visually shows the ideal body shape that the user is aiming for.

[0958] 2. "Image analysis" is the process of analyzing transmitted image data and extracting necessary information from its contents.

[0959] 3. "Training Menu" means a schedule of exercises and activities required for the user to achieve the desired body shape.

[0960] 4. "Video" refers to video data of a user performing training.

[0961] 5. "Form correction instructions" refers to real-time instruction provided to help users adopt the correct exercise posture.

[0962] 6. "Schedule information" is data that represents a user's daily activities and free time.

[0963] 7. "Spare time" refers to a period of time in a user's schedule when they can engage in an activity even for a short period of time.

[0964] 8. "Meal images" are photographs of food taken by the user.

[0965] 9. "Calorie counting" is the process of calculating the amount of energy intake based on the contents of a meal.

[0966] 10. "Menu suggestion" is a suggestion for the next meal that takes into account the user's preferences and nutritional balance.

[0967] 11. A "common goal" is a training or health-related objective shared by multiple users.

[0968] 12. "Matching" is the process of identifying and pairing or grouping users with common goals or interests.

[0969] 13. A "Training Event" is an opportunity for users with similar goals to come together and exercise together.

[0970] 14. "Notification" means a communication method used to inform users about training events or important information.

[0971] The system of the present invention is designed to provide users with personalized training menus, support dietary management, and promote community activities. The system consists of three main components: a server, a terminal, and users.

[0972] Training menu planning / guidance

[0973] server:

[0974] The server performs the following functions:

[0975] "Image Reception and Analysis Module": Receives images of the user's desired body shape and performs image analysis. This analysis uses software such as the image analysis library "OpenCV." The analysis results are used to extract the characteristics of the user's ideal body shape.

[0976] "Menu generation module": Generates an optimal training menu based on the image analysis results. This uses a generative AI model (e.g., GPT-4).

[0977] "Form Check Module": This module receives real-time video footage of the user training, checks whether the training is being performed with proper form, and generates correction instructions as necessary. This process uses the real-time video processing library "Kinesis Video Streams."

[0978] "Schedule Management Module": Based on the user's schedule information, it creates a training plan that utilizes their free time.

[0979] Device:

[0980] The device is equipped with the following features:

[0981] "Training module": The user uses the device's camera to send images to the server while training, and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[0982] User:

[0983] The user performs the following actions:

[0984] "Send image": Send an image of the desired body shape from your device to the server.

[0985] "Training": Training is carried out according to instructions from the server.

[0986] Dietary management

[0987] server:

[0988] The server supports the following features:

[0989] "Meal Image Analysis Module": Receives meal images taken by the user and performs image analysis. This analysis uses "Tesseract OCR" to identify the foods contained in the meal and their amounts.

[0990] "Calorie Calculation Module": Calculates the calorie content of food based on the results of image analysis. Uses a dedicated calorie calculation API.

[0991] "Menu suggestion module": Suggests the menu for the next meal, taking into account the user's likes and dislikes and eating history.

[0992] Device:

[0993] The device will be equipped with the following features:

[0994] "Meal Recording Module": The user takes a photo of what they have eaten and sends it to the server.

[0995] "Menu display module": Displays the menu sent from the server to the user and suggests the next meal.

[0996] User:

[0997] The user performs the following actions:

[0998] "Photo of food": Take a photo of your meal and send it from your device to the server.

[0999] "Confirm Menu": Check the menu suggestions from the server and select an appropriate meal.

[1000] community

[1001] server:

[1002] The server provides the following functions:

[1003] "User Matching Module": Matches users with common goals.

[1004] "Event Planning Module": Plans and announces training sessions and events between matched users. Data management uses "MySQL" and "Django."

[1005] Device:

[1006] The device will be equipped with the following features:

[1007] "Community Participation Module": Users check community information and participate in events.

[1008] "Event notification module": Notifies the user of event information sent from the server.

[1009] User:

[1010] The user performs the following actions:

[1011] "Community participation": Become interested in a notified event and participate through the app.

[1012] "Interact": Participate in events and deepen your interactions with other users.

[1013] Prompt Sentence Examples

[1014] 1. Training menu generation

[1015] "Upload an image of the body shape you want to achieve. After analyzing it, the system will suggest the optimal training menu."

[1016] 2. Real-time form checking

[1017] "Please record your training with a camera and send it to us. We will check your form in real time and provide appropriate guidance."

[1018] 3. Dietary Management

[1019] "Take a photo of the food you ate today and upload it. We'll analyze the calories and give you suggestions for your next meal."

[1020] 4. Community Support

[1021] "We will be organizing events for members with common goals. Please check the announcements if you would like to participate."

[1022] The above is a specific embodiment for carrying out the present invention, which makes it possible to provide training guidance and dietary management that is optimized for each individual user, and also to increase motivation through community activities.

[1023] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1024] Step 1:

[1025] The user takes a picture of the body shape they are aiming for using their smartphone and sends it from the device to the server.

[1026] Input: Body image

[1027] Data processing: Image data stored on the device is uploaded to the server via the device's application.

[1028] Output: The body image is sent to the server.

[1029] Step 2:

[1030] The server's image reception and analysis module analyzes the received body shape image.

[1031] Input: Body image

[1032] Data processing: Image features are extracted using the OpenCV library to identify ideal body shape properties.

[1033] Output: Body shape characteristic data is obtained as the analysis result.

[1034] Step 3:

[1035] The server's menu generation module generates an optimal training menu based on the image analysis results.

[1036] Input: Body shape feature data

[1037] Data processing: Using a generative AI model (e.g., GPT-4), a training menu is generated based on the user's goals and current physical condition.

[1038] Output: Customized training menu

[1039] Step 4:

[1040] The user begins training, takes a video of themselves using their smartphone camera, and sends it to the server in real time from the device.

[1041] Input: Video of training

[1042] Data processing: Real-time video data is acquired using the device's camera function.

[1043] Output: Live video is sent to the server.

[1044] Step 5:

[1045] The server's form check module analyzes the real-time video and generates instructions for correcting training form.

[1046] Input: Live footage of training

[1047] Data Processing: Using Kinesis Video Streams and OpenCV, we analyze the user's posture and determine the proper form.

[1048] Output: Form correction instructions

[1049] Step 6:

[1050] The server's instructions are sent to the terminal and displayed on the user's terminal.

[1051] Input: Form correction instructions

[1052] Data processing: Transfer instruction data to the terminal.

[1053] Output: Form correction instructions are displayed on the terminal.

[1054] Step 7:

[1055] The user takes a photo of the meal and sends it to the server from the device.

[1056] Input: Food image

[1057] Data processing: Photo data stored on the device is uploaded to the server via the app.

[1058] Output: The food image is sent to the server.

[1059] Step 8:

[1060] The server's food image analysis module analyzes the received food image and calculates calories.

[1061] Input: Food image

[1062] Data processing: Identify food items in the image using Tesseract OCR and calculate calories using a dedicated API.

[1063] Output: Calorie data of meals

[1064] Step 9:

[1065] The server's menu suggestion module considers calorie data and the user's preferences to suggest a menu for the next meal.

[1066] Input: Calorie data, user preference data

[1067] Data processing: Generates an optimal menu list based on past meal history and preference data.

[1068] Output: Suggested menu

[1069] Step 10:

[1070] The server matches users with common goals and organizes and announces training events.

[1071] Input: User goal data

[1072] Data Processing: Using Django framework and MySQL database to match user information and plan training events.

[1073] Output: Event notification data

[1074] Step 11:

[1075] The server sends the event notification data to the terminal, which displays the notification to the user.

[1076] Input: Event notification data

[1077] Data processing: Send notification data to the device.

[1078] Output: An event notification is displayed on the user's terminal.

[1079] The above is a specific processing flow of the system of the present invention, which provides optimized support to individual users.

[1080] 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.

[1081] This system creates optimal training menus for individual users, manages their diet, and supports community activities. It also incorporates an emotion engine that recognizes the user's emotional state, enabling these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and users.

[1082] Training menu planning / guidance

[1083] server:

[1084] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[1085] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[1086] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[1087] Emotion engine: Analyzes the user's facial expressions and voice to recognize their emotional state, and uses that information to appropriately adjust the content of training guidance and support.

[1088] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[1089] Device:

[1090] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The server also displays training menus, correction instructions, and emotional support messages.

[1091] User:

[1092] Image transmission: Send an image of the desired body shape from your device to the server.

[1093] Training: Train according to instructions and encouraging messages from the server.

[1094] Dietary management

[1095] server:

[1096] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[1097] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[1098] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history. In addition, an emotion engine analyzes the user's emotional state during meal recording and, based on the results, suggests menus that are adapted to the user's psychological state.

[1099] Device:

[1100] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[1101] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[1102] User:

[1103] Food photography: Take a photo of your food and send it to the server from your device.

[1104] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[1105] community

[1106] server:

[1107] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[1108] Event planning module: Plans and announces training sessions and events between matched users.

[1109] Emotion Engine: Recognizes the emotions of each user during communication between users and appropriately supports interactions within the community based on the results.

[1110] Device:

[1111] Community Participation Module: Users can view community information and participate in events.

[1112] Event notification module: Notifies the user of event information sent from the server.

[1113] User:

[1114] Community participation: Become interested in the events you are notified about and participate through the app.

[1115] Socialize: Attend events and connect with other users.

[1116] Specific examples

[1117] 1. Training menu planning / guidance:

[1118] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[1119] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[1120] 2. Dietary Management:

[1121] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[1122] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[1123] 3. Community:

[1124] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[1125] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[1126] The processing flow will be explained below.

[1127] Training menu planning / guidance

[1128] Step 1:

[1129] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[1130] Step 2:

[1131] The server's image reception and analysis module analyzes the received images and extracts body shape characteristics from the analysis results.

[1132] Step 3:

[1133] The menu generation module of the server generates an optimal training menu based on the image analysis results.

[1134] Step 4:

[1135] The server transmits the generated training menu to the terminal, and the user confirms the displayed menu.

[1136] Step 5:

[1137] The user starts training and sends real-time video to the server via the device's camera.

[1138] Step 6:

[1139] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the training form. The emotion engine also recognizes the user's emotions from the video and audio.

[1140] Step 7:

[1141] The server generates correction instructions and sends cheering messages based on the user's emotional state to the terminal, which the user confirms. The user then continues to correct their training form accordingly.

[1142] Step 8:

[1143] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[1144] Dietary management

[1145] Step 1:

[1146] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[1147] Step 2:

[1148] The server's food image analysis module receives the image and performs image analysis to identify the type and amount of food.

[1149] Step 3:

[1150] The server's calorie calculation module calculates the calories of each food item based on the image analysis results.

[1151] Step 4:

[1152] The server takes into account the calorie calculation results, the user's preferences, and past meal history, and then uses an emotion engine to analyze the user's emotional state when recording their meals, and based on the results, generates a menu that is adapted to the user's psychological state.

[1153] Step 5:

[1154] The server sends the generated menu suggestions to the terminal, and the user checks the displayed menu. The user selects an appropriate meal and then follows the instructions.

[1155] community

[1156] Step 1:

[1157] The server's user matching module analyzes users' desired body type, hobbies, thoughts, and emotional state, and matches users with many commonalities.

[1158] Step 2:

[1159] The server's event planning module plans training sessions and events for matched users. The emotion engine determines the user's emotional state and notifies them of events at the optimal time.

[1160] Step 3:

[1161] The server sends the generated event information to the terminal and notifies the user, who then checks the notification content.

[1162] Step 4:

[1163] A user applies to participate in an event that they are interested in. The device sends the participation request to the server.

[1164] Step 5:

[1165] On the day of the event, users participate in the event at a designated location or online. The server's emotion engine monitors the user's emotional state during the event in real time and generates feedback to support interaction.

[1166] Step 6:

[1167] The server generates feedback and sends it to the terminal, where the user receives it. This deepens interaction with other users and increases motivation for training.

[1168] Example 2

[1169] 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."

[1170] Conventional training and diet management systems struggle to provide optimal guidance and support tailored to individual users' goals and emotional states. Furthermore, they lack emotional support for communication and collaborative training, making it difficult to maintain motivation. This results in a lack of continuous health management and community building for users.

[1171] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of a desired body shape and performing image analysis, means for generating an optimal training menu based on the image analysis results, means for receiving video of a user performing training in real time and generating instructions for correcting the user's training form, means for analyzing the user's emotional state in real time and generating an emotional support message, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents, means for calculating calories based on the image analysis results, means for analyzing the user's emotional state and generating an optimal menu based on the analyzed results, means for matching users with similar desired body shapes and hobbies, means for planning and notifying training sessions and events for matched users, and means for recognizing emotions during communication between users and providing emotional support for interaction. This makes it possible to provide optimal training and dietary management for each user, and further realize support for community activities and emotional motivation maintenance.

[1172] "Image reception and analysis module" refers to the device or software that receives images of the desired body shape and performs image analysis.

[1173] A "menu generation module" refers to a device or software that generates an optimal training menu based on the results of image analysis, taking into account the user's goals and current physical condition.

[1174] A "form check module" refers to a device or software that receives video of a user performing training in real time and generates instructions for correcting the training form.

[1175] An "emotion engine" refers to a device or software that analyzes a user's facial expressions and voice in real time, recognizes their emotional state, and generates cheering messages and other information based on that information.

[1176] A "schedule management module" refers to a device or software that creates a training plan for spare time based on the user's schedule information.

[1177] A "meal image analysis module" refers to a device or software that receives images of meals taken by users and performs image analysis of the meal contents.

[1178] A "calorie calculation module" refers to a device or software that calculates the calories of a meal based on the results of image analysis.

[1179] A "menu suggestion module" refers to a device or software that generates an optimal menu taking into account the user's emotional state and eating history.

[1180] A "user matching module" refers to a device or software that matches users with similar body types and hobbies.

[1181] An "event planning module" refers to a device or software that plans and notifies training sessions and events between matched users.

[1182] "Community participation module" refers to a device or software that provides a function for users to check community information and participate in events.

[1183] An "event notification module" refers to a device or software that notifies a user of event information sent from a server.

[1184] "Training implementation module" refers to a device or software that provides a function that allows a user to use the device's camera to send images to a server while training and receive form guidance in real time.

[1185] A "meal record module" refers to a device or software that provides the function of allowing a user to take a photo of what they have eaten and send it to a server.

[1186] A "menu display module" refers to a device or software that displays the menu sent from the server to the user and suggests the next meal.

[1187] The present invention is a system for efficiently managing the health of each user. This system consists of three main elements: a server, a terminal, and a user, and realizes the invention through the following configuration and operation.

[1188] server

[1189] The server uses multiple dedicated modules to support users in training, dietary management, and community activities.

[1190] 1. Image reception and analysis module

[1191] The server receives images of the user's desired body shape and performs image analysis. Specifically, it uses image analysis software (e.g., OpenCV) to extract body shape characteristics. Based on this information, it creates a training menu, which will be described later.

[1192] 2. Menu Generation Module

[1193] Based on the results of image analysis, the server generates an optimal training menu that takes into account the user's goals and current physical condition. For example, it creates a program that combines strength training three times a week and aerobic exercise twice a week and provides it to each individual user.

[1194] 3. Form Check Module

[1195] The server receives real-time video footage sent from the user's device while they are training. Using video analysis technology, it checks the user's form and generates necessary correction instructions. For example, if the user's posture is poor, it sends a message saying, "Straighten your back."

[1196] 4. Emotion Engine

[1197] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state. Using technologies such as Google Cloud Vision API and Microsoft Azure Emotion API, the server then uses this information to appropriately tailor training instructions and support messages.

[1198] 5. Schedule Management Module

[1199] The server creates a training plan that utilizes the user's free time based on the user's schedule information, making it possible to provide a training plan that the user can continue without straining themselves.

[1200] 6. Food Image Analysis Module

[1201] The server receives the image of the meal taken by the user and performs image analysis using OpenCV etc. to identify the ingredients and their amounts, and calculates the calories based on this information.

[1202] 7. Calorie Counting Module

[1203] The server calculates the calories of the meal based on the image analysis results, allowing the user to accurately grasp the calorie intake of their food.

[1204] 8. Menu suggestion module

[1205] The server analyzes the user's eating history and emotional state to suggest optimal meals. For example, it generates a meal plan using ingredients that have a relaxing effect for a stressed user.

[1206] 9. User Matching Module

[1207] The server matches users with similar body types, hobbies, and ways of thinking. This module allows users to find others who share the same goals and work together to achieve their goals.

[1208] 10. Event Planning Module

[1209] The server plans and notifies training sessions and events between matched users, thereby promoting interaction between users.

[1210] 11. Communication Support

[1211] The server recognizes emotions during communication between users and supports interactions based on those emotions. For example, it provides appropriate interaction support through emotion analysis during an event.

[1212] Terminal

[1213] A terminal refers to a device or software that communicates with a server through user operation and provides various information.

[1214] 1. Training Implementation Module

[1215] When a user starts training, the device's camera activates and transmits the video in real time to the server, which then displays the training menu, form instructions, and encouraging messages.

[1216] 2. Food Record Module

[1217] It provides a function that allows users to take a photo of what they have eaten and send it to the server.

[1218] 3. Community Participation Module

[1219] It provides users with the ability to check community information and participate in events.

[1220] User

[1221] Users can use this system to manage their own health. Specific operations include sending images of their desired body shape, doing training, taking photos of meals, and participating in the community.

[1222] Specific examples

[1223] 1. Training menu planning / guidance:

[1224] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[1225] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[1226] 2. Dietary Management:

[1227] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[1228] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[1229] 3. Community:

[1230] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[1231] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[1232] Example prompt for a generative AI model:

[1233] Develop a system that generates an optimal training menu based on images of the user's desired physique, checks their form in real time, and provides cheering messages based on their emotional state. The system receives images from the user, analyzes them to create a specific training menu, analyzes footage of the training session to generate instructions for correcting their form, and uses an emotion engine to provide appropriate cheering messages.

[1234] The above is the "Mode for Carrying Out the Invention."

[1235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1236] Training menu planning / guidance

[1237] server

[1238] Step 1:

[1239] The server receives an image of a desired body type from the user.

[1240] Specific behavior:

[1241] The user takes a photo of the fitness model with their smartphone and sends it to the server via the app.

[1242] Input: An image of the body type the user is aiming for.

[1243] Output: Receiving image data.

[1244] Step 2:

[1245] The server analyzes the received images using image analysis software (e.g., OpenCV) and extracts body shape features.

[1246] Specific behavior:

[1247] The server reads the received images using OpenCV and analyzes specific features (muscle shape and fat distribution).

[1248] Input: Image data.

[1249] Output: Analyzed body feature data.

[1250] Step 3:

[1251] The server generates an optimal training menu based on the results of the image analysis.

[1252] Specific behavior:

[1253] Based on the analysis results, the server creates a menu that combines three sessions of strength training and two sessions of aerobic exercise per week.

[1254] Input: Body shape feature data.

[1255] Output: Training menu.

[1256] Terminal

[1257] Step 1:

[1258] When a user starts training, the device's camera is used to send images to the server in real time.

[1259] Specific behavior:

[1260] When the user launches the app and presses the "Start Training" button, the camera activates and the video is sent to the server.

[1261] Input: User training start signal.

[1262] Output: Real-time video data transmission.

[1263] server

[1264] Step 4:

[1265] The server analyzes the received video and checks the user's training form.

[1266] Specific behavior:

[1267] The server uses video analysis technology to analyze the user's actions in real time and evaluate whether they are correct.

[1268] Input: Real-time video data.

[1269] Output: Form check results.

[1270] Step 5:

[1271] The server generates correction instructions if the user's form is incorrect.

[1272] Specific behavior:

[1273] When the server detects improper form, it generates correction instructions such as "Stand up a little straighter."

[1274] Input: Form check result.

[1275] Output: Form correction instructions.

[1276] Step 6:

[1277] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[1278] Specific behavior:

[1279] The server performs emotion analysis using the Google Cloud Vision API and Microsoft Azure Emotion API.

[1280] Input: Real-time video and audio data.

[1281] Output: Emotional state data.

[1282] Step 7:

[1283] The server appropriately adjusts the cheering message based on the emotional state.

[1284] Specific behavior:

[1285] The server sends a message of encouragement saying "Keep it up!" to a user who is feeling unmotivated.

[1286] Input: Emotional state data.

[1287] Output: A message of encouragement.

[1288] Dietary management

[1289] User

[1290] Step 1:

[1291] The user takes a photo of the meal with their smartphone and sends it to the server.

[1292] Specific behavior:

[1293] The user takes a photo of their lunch salad and steak using the app and hits send.

[1294] Input: food photos.

[1295] Output: Sending food image data.

[1296] server

[1297] Step 2:

[1298] The server analyzes the received meal images using image analysis software (e.g., OpenCV) to identify the ingredients and their quantities.

[1299] Specific behavior:

[1300] The server analyzes the food image and identifies the type of vegetables in the salad and the gram weight of the steak.

[1301] Input: Food image data.

[1302] Output: Parsed ingredient data.

[1303] Step 3:

[1304] The server calculates the calories of the meal based on the analysis results.

[1305] Specific behavior:

[1306] The server calculates the calories based on the amount of ingredients specified and displays 500 kcal.

[1307] Input: Parsed ingredient data.

[1308] Output: Calorie calculation results.

[1309] Step 4:

[1310] The server analyzes the user's emotional state in real time and suggests a menu that suits their psychological state.

[1311] Specific behavior:

[1312] The server suggests a relaxing dinner to users who are feeling stressed.

[1313] Input: Emotional state data.

[1314] Output: Menu suggestions.

[1315] community

[1316] server

[1317] Step 1:

[1318] The server matches users with similar body types, hobbies, and ways of thinking.

[1319] Specific behavior:

[1320] The server compares the registered user information and notifies the user that "we have found users with similar goals to you."

[1321] Input: User profile data.

[1322] Output: Matching results.

[1323] Step 2:

[1324] The server plans and notifies training sessions and events between matched users.

[1325] Specific behavior:

[1326] The server announces, "The next training event is next Saturday."

[1327] Input: Matching results.

[1328] Output: Event notification.

[1329] Step 3:

[1330] The server recognizes emotions during communication between users and provides emotion-based interaction support.

[1331] Specific behavior:

[1332] The server analyzes the emotional state and generates messages during the event such as "You're having fun! Let's talk more!"

[1333] Input: Real-time emotion data.

[1334] Output: AC support message.

[1335] User

[1336] Step 1:

[1337] The user becomes interested in the event and participates through the app.

[1338] Specific behavior:

[1339] The user opens the app and presses the event participation button.

[1340] Input: User's willingness to attend the event.

[1341] Output: Event registration.

[1342] Step 2:

[1343] Users can participate in events and interact with other users.

[1344] Specific behavior:

[1345] Users can talk with other participants at the event venue and exchange messages using social networking features.

[1346] Input: User interactions.

[1347] Output: Promoting interaction.

[1348] The above are the specific processing steps of the program of this system.

[1349] (Application example 2)

[1350] 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."

[1351] Conventional training menu planning and diet management systems face challenges in that they are unable to adequately respond to users' emotional states and individual schedules. Furthermore, real-time training guidance and diet management are difficult, making it difficult for users to maintain a consistent fitness plan. Furthermore, in community activities, there is a lack of mechanisms to effectively support interactions between users. To solve these challenges, it is necessary to recognize users' emotional states and provide individually optimized guidance and management.

[1352] 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.

[1353] In this invention, the server includes means for receiving images of the target body shape and analyzing the images, means for generating an optimal training menu based on the image analysis results, means for receiving video of the user's training in real time and generating training form correction instructions, means for formulating a training plan for spare time based on the user's schedule information, means for providing training in a virtual reality environment or an augmented reality environment, means for providing form guidance using a real-time haptic device, and means for analyzing the user's emotional state and adjusting the training instruction content and support messages based on the user's emotions. This enables the provision of a consistent fitness plan tailored to each user's emotional state and real-time, effective training guidance. It also appropriately supports communication between users, revitalizing the fitness community.

[1354] The "image of the desired body type" is image data showing the ideal body type that the user desires.

[1355] "Image analysis" is the process of extracting and analyzing features from received image data.

[1356] A "training menu" is a series of exercise programs designed to help a user achieve their goals.

[1357] "Real-time video" refers to current video data while the user is working out.

[1358] "Instructions for correcting training form" refers to providing guidance and suggestions for correction to maintain proper exercise form.

[1359] "Schedule information" is data relating to the user's plans and timetable.

[1360] A "spare time training plan" is a training plan that utilizes the user's free time.

[1361] A "virtual reality environment" is a virtual training environment that a user experiences through a VR device.

[1362] An "augmented reality environment" is a training environment that uses AR technology to overlay digital information onto the real environment.

[1363] A "haptic device" is a device that provides tactile feedback, allowing users to physically feel the feedback during training.

[1364] "Emotional state" refers to the user's emotional and psychological state, and is used to provide appropriate guidance and support by analyzing it.

[1365] "Image analysis of food content" is the process of analyzing photos of meals taken by users to identify the foods and amounts included.

[1366] "Calorie calculation" refers to calculating the total calorie content of a meal based on the results of image analysis.

[1367] A "menu" is a meal plan suggested based on the user's nutritional balance and preferences.

[1368] "User likes and dislikes" is information about foods that a user likes and dislikes.

[1369] "Matching" is the process of connecting users who share common goals or interests.

[1370] "Training sessions and events" are activities or sessions where users come together to share common experiences.

[1371] "Communication support" means helping users to interact with each other in an enjoyable and effective way.

[1372] This invention is a system that supports users in formulating optimal training menus, managing their diet, and participating in community activities, and it combines an emotion engine that recognizes the user's emotional state to enable these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and a user.

[1373] Training menu planning / guidance

[1374] 1. Server:

[1375] The server receives images of the desired body shape and performs image analysis. This analysis uses TensorFlow and PIL. As a result of the image analysis, the user's body characteristics are extracted, and an optimal training menu is generated based on this information. This information is materialized by the "menu generation module." Furthermore, real-time video of the user training is received, and instructions for correcting training form are generated using the form check module. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. Based on this information, training instructions and encouraging messages are appropriately adjusted. The user's schedule information is also stored on the server, and a training plan that makes effective use of spare time is formulated by the "schedule management module."

[1376] 2. Terminal:

[1377] Users can experience a virtual training environment using smart glasses or a head-mounted display. During training, the user's movements are transmitted in real time to a server via the smart glasses' camera, and form guidance and correction instructions are displayed. A haptic device provides physical guidance on form during training. In addition, cheering messages and instructional content are customized based on an emotion engine and provided to the user.

[1378] Dietary management

[1379] 1. Server:

[1380] The server receives images of meals taken by the user and performs image analysis. This analysis uses a meal image analysis module and a machine learning model to identify foods and their portions. Based on the analysis results, calorie calculations are performed and the results are derived by the calorie calculation module. Furthermore, the server generates an optimal menu taking into account the user's likes and dislikes, dietary history, and emotional state. This information is provided to the user by the "menu suggestion module."

[1381] 2. Terminal:

[1382] The user uses the smart glasses to take photos of their meals and send them to the server. The meal record module records the user's meal contents, and the menu display module displays appropriate menu suggestions to the user.

[1383] community

[1384] 1. Server:

[1385] The user matching module matches users with similar body types and hobbies. The event planning module plans and notifies users of training sessions and events for matched users. The emotion engine recognizes the emotional state of users when they communicate with each other and appropriately supports their interactions.

[1386] 2. Terminal:

[1387] Users can receive event notifications and participate in virtual training sessions, interact with other users in virtual or augmented reality environments, and be supported by an emotion engine.

[1388] Specific examples

[1389] 1. Training menu planning:

[1390] The user takes a photo of the fitness model with the smart glasses and sends it to the server. The server analyzes the image and generates a training menu. The user then begins training, and the video is sent in real time via the smart glasses' camera. The form check module analyzes the user's form, and appropriate guidance is provided via the haptic device.

[1391] 2. Dietary Management:

[1392] A user takes a photo of their lunch salad and steak using smart glasses and sends it to the server. Image analysis is performed to calculate the calories of each food item. The user's emotional state is also analyzed, and a menu appropriate to their psychological state is suggested. For example, if a user is feeling stressed, a menu using ingredients with a relaxing effect will be suggested.

[1393] 3. Community:

[1394] The server matches users with common goals and hobbies, plans monthly training sessions, and notifies them. Users receive the notifications, participate in events they are interested in, and interact with other users. The emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[1395] Prompt Sentence Examples

[1396] "Analyze images of your fitness goals and generate the optimal training menu."

[1397] "Analyzes user video feeds, recognizes real-time emotional states, and generates supportive messages"

[1398] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1399] Step 1:

[1400] The user uses smart glasses or a head-mounted display to take an image of the desired body shape and sends the image to the server via the terminal.

[1401] Input: Image data of the desired body shape

[1402] Output: The image is sent to the server

[1403] Step 2:

[1404] The server inputs the received image data into the image analysis module and performs image analysis using TensorFlow and PIL. This analysis extracts the features of the user's target body shape.

[1405] Input: Image data of the desired body shape

[1406] Data processing: Resize and normalize the image to 128x128 pixels.

[1407] Data computation: Feature extraction with TensorFlow model

[1408] Output: Feature data of target body shape

[1409] Step 3:

[1410] The server generates an optimal training menu using a menu generation module based on the results of the image analysis.

[1411] Input: Feature data of target body shape

[1412] Data calculation: Applying an algorithm to generate training menus based on feature values

[1413] Output: Training menu data

[1414] Step 4:

[1415] When the user starts training, the server receives the user's video in real time from the terminal and generates appropriate form correction instructions using a form check module.

[1416] Input: Real-time video data of the user

[1417] Data processing: Processing video data in real time and analyzing training form

[1418] Data calculations: Applying algorithms to evaluate the suitability of a form

[1419] Output: Form correction instruction data

[1420] Step 5:

[1421] The server uses an emotion engine to analyze the user's facial expressions and voice in real time to recognize their emotional state, and then adjusts the training instructions and cheering messages accordingly.

[1422] Input: User's facial expression data and voice data

[1423] Data processing: Input facial expression data and voice data into the emotion analysis model

[1424] Data Computing: Recognizing Emotional States with Sentiment Analysis Models

[1425] Output: Emotional state data and cheering message

[1426] Step 6:

[1427] The terminal displays to the user training menus, form correction instructions, and emotional support messages sent from the server.

[1428] Input: Training menu, form correction instructions, support messages

[1429] Output: Training menu, form correction instructions, and cheering messages are displayed on the device.

[1430] Step 7:

[1431] The user takes an image of their meal through the smart glasses and sends the image to the server.

[1432] Input: Food image data

[1433] Output: The image is sent to the server

[1434] Step 8:

[1435] The server uses a meal image analysis module to analyze the received meal images to identify foods and their portions.

[1436] Input: Food image data

[1437] Data processing: Inputting images into the analysis model

[1438] Data Computation: Food Identification and Quantity Calculation Using Image Analysis Models

[1439] Output: Food data and quantity data

[1440] Step 9:

[1441] The server uses a calorie calculation module to calculate calories based on the identified food data and amount data.

[1442] Input: Food data and quantity data

[1443] Data calculation: Apply calorie calculation algorithm

[1444] Output: Calorie data

[1445] Step 10:

[1446] The server takes into account the user's likes and dislikes, eating history, and emotional state and uses a menu suggestion module to generate an optimal menu.

[1447] Input: User likes and dislikes, food history, and emotional state data

[1448] Data calculation: Apply menu generation algorithm

[1449] Output: Menu data

[1450] Step 11:

[1451] The terminal displays the menu suggestions sent from the server to the user and makes suggestions for the next meal.

[1452] Input: Menu data

[1453] Output: Menu data is displayed on the terminal.

[1454] Step 12:

[1455] The server uses a user matching module to match users with similar body types and hobby preferences.

[1456] Input: User's body type data and hobby data

[1457] Data calculation: Apply matching algorithm

[1458] Output: Matching result data

[1459] Step 13:

[1460] The server plans and notifies training sessions and events for matched users.

[1461] Input: Matching result data

[1462] Output: Training session and event notification data

[1463] Step 14:

[1464] The terminal notifies the user of training sessions and events sent from the server.

[1465] Input: Training session and event notification data

[1466] Output: Training session and event notifications appear on your device

[1467] Step 15:

[1468] Users participate in virtual training sessions and events, and the server analyzes their emotional state during communication and provides appropriate interaction support.

[1469] Input: User emotion data

[1470] Data calculation: Applying emotional state analysis algorithms

[1471] Output: AC support data

[1472] 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.

[1473] 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.

[1474] 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.

[1475] [Third embodiment]

[1476] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1477] 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.

[1478] 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).

[1479] 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.

[1480] 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.

[1481] 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).

[1482] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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."

[1488] This invention is a system that develops optimal training menus for individual users, manages dietary habits, and supports community activities. This system consists of three main components: a server, a terminal, and users.

[1489] Training menu planning / guidance

[1490] server:

[1491] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[1492] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[1493] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[1494] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[1495] Device:

[1496] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[1497] User:

[1498] Image transmission: Send an image of the desired body shape from your device to the server.

[1499] Training implementation: Training is carried out according to instructions from the server.

[1500] Dietary management

[1501] server:

[1502] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[1503] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[1504] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history.

[1505] Device:

[1506] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[1507] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[1508] User:

[1509] Food photography: Take a photo of your food and send it to the server from your device.

[1510] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[1511] community

[1512] server:

[1513] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[1514] Event planning module: Plans and announces training sessions and events between matched users.

[1515] Device:

[1516] Community Participation Module: Users can view community information and participate in events.

[1517] Event notification module: Notifies the user of event information sent from the server.

[1518] User:

[1519] Community participation: Become interested in the events you are notified about and participate through the app.

[1520] Socialize: Attend events and connect with other users.

[1521] Specific examples

[1522] 1. Training menu planning / guidance:

[1523] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[1524] When the user starts training, the smartphone camera sends the video to the server in real time, and the form check module generates appropriate form correction instructions and gives them to the user.

[1525] 2. Dietary Management:

[1526] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[1527] Based on the user's likes and dislikes and past eating history, the server suggests a menu for the next meal and displays it on the device.

[1528] 3. Community:

[1529] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[1530] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[1531] The processing flow will be explained below.

[1532] Training menu planning / guidance

[1533] Step 1:

[1534] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[1535] Step 2:

[1536] The image reception and analysis module on the server receives the images and extracts body shape features using an image analysis model.

[1537] Step 3:

[1538] The server's menu generation module generates the optimal training menu for the user based on the results of image analysis.

[1539] Step 4:

[1540] The server transmits the generated training menu to the terminal and displays it to the user.

[1541] Step 5:

[1542] The user starts training and transmits images to the server in real time via the device's camera.

[1543] Step 6:

[1544] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the user's training form.

[1545] Step 7:

[1546] The server sends the generated correction instructions to the terminal and displays them to the user, who then corrects the training form according to the instructions.

[1547] Step 8:

[1548] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[1549] Dietary management

[1550] Step 1:

[1551] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[1552] Step 2:

[1553] The server's food image analysis module receives the image and uses image analysis models to recognize the food content, identifying the type and quantity of food.

[1554] Step 3:

[1555] The server's calorie calculation module calculates the calories of each food item based on the results of image analysis.

[1556] Step 4:

[1557] The server generates advice for the next meal based on the calorie calculation results, and creates menu suggestions that take into account the user's preferences and past meal history.

[1558] Step 5:

[1559] The server generates a menu suggestion, which is sent to the terminal and displayed to the user. The user then checks the menu and selects their next meal.

[1560] community

[1561] Step 1:

[1562] The server's user matching module analyzes the user's desired body type and hobbies and preferences, and performs matching based on this.

[1563] Step 2:

[1564] The server's event planning module plans training sessions and events based on the matching results.

[1565] Step 3:

[1566] The server generates event information planned by the user and sends it to the terminal, notifying the user of events that match their interests.

[1567] Step 4:

[1568] An event notification module of the terminal receives the event information sent from the server and notifies the user of the event information.

[1569] Step 5:

[1570] The user checks the notification content and registers to participate in events of interest.

[1571] Step 6:

[1572] On the day of the event, users will participate in training sessions and offline meetups at designated locations or online to deepen their interactions with other users.

[1573] Example 1

[1574] 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."

[1575] In today's busy lifestyles, it is difficult to develop optimal training programs for individual users, manage their diets, and support community activities. Conventional systems lack the advanced analytical capabilities to address individual needs or the ability to provide real-time feedback. This makes it difficult for users to self-manage and maintain motivation. The present invention aims to solve these challenges and support users in maintaining their health and building communities.

[1576] 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.

[1577] In this invention, the server includes means for receiving images of a desired body shape and analyzing the images using a machine learning model, means for generating an optimal training menu using a genetic algorithm based on the image analysis results, means for receiving video of a user performing a workout in real time and generating training form correction instructions using posture analysis technology, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents using image recognition technology, means for calculating calories by referencing a food composition database based on the image analysis results, means for generating an optimal menu taking into account the user's likes and dislikes using a recommendation algorithm, means for matching users with similar desired body shapes and hobbies and preferences using a clustering algorithm, and means for planning and notifying training sessions and events for matched users. This enables the provision of training menus tailored to individual user needs, appropriate dietary management, and support for community activities.

[1578] "Image analysis" is a technology that processes image data to understand and recognize its contents.

[1579] A "machine learning model" is a collection of algorithms that learn from large amounts of data and perform specific tasks automatically.

[1580] A "genetic algorithm" is a computational method for finding optimal solutions by imitating the evolutionary process of living organisms.

[1581] "Posture analysis technology" is a technology that analyzes a person's body movements and poses and identifies their posture.

[1582] The "Food Composition Database" is a database that systematically organizes and provides nutritional information on various foods.

[1583] A "recommendation algorithm" is an algorithm that analyzes user preferences and behavioral history to make optimal suggestions to individual users.

[1584] A "clustering algorithm" is a method for grouping data based on similarity.

[1585] "Real-time" refers to data processing and transmission occurring almost simultaneously with the real time axis.

[1586] A "training menu" is a collection of movements or exercises designed to achieve a specific goal or objective.

[1587] "Schedule information" is information including plans and timetables set by the user.

[1588] "Meal contents" refers to the types and amounts of ingredients and dishes consumed by the user.

[1589] "Calorie calculation" is a calculation to calculate the amount of energy contained in food.

[1590] "Matching" refers to linking multiple elements (e.g., users) based on specific conditions.

[1591] "Event notification" is the act of communicating information to interested parties about a particular occurrence or activity.

[1592] The present invention is a system that develops optimal training menus for individual users, manages their diet, and supports community activities. To implement this system, the following specific hardware and software are required.

[1593] Training menu planning / guidance

[1594] server:

[1595] Image reception and analysis module: The server receives an image of the user's desired body shape and performs image analysis using a machine learning model (e.g., TensorFlow). This analysis extracts body shape features (such as muscle distribution and fat distribution).

[1596] Menu generation module: The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[1597] Form check module: The server receives real-time video of the user training and uses posture analysis technology (e.g., OpenPose) to check whether the training is being performed with proper form, generating correction instructions as necessary.

[1598] Schedule management module: The server creates a training plan that utilizes the user's free time based on the user's schedule information.

[1599] Device:

[1600] Training module: The user uses the device's camera to transmit images of themselves training to the server, and receives real-time guidance on their form. The module also displays training menus and correction instructions sent from the server.

[1601] User:

[1602] Image transmission: The user sends an image of the desired body shape from their smartphone to the server. For example, they can take a photo of a fitness model and send it.

[1603] Training implementation: The user implements the training according to the instructions from the server.

[1604] Dietary management

[1605] server:

[1606] Food image analysis module: The server receives food images taken by the user and analyzes the food contents using image recognition technology (e.g., ResNet). This analysis identifies the foods contained in the meal and their amounts.

[1607] Calorie calculation module: The server calculates calories based on the image analysis results and references a food composition database (e.g., USDA food composition database).

[1608] Menu suggestion module: The server uses a recommendation algorithm (e.g., collaborative filtering) to generate an optimal menu, taking into account the user's likes and dislikes and dietary history.

[1609] Device:

[1610] Meal Recording Module: The user takes a photo of the meal and sends it to the server.

[1611] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[1612] User:

[1613] Food photography: A user takes a photo of their meal with their smartphone and sends it to the server from the device. For example, they take a photo of their lunch or dinner.

[1614] Menu confirmation: The user checks the menu suggestions from the server and selects the appropriate meal.

[1615] Community Activities

[1616] server:

[1617] User matching module: The server uses a clustering algorithm (e.g., K-Means) to match users with similar desired body types and hobbies and preferences.

[1618] Event planning module: The server plans training sessions and events for matched users and notifies them of the information.

[1619] Device:

[1620] Community participation module: Users can check community information and participate in events.

[1621] Event notification module: Notifies the user of event information sent from the server.

[1622] User:

[1623] Community participation: Users are interested in events they are notified about and participate through the app, for example, by attending a monthly training session.

[1624] Socialize: Users attend events, interact with other users, and train together.

[1625] Specific examples

[1626] 1. Training menu planning / guidance:

[1627] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server then analyzes the image using TensorFlow and generates an optimal training menu.

[1628] When the user starts training, the smartphone camera sends images to the server in real time, and the form check module using OpenPose generates appropriate form correction instructions and provides them to the user.

[1629] 2. Dietary Management:

[1630] A user takes a photo of their lunch salad and steak and sends it to the server, which analyzes the image using ResNet and calculates the calories of each food item from the USDA Food Composition Database.

[1631] The server uses collaborative filtering to suggest the next meal menu based on the user's likes and dislikes and past eating history, and displays it on the device.

[1632] 3. Community Activities:

[1633] The server uses clustering to match users with common goals and hobbies, and then plans and notifies them of monthly training sessions.

[1634] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[1635] Prompt Sentence Examples

[1636] "How can I send you an image of the body shape I'm aiming for?"

[1637] "I want to make sure my form is correct during my workouts. How can I do that?"

[1638] "I'd like you to calculate the calories in today's lunch. I took a photo and sent it to you."

[1639] "I would like to participate in events where I can interact with people who share the same hobbies."

[1640] The above is a specific embodiment of the present invention. This system makes it possible to provide training menus tailored to the needs of individual users, manage their diet appropriately, and support community activities.

[1641] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1642] Training menu planning / guidance

[1643] Step 1:

[1644] The user takes a picture of the body shape they are aiming for with their smartphone and sends it to the server using a dedicated app. The input is the image of the body shape acquired by the user, and the output is the result of sending the image data to the server.

[1645] Step 2:

[1646] The server receives the images and performs image analysis using a machine learning model (TensorFlow). The input is the received image data, and the output is data that extracts body shape features. This analysis allows for the acquisition of body shape features such as muscle distribution and fat distribution.

[1647] Step 3:

[1648] The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The input is the extracted body shape feature data, and the output is an optimized training menu. The menu includes the required exercises, their intensity, frequency, etc.

[1649] Step 4:

[1650] The user starts training and sends the training video to the server in real time using the smartphone camera. The input is the video data during training, and the output is the video transmission result to the server.

[1651] Step 5:

[1652] The server analyzes the video received in real time and uses posture analysis technology such as OpenPose to check whether the correct form is being maintained. The input is real-time video data, and the output is the evaluation result of the form appropriateness. Instructions for correcting the form are generated as needed.

[1653] Step 6:

[1654] The server generates form correction instructions, which are sent to the terminal and displayed to the user. The input is the form correction instruction data, and the output is the display result on the user's terminal. The user performs training according to these instructions.

[1655] Dietary management

[1656] Step 1:

[1657] The user takes a photo of their meal with their smartphone and sends it to the server using a dedicated app. The input is the image data of the meal, and the output is the result of sending the image data to the server.

[1658] Step 2:

[1659] The server receives the food images and performs image analysis using image recognition techniques such as ResNet. The input is the received image data, and the output is the identified foods and their quantities.

[1660] Step 3:

[1661] The server calculates calories based on the image analysis results by checking against the food composition database (USDA food composition database). The input is the identified food and its quantity data, and the output is the calculated calorie value.

[1662] Step 4:

[1663] The server uses a collaborative filtering algorithm to generate a menu for the next meal, taking into account the user's likes and dislikes and dietary history. The input is the user's dietary history and likes and dislikes, and the output is the generated menu.

[1664] Step 5:

[1665] The server sends the generated menu to the user's device and suggests the next meal. The input is the generated menu data, and the output is the display result on the user's device. The user selects an appropriate meal based on the suggestions.

[1666] Community Activities

[1667] Step 1:

[1668] The server analyzes the user's desired body type and hobbies and preferences, and matches similar users using a clustering algorithm (K-Means). The input is the user's goals and preference data, and the output is the matching results.

[1669] Step 2:

[1670] The server plans training sessions and events for matched users and notifies them of the information. The input is the matching result data, and the output is the planned event information data.

[1671] Step 3:

[1672] The server sends planned event information to users' terminals and encourages them to participate in the event. The input is event information data, and the output is the notification result sent to the user terminal.

[1673] Step 4:

[1674] The user checks the event information displayed on the terminal and registers to participate in the events they are interested in. The input is the event information data, and the output is the registration result.

[1675] Step 5:

[1676] On the day of the event, users participate in community activities with other users and deepen their interactions. The input is event participation information, and the output is interaction experience points and feedback.

[1677] (Application example 1)

[1678] 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."

[1679] Conventional training support systems have had the problem of making it difficult to create training menus tailored to each user's physical condition and goals, and of not being able to check or correct form in real time. Furthermore, when it comes to dietary management, calorie calculations and menu suggestions are time-consuming, and measures to address these issues are insufficient. Furthermore, there was a lack of mechanisms to encourage interaction between users with common goals or hobbies or to participate in events, making it difficult to maintain motivation.

[1680] 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.

[1681] In this invention, the server includes: means for receiving images of the desired body shape and analyzing the images; means for generating an optimal training menu based on the image analysis results; means for receiving video of the user's training in real time and generating training form correction instructions; means for formulating a training plan for spare time based on the user's schedule information; means for the user to take images of their meals and send them to the server, which then analyzes the images and calculates calories; and means for matching users with common goals and planning and notifying them of training events inside and outside the store. This enables the formulation of optimal training menus tailored to each user's individual goals, real-time form checks, and smooth calorie management and menu suggestions. Furthermore, it encourages interaction and event participation among users with common goals and hobbies, helping to maintain motivation.

[1682] 1. "Body shape image" is an image that visually shows the ideal body shape that the user is aiming for.

[1683] 2. "Image analysis" is the process of analyzing transmitted image data and extracting necessary information from its contents.

[1684] 3. "Training Menu" means a schedule of exercises and activities required for the user to achieve the desired body shape.

[1685] 4. "Video" refers to video data of a user performing training.

[1686] 5. "Form correction instructions" refers to real-time instruction provided to help users adopt the correct exercise posture.

[1687] 6. "Schedule information" is data that represents a user's daily activities and free time.

[1688] 7. "Spare time" refers to a period of time in a user's schedule when they can engage in an activity even for a short period of time.

[1689] 8. "Meal images" are photographs of food taken by the user.

[1690] 9. "Calorie counting" is the process of calculating the amount of energy intake based on the contents of a meal.

[1691] 10. "Menu suggestion" is a suggestion for the next meal that takes into account the user's preferences and nutritional balance.

[1692] 11. A "common goal" is a training or health-related objective shared by multiple users.

[1693] 12. "Matching" is the process of identifying and pairing or grouping users with common goals or interests.

[1694] 13. A "Training Event" is an opportunity for users with similar goals to come together and exercise together.

[1695] 14. "Notification" means a communication method used to inform users about training events or important information.

[1696] The system of the present invention is designed to provide users with personalized training menus, support dietary management, and promote community activities. The system consists of three main components: a server, a terminal, and users.

[1697] Training menu planning / guidance

[1698] server:

[1699] The server performs the following functions:

[1700] "Image Reception and Analysis Module": Receives images of the user's desired body shape and performs image analysis. This analysis uses software such as the image analysis library "OpenCV." The analysis results are used to extract the characteristics of the user's ideal body shape.

[1701] "Menu generation module": Generates an optimal training menu based on the image analysis results. This uses a generative AI model (e.g., GPT-4).

[1702] "Form Check Module": This module receives real-time video footage of the user training, checks whether the training is being performed with proper form, and generates correction instructions as necessary. This process uses the real-time video processing library "Kinesis Video Streams."

[1703] "Schedule Management Module": Based on the user's schedule information, it creates a training plan that utilizes their free time.

[1704] Device:

[1705] The device is equipped with the following features:

[1706] "Training module": The user uses the device's camera to send images to the server while training, and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[1707] User:

[1708] The user performs the following actions:

[1709] "Send image": Send an image of the desired body shape from your device to the server.

[1710] "Training": Training is carried out according to instructions from the server.

[1711] Dietary management

[1712] server:

[1713] The server supports the following features:

[1714] "Meal Image Analysis Module": Receives meal images taken by the user and performs image analysis. This analysis uses "Tesseract OCR" to identify the foods contained in the meal and their amounts.

[1715] "Calorie Calculation Module": Calculates the calorie content of food based on the results of image analysis. Uses a dedicated calorie calculation API.

[1716] "Menu suggestion module": Suggests the menu for the next meal, taking into account the user's likes and dislikes and eating history.

[1717] Device:

[1718] The device will be equipped with the following features:

[1719] "Meal Recording Module": The user takes a photo of what they have eaten and sends it to the server.

[1720] "Menu display module": Displays the menu sent from the server to the user and suggests the next meal.

[1721] User:

[1722] The user performs the following actions:

[1723] "Photo of food": Take a photo of your meal and send it from your device to the server.

[1724] "Confirm Menu": Check the menu suggestions from the server and select an appropriate meal.

[1725] community

[1726] server:

[1727] The server provides the following functions:

[1728] "User Matching Module": Matches users with common goals.

[1729] "Event Planning Module": Plans and announces training sessions and events between matched users. Data management uses "MySQL" and "Django."

[1730] Device:

[1731] The device will be equipped with the following features:

[1732] "Community Participation Module": Users check community information and participate in events.

[1733] "Event notification module": Notifies the user of event information sent from the server.

[1734] User:

[1735] The user performs the following actions:

[1736] "Community participation": Become interested in a notified event and participate through the app.

[1737] "Interact": Participate in events and deepen your interactions with other users.

[1738] Prompt Sentence Examples

[1739] 1. Training menu generation

[1740] "Upload an image of the body shape you want to achieve. After analyzing it, the system will suggest the optimal training menu."

[1741] 2. Real-time form checking

[1742] "Please record your training with a camera and send it to us. We will check your form in real time and provide appropriate guidance."

[1743] 3. Dietary Management

[1744] "Take a photo of the food you ate today and upload it. We'll analyze the calories and give you suggestions for your next meal."

[1745] 4. Community Support

[1746] "We will be organizing events for members with common goals. Please check the announcements if you would like to participate."

[1747] The above is a specific embodiment for carrying out the present invention, which makes it possible to provide training guidance and dietary management that is optimized for each individual user, and also to increase motivation through community activities.

[1748] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1749] Step 1:

[1750] The user takes a picture of the body shape they are aiming for using their smartphone and sends it from the device to the server.

[1751] Input: Body image

[1752] Data processing: Image data stored on the device is uploaded to the server via the device's application.

[1753] Output: The body image is sent to the server.

[1754] Step 2:

[1755] The server's image reception and analysis module analyzes the received body shape image.

[1756] Input: Body image

[1757] Data processing: Image features are extracted using the OpenCV library to identify ideal body shape properties.

[1758] Output: Body shape characteristic data is obtained as the analysis result.

[1759] Step 3:

[1760] The server's menu generation module generates an optimal training menu based on the image analysis results.

[1761] Input: Body shape feature data

[1762] Data processing: Using a generative AI model (e.g., GPT-4), a training menu is generated based on the user's goals and current physical condition.

[1763] Output: Customized training menu

[1764] Step 4:

[1765] The user begins training, takes a video of themselves using their smartphone camera, and sends it to the server in real time from the device.

[1766] Input: Video of training

[1767] Data processing: Real-time video data is acquired using the device's camera function.

[1768] Output: Live video is sent to the server.

[1769] Step 5:

[1770] The server's form check module analyzes the real-time video and generates instructions for correcting training form.

[1771] Input: Live footage of training

[1772] Data Processing: Using Kinesis Video Streams and OpenCV, we analyze the user's posture and determine the proper form.

[1773] Output: Form correction instructions

[1774] Step 6:

[1775] The server's instructions are sent to the terminal and displayed on the user's terminal.

[1776] Input: Form correction instructions

[1777] Data processing: Transfer instruction data to the terminal.

[1778] Output: Form correction instructions are displayed on the terminal.

[1779] Step 7:

[1780] The user takes a photo of the meal and sends it to the server from the device.

[1781] Input: Food image

[1782] Data processing: Photo data stored on the device is uploaded to the server via the app.

[1783] Output: The food image is sent to the server.

[1784] Step 8:

[1785] The server's food image analysis module analyzes the received food image and calculates calories.

[1786] Input: Food image

[1787] Data processing: Identify food items in the image using Tesseract OCR and calculate calories using a dedicated API.

[1788] Output: Calorie data of meals

[1789] Step 9:

[1790] The server's menu suggestion module considers calorie data and the user's preferences to suggest a menu for the next meal.

[1791] Input: Calorie data, user preference data

[1792] Data processing: Generates an optimal menu list based on past meal history and preference data.

[1793] Output: Suggested menu

[1794] Step 10:

[1795] The server matches users with common goals and organizes and announces training events.

[1796] Input: User goal data

[1797] Data Processing: Using Django framework and MySQL database to match user information and plan training events.

[1798] Output: Event notification data

[1799] Step 11:

[1800] The server sends the event notification data to the terminal, which displays the notification to the user.

[1801] Input: Event notification data

[1802] Data processing: Send notification data to the device.

[1803] Output: An event notification is displayed on the user's terminal.

[1804] The above is a specific processing flow of the system of the present invention, which provides optimized support to individual users.

[1805] 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.

[1806] This system creates optimal training menus for individual users, manages their diet, and supports community activities. It also incorporates an emotion engine that recognizes the user's emotional state, enabling these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and users.

[1807] Training menu planning / guidance

[1808] server:

[1809] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[1810] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[1811] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[1812] Emotion engine: Analyzes the user's facial expressions and voice to recognize their emotional state, and uses that information to appropriately adjust the content of training guidance and support.

[1813] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[1814] Device:

[1815] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The server also displays training menus, correction instructions, and emotional support messages.

[1816] User:

[1817] Image transmission: Send an image of the desired body shape from your device to the server.

[1818] Training: Train according to instructions and encouraging messages from the server.

[1819] Dietary management

[1820] server:

[1821] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[1822] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[1823] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history. In addition, an emotion engine analyzes the user's emotional state during meal recording and, based on the results, suggests menus that are adapted to the user's psychological state.

[1824] Device:

[1825] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[1826] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[1827] User:

[1828] Food photography: Take a photo of your food and send it to the server from your device.

[1829] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[1830] community

[1831] server:

[1832] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[1833] Event planning module: Plans and announces training sessions and events between matched users.

[1834] Emotion Engine: Recognizes the emotions of each user during communication between users and appropriately supports interactions within the community based on the results.

[1835] Device:

[1836] Community Participation Module: Users can view community information and participate in events.

[1837] Event notification module: Notifies the user of event information sent from the server.

[1838] User:

[1839] Community participation: Become interested in the events you are notified about and participate through the app.

[1840] Socialize: Attend events and connect with other users.

[1841] Specific examples

[1842] 1. Training menu planning / guidance:

[1843] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[1844] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[1845] 2. Dietary Management:

[1846] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[1847] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[1848] 3. Community:

[1849] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[1850] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[1851] The processing flow will be explained below.

[1852] Training menu planning / guidance

[1853] Step 1:

[1854] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[1855] Step 2:

[1856] The server's image reception and analysis module analyzes the received images and extracts body shape characteristics from the analysis results.

[1857] Step 3:

[1858] The menu generation module of the server generates an optimal training menu based on the image analysis results.

[1859] Step 4:

[1860] The server transmits the generated training menu to the terminal, and the user confirms the displayed menu.

[1861] Step 5:

[1862] The user starts training and sends real-time video to the server via the device's camera.

[1863] Step 6:

[1864] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the training form. The emotion engine also recognizes the user's emotions from the video and audio.

[1865] Step 7:

[1866] The server generates correction instructions and sends cheering messages based on the user's emotional state to the terminal, which the user confirms. The user then continues to correct their training form accordingly.

[1867] Step 8:

[1868] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[1869] Dietary management

[1870] Step 1:

[1871] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[1872] Step 2:

[1873] The server's food image analysis module receives the image and performs image analysis to identify the type and amount of food.

[1874] Step 3:

[1875] The server's calorie calculation module calculates the calories of each food item based on the image analysis results.

[1876] Step 4:

[1877] The server takes into account the calorie calculation results, the user's preferences, and past meal history, and then uses an emotion engine to analyze the user's emotional state when recording their meals, and based on the results, generates a menu that is adapted to the user's psychological state.

[1878] Step 5:

[1879] The server sends the generated menu suggestions to the terminal, and the user checks the displayed menu. The user selects an appropriate meal and then follows the instructions.

[1880] community

[1881] Step 1:

[1882] The server's user matching module analyzes users' desired body type, hobbies, thoughts, and emotional state, and matches users with many commonalities.

[1883] Step 2:

[1884] The server's event planning module plans training sessions and events for matched users. The emotion engine determines the user's emotional state and notifies them of events at the optimal time.

[1885] Step 3:

[1886] The server sends the generated event information to the terminal and notifies the user, who then checks the notification content.

[1887] Step 4:

[1888] A user applies to participate in an event that they are interested in. The device sends the participation request to the server.

[1889] Step 5:

[1890] On the day of the event, users participate in the event at a designated location or online. The server's emotion engine monitors the user's emotional state during the event in real time and generates feedback to support interaction.

[1891] Step 6:

[1892] The server generates feedback and sends it to the terminal, where the user receives it. This deepens interaction with other users and increases motivation for training.

[1893] Example 2

[1894] 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."

[1895] Conventional training and diet management systems struggle to provide optimal guidance and support tailored to individual users' goals and emotional states. Furthermore, they lack emotional support for communication and collaborative training, making it difficult to maintain motivation. This results in a lack of continuous health management and community building for users.

[1896] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving images of a desired body shape and performing image analysis, means for generating an optimal training menu based on the image analysis results, means for receiving video of a user performing training in real time and generating instructions for correcting the user's training form, means for analyzing the user's emotional state in real time and generating an emotional support message, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents, means for calculating calories based on the image analysis results, means for analyzing the user's emotional state and generating an optimal menu based on the analyzed results, means for matching users with similar desired body shapes and hobbies, means for planning and notifying training sessions and events for matched users, and means for recognizing emotions during communication between users and providing emotional support for interaction. This makes it possible to provide optimal training and dietary management for each user, and further realize support for community activities and emotional motivation maintenance.

[1897] "Image reception and analysis module" refers to the device or software that receives images of the desired body shape and performs image analysis.

[1898] A "menu generation module" refers to a device or software that generates an optimal training menu based on the results of image analysis, taking into account the user's goals and current physical condition.

[1899] A "form check module" refers to a device or software that receives video of a user performing training in real time and generates instructions for correcting the training form.

[1900] An "emotion engine" refers to a device or software that analyzes a user's facial expressions and voice in real time, recognizes their emotional state, and generates cheering messages and other information based on that information.

[1901] A "schedule management module" refers to a device or software that creates a training plan for spare time based on the user's schedule information.

[1902] A "meal image analysis module" refers to a device or software that receives images of meals taken by users and performs image analysis of the meal contents.

[1903] A "calorie calculation module" refers to a device or software that calculates the calories of a meal based on the results of image analysis.

[1904] A "menu suggestion module" refers to a device or software that generates an optimal menu taking into account the user's emotional state and eating history.

[1905] A "user matching module" refers to a device or software that matches users with similar body types and hobbies.

[1906] An "event planning module" refers to a device or software that plans and notifies training sessions and events between matched users.

[1907] "Community participation module" refers to a device or software that provides a function for users to check community information and participate in events.

[1908] An "event notification module" refers to a device or software that notifies a user of event information sent from a server.

[1909] "Training implementation module" refers to a device or software that provides a function that allows a user to use the device's camera to send images to a server while training and receive form guidance in real time.

[1910] A "meal record module" refers to a device or software that provides the function of allowing a user to take a photo of what they have eaten and send it to a server.

[1911] A "menu display module" refers to a device or software that displays the menu sent from the server to the user and suggests the next meal.

[1912] The present invention is a system for efficiently managing the health of each user. This system consists of three main elements: a server, a terminal, and a user, and realizes the invention through the following configuration and operation.

[1913] server

[1914] The server uses multiple dedicated modules to support users in training, dietary management, and community activities.

[1915] 1. Image reception and analysis module

[1916] The server receives images of the user's desired body shape and performs image analysis. Specifically, it uses image analysis software (e.g., OpenCV) to extract body shape characteristics. Based on this information, it creates a training menu, which will be described later.

[1917] 2. Menu Generation Module

[1918] Based on the results of image analysis, the server generates an optimal training menu that takes into account the user's goals and current physical condition. For example, it creates a program that combines strength training three times a week and aerobic exercise twice a week and provides it to each individual user.

[1919] 3. Form Check Module

[1920] The server receives real-time video footage sent from the user's device while they are training. Using video analysis technology, it checks the user's form and generates necessary correction instructions. For example, if the user's posture is poor, it sends a message saying, "Straighten your back."

[1921] 4. Emotion Engine

[1922] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state. Using technologies such as Google Cloud Vision API and Microsoft Azure Emotion API, the server then uses this information to appropriately tailor training instructions and support messages.

[1923] 5. Schedule Management Module

[1924] The server creates a training plan that utilizes the user's free time based on the user's schedule information, making it possible to provide a training plan that the user can continue without straining themselves.

[1925] 6. Food Image Analysis Module

[1926] The server receives the image of the meal taken by the user and performs image analysis using OpenCV etc. to identify the ingredients and their amounts, and calculates the calories based on this information.

[1927] 7. Calorie Counting Module

[1928] The server calculates the calories of the meal based on the image analysis results, allowing the user to accurately grasp the calorie intake of their food.

[1929] 8. Menu suggestion module

[1930] The server analyzes the user's eating history and emotional state to suggest optimal meals. For example, it generates a meal plan using ingredients that have a relaxing effect for a stressed user.

[1931] 9. User Matching Module

[1932] The server matches users with similar body types, hobbies, and ways of thinking. This module allows users to find others who share the same goals and work together to achieve their goals.

[1933] 10. Event Planning Module

[1934] The server plans and notifies training sessions and events between matched users, thereby promoting interaction between users.

[1935] 11. Communication Support

[1936] The server recognizes emotions during communication between users and supports interactions based on those emotions. For example, it provides appropriate interaction support through emotion analysis during an event.

[1937] Terminal

[1938] A terminal refers to a device or software that communicates with a server through user operation and provides various information.

[1939] 1. Training Implementation Module

[1940] When a user starts training, the device's camera activates and transmits the video in real time to the server, which then displays the training menu, form instructions, and encouraging messages.

[1941] 2. Food Record Module

[1942] It provides a function that allows users to take a photo of what they have eaten and send it to the server.

[1943] 3. Community Participation Module

[1944] It provides users with the ability to check community information and participate in events.

[1945] User

[1946] Users can use this system to manage their own health. Specific operations include sending images of their desired body shape, doing training, taking photos of meals, and participating in the community.

[1947] Specific examples

[1948] 1. Training menu planning / guidance:

[1949] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[1950] When a user starts training, the smartphone camera sends the video to the server in real time, and the form check module and emotion engine generate appropriate instructions for correcting form and emotionally-based cheering messages to instruct the user.

[1951] 2. Dietary Management:

[1952] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[1953] The system analyzes the user's emotional state using an emotion engine and suggests menus that suit that psychological state. For example, if a user is feeling stressed, it suggests a menu using ingredients that have a relaxing effect.

[1954] 3. Community:

[1955] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[1956] Users receive notifications, become interested, and participate in events. They interact with other users at the event, and the emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[1957] Example prompt for a generative AI model:

[1958] Develop a system that generates an optimal training menu based on images of the user's desired physique, checks their form in real time, and provides cheering messages based on their emotional state. The system receives images from the user, analyzes them to create a specific training menu, analyzes footage of the training session to generate instructions for correcting their form, and uses an emotion engine to provide appropriate cheering messages.

[1959] The above is the "Mode for Carrying Out the Invention."

[1960] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1961] Training menu planning / guidance

[1962] server

[1963] Step 1:

[1964] The server receives an image of a desired body type from the user.

[1965] Specific behavior:

[1966] The user takes a photo of the fitness model with their smartphone and sends it to the server via the app.

[1967] Input: An image of the body type the user is aiming for.

[1968] Output: Receiving image data.

[1969] Step 2:

[1970] The server analyzes the received images using image analysis software (e.g., OpenCV) and extracts body shape features.

[1971] Specific behavior:

[1972] The server reads the received images using OpenCV and analyzes specific features (muscle shape and fat distribution).

[1973] Input: Image data.

[1974] Output: Analyzed body feature data.

[1975] Step 3:

[1976] The server generates an optimal training menu based on the results of the image analysis.

[1977] Specific behavior:

[1978] Based on the analysis results, the server creates a menu that combines three sessions of strength training and two sessions of aerobic exercise per week.

[1979] Input: Body shape feature data.

[1980] Output: Training menu.

[1981] Terminal

[1982] Step 1:

[1983] When a user starts training, the device's camera is used to send images to the server in real time.

[1984] Specific behavior:

[1985] When the user launches the app and presses the "Start Training" button, the camera activates and the video is sent to the server.

[1986] Input: User training start signal.

[1987] Output: Real-time video data transmission.

[1988] server

[1989] Step 4:

[1990] The server analyzes the received video and checks the user's training form.

[1991] Specific behavior:

[1992] The server uses video analysis technology to analyze the user's actions in real time and evaluate whether they are correct.

[1993] Input: Real-time video data.

[1994] Output: Form check results.

[1995] Step 5:

[1996] The server generates correction instructions if the user's form is incorrect.

[1997] Specific behavior:

[1998] When the server detects improper form, it generates correction instructions such as "Stand up a little straighter."

[1999] Input: Form check result.

[2000] Output: Form correction instructions.

[2001] Step 6:

[2002] The server analyzes the user's facial expressions and voice in real time to recognize their emotional state.

[2003] Specific behavior:

[2004] The server performs emotion analysis using the Google Cloud Vision API and Microsoft Azure Emotion API.

[2005] Input: Real-time video and audio data.

[2006] Output: Emotional state data.

[2007] Step 7:

[2008] The server appropriately adjusts the cheering message based on the emotional state.

[2009] Specific behavior:

[2010] The server sends a message of encouragement saying "Keep it up!" to a user who is feeling unmotivated.

[2011] Input: Emotional state data.

[2012] Output: A message of encouragement.

[2013] Dietary management

[2014] User

[2015] Step 1:

[2016] The user takes a photo of the meal with their smartphone and sends it to the server.

[2017] Specific behavior:

[2018] The user takes a photo of their lunch salad and steak using the app and hits send.

[2019] Input: food photos.

[2020] Output: Sending food image data.

[2021] server

[2022] Step 2:

[2023] The server analyzes the received meal images using image analysis software (e.g., OpenCV) to identify the ingredients and their quantities.

[2024] Specific behavior:

[2025] The server analyzes the food image and identifies the type of vegetables in the salad and the gram weight of the steak.

[2026] Input: Food image data.

[2027] Output: Parsed ingredient data.

[2028] Step 3:

[2029] The server calculates the calories of the meal based on the analysis results.

[2030] Specific behavior:

[2031] The server calculates the calories based on the amount of ingredients specified and displays 500 kcal.

[2032] Input: Parsed ingredient data.

[2033] Output: Calorie calculation results.

[2034] Step 4:

[2035] The server analyzes the user's emotional state in real time and suggests a menu that suits their psychological state.

[2036] Specific behavior:

[2037] The server suggests a relaxing dinner to users who are feeling stressed.

[2038] Input: Emotional state data.

[2039] Output: Menu suggestions.

[2040] community

[2041] server

[2042] Step 1:

[2043] The server matches users with similar body types, hobbies, and ways of thinking.

[2044] Specific behavior:

[2045] The server compares the registered user information and notifies the user that "we have found users with similar goals to you."

[2046] Input: User profile data.

[2047] Output: Matching results.

[2048] Step 2:

[2049] The server plans and notifies training sessions and events between matched users.

[2050] Specific behavior:

[2051] The server announces, "The next training event is next Saturday."

[2052] Input: Matching results.

[2053] Output: Event notification.

[2054] Step 3:

[2055] The server recognizes emotions during communication between users and provides emotion-based interaction support.

[2056] Specific behavior:

[2057] The server analyzes the emotional state and generates messages during the event such as "You're having fun! Let's talk more!"

[2058] Input: Real-time emotion data.

[2059] Output: AC support message.

[2060] User

[2061] Step 1:

[2062] The user becomes interested in the event and participates through the app.

[2063] Specific behavior:

[2064] The user opens the app and presses the event participation button.

[2065] Input: User's willingness to attend the event.

[2066] Output: Event registration.

[2067] Step 2:

[2068] Users can participate in events and interact with other users.

[2069] Specific behavior:

[2070] Users can talk with other participants at the event venue and exchange messages using social networking features.

[2071] Input: User interactions.

[2072] Output: Promoting interaction.

[2073] The above are the specific processing steps of the program of this system.

[2074] (Application example 2)

[2075] 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."

[2076] Conventional training menu planning and diet management systems face challenges in that they are unable to adequately respond to users' emotional states and individual schedules. Furthermore, real-time training guidance and diet management are difficult, making it difficult for users to maintain a consistent fitness plan. Furthermore, in community activities, there is a lack of mechanisms to effectively support interactions between users. To solve these challenges, it is necessary to recognize users' emotional states and provide individually optimized guidance and management.

[2077] 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.

[2078] In this invention, the server includes means for receiving images of the target body shape and analyzing the images, means for generating an optimal training menu based on the image analysis results, means for receiving video of the user's training in real time and generating training form correction instructions, means for formulating a training plan for spare time based on the user's schedule information, means for providing training in a virtual reality environment or an augmented reality environment, means for providing form guidance using a real-time haptic device, and means for analyzing the user's emotional state and adjusting the training instruction content and support messages based on the user's emotions. This enables the provision of a consistent fitness plan tailored to each user's emotional state and real-time, effective training guidance. It also appropriately supports communication between users, revitalizing the fitness community.

[2079] The "image of the desired body type" is image data showing the ideal body type that the user desires.

[2080] "Image analysis" is the process of extracting and analyzing features from received image data.

[2081] A "training menu" is a series of exercise programs designed to help a user achieve their goals.

[2082] "Real-time video" refers to current video data while the user is working out.

[2083] "Instructions for correcting training form" refers to providing guidance and suggestions for correction to maintain proper exercise form.

[2084] "Schedule information" is data relating to the user's plans and timetable.

[2085] A "spare time training plan" is a training plan that utilizes the user's free time.

[2086] A "virtual reality environment" is a virtual training environment that a user experiences through a VR device.

[2087] An "augmented reality environment" is a training environment that uses AR technology to overlay digital information onto the real environment.

[2088] A "haptic device" is a device that provides tactile feedback, allowing users to physically feel the feedback during training.

[2089] "Emotional state" refers to the user's emotional and psychological state, and is used to provide appropriate guidance and support by analyzing it.

[2090] "Image analysis of food content" is the process of analyzing photos of meals taken by users to identify the foods and amounts included.

[2091] "Calorie calculation" refers to calculating the total calorie content of a meal based on the results of image analysis.

[2092] A "menu" is a meal plan suggested based on the user's nutritional balance and preferences.

[2093] "User likes and dislikes" is information about foods that a user likes and dislikes.

[2094] "Matching" is the process of connecting users who share common goals or interests.

[2095] "Training sessions and events" are activities or sessions where users come together to share common experiences.

[2096] "Communication support" means helping users to interact with each other in an enjoyable and effective way.

[2097] This invention is a system that supports users in formulating optimal training menus, managing their diet, and participating in community activities, and it combines an emotion engine that recognizes the user's emotional state to enable these activities to be carried out more effectively. This system consists of three main components: a server, a terminal, and a user.

[2098] Training menu planning / guidance

[2099] 1. Server:

[2100] The server receives images of the desired body shape and performs image analysis. This analysis uses TensorFlow and PIL. As a result of the image analysis, the user's body characteristics are extracted, and an optimal training menu is generated based on this information. This information is materialized by the "menu generation module." Furthermore, real-time video of the user training is received, and instructions for correcting training form are generated using the form check module. The emotion engine analyzes the user's facial expressions and voice to recognize their emotional state. Based on this information, training instructions and encouraging messages are appropriately adjusted. The user's schedule information is also stored on the server, and a training plan that makes effective use of spare time is formulated by the "schedule management module."

[2101] 2. Terminal:

[2102] Users can experience a virtual training environment using smart glasses or a head-mounted display. During training, the user's movements are transmitted in real time to a server via the smart glasses' camera, and form guidance and correction instructions are displayed. A haptic device provides physical guidance on form during training. In addition, cheering messages and instructional content are customized based on an emotion engine and provided to the user.

[2103] Dietary management

[2104] 1. Server:

[2105] The server receives images of meals taken by the user and performs image analysis. This analysis uses a meal image analysis module and a machine learning model to identify foods and their portions. Based on the analysis results, calorie calculations are performed and the results are derived by the calorie calculation module. Furthermore, the server generates an optimal menu taking into account the user's likes and dislikes, dietary history, and emotional state. This information is provided to the user by the "menu suggestion module."

[2106] 2. Terminal:

[2107] The user uses the smart glasses to take photos of their meals and send them to the server. The meal record module records the user's meal contents, and the menu display module displays appropriate menu suggestions to the user.

[2108] community

[2109] 1. Server:

[2110] The user matching module matches users with similar body types and hobbies. The event planning module plans and notifies users of training sessions and events for matched users. The emotion engine recognizes the emotional state of users when they communicate with each other and appropriately supports their interactions.

[2111] 2. Terminal:

[2112] Users can receive event notifications and participate in virtual training sessions, interact with other users in virtual or augmented reality environments, and be supported by an emotion engine.

[2113] Specific examples

[2114] 1. Training menu planning:

[2115] The user takes a photo of the fitness model with the smart glasses and sends it to the server. The server analyzes the image and generates a training menu. The user then begins training, and the video is sent in real time via the smart glasses' camera. The form check module analyzes the user's form, and appropriate guidance is provided via the haptic device.

[2116] 2. Dietary Management:

[2117] A user takes a photo of their lunch salad and steak using smart glasses and sends it to the server. Image analysis is performed to calculate the calories of each food item. The user's emotional state is also analyzed, and a menu appropriate to their psychological state is suggested. For example, if a user is feeling stressed, a menu using ingredients with a relaxing effect will be suggested.

[2118] 3. Community:

[2119] The server matches users with common goals and hobbies, plans monthly training sessions, and notifies them. Users receive the notifications, participate in events they are interested in, and interact with other users. The emotion engine analyzes the user's emotional state and provides appropriate interaction support.

[2120] Prompt Sentence Examples

[2121] "Analyze images of your fitness goals and generate the optimal training menu."

[2122] "Analyzes user video feeds, recognizes real-time emotional states, and generates supportive messages"

[2123] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2124] Step 1:

[2125] The user uses smart glasses or a head-mounted display to take an image of the desired body shape and sends the image to the server via the terminal.

[2126] Input: Image data of the desired body shape

[2127] Output: The image is sent to the server

[2128] Step 2:

[2129] The server inputs the received image data into the image analysis module and performs image analysis using TensorFlow and PIL. This analysis extracts the features of the user's target body shape.

[2130] Input: Image data of the desired body shape

[2131] Data processing: Resize and normalize the image to 128x128 pixels.

[2132] Data computation: Feature extraction with TensorFlow model

[2133] Output: Feature data of target body shape

[2134] Step 3:

[2135] The server generates an optimal training menu using a menu generation module based on the results of the image analysis.

[2136] Input: Feature data of target body shape

[2137] Data calculation: Applying an algorithm to generate training menus based on feature values

[2138] Output: Training menu data

[2139] Step 4:

[2140] When the user starts training, the server receives the user's video in real time from the terminal and generates appropriate form correction instructions using a form check module.

[2141] Input: Real-time video data of the user

[2142] Data processing: Processing video data in real time and analyzing training form

[2143] Data calculations: Applying algorithms to evaluate the suitability of a form

[2144] Output: Form correction instruction data

[2145] Step 5:

[2146] The server uses an emotion engine to analyze the user's facial expressions and voice in real time to recognize their emotional state, and then adjusts the training instructions and cheering messages accordingly.

[2147] Input: User's facial expression data and voice data

[2148] Data processing: Input facial expression data and voice data into the emotion analysis model

[2149] Data Computing: Recognizing Emotional States with Sentiment Analysis Models

[2150] Output: Emotional state data and cheering message

[2151] Step 6:

[2152] The terminal displays to the user training menus, form correction instructions, and emotional support messages sent from the server.

[2153] Input: Training menu, form correction instructions, support messages

[2154] Output: Training menu, form correction instructions, and cheering messages are displayed on the device.

[2155] Step 7:

[2156] The user takes an image of their meal through the smart glasses and sends the image to the server.

[2157] Input: Food image data

[2158] Output: The image is sent to the server

[2159] Step 8:

[2160] The server uses a meal image analysis module to analyze the received meal images to identify foods and their portions.

[2161] Input: Food image data

[2162] Data processing: Inputting images into the analysis model

[2163] Data Computation: Food Identification and Quantity Calculation Using Image Analysis Models

[2164] Output: Food data and quantity data

[2165] Step 9:

[2166] The server uses a calorie calculation module to calculate calories based on the identified food data and amount data.

[2167] Input: Food data and quantity data

[2168] Data calculation: Apply calorie calculation algorithm

[2169] Output: Calorie data

[2170] Step 10:

[2171] The server takes into account the user's likes and dislikes, eating history, and emotional state and uses a menu suggestion module to generate an optimal menu.

[2172] Input: User likes and dislikes, food history, and emotional state data

[2173] Data calculation: Apply menu generation algorithm

[2174] Output: Menu data

[2175] Step 11:

[2176] The terminal displays the menu suggestions sent from the server to the user and makes suggestions for the next meal.

[2177] Input: Menu data

[2178] Output: Menu data is displayed on the terminal.

[2179] Step 12:

[2180] The server uses a user matching module to match users with similar body types and hobby preferences.

[2181] Input: User's body type data and hobby data

[2182] Data calculation: Apply matching algorithm

[2183] Output: Matching result data

[2184] Step 13:

[2185] The server plans and notifies training sessions and events for matched users.

[2186] Input: Matching result data

[2187] Output: Training session and event notification data

[2188] Step 14:

[2189] The terminal notifies the user of training sessions and events sent from the server.

[2190] Input: Training session and event notification data

[2191] Output: Training session and event notifications appear on your device

[2192] Step 15:

[2193] Users participate in virtual training sessions and events, and the server analyzes their emotional state during communication and provides appropriate interaction support.

[2194] Input: User emotion data

[2195] Data calculation: Applying emotional state analysis algorithms

[2196] Output: AC support data

[2197] 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.

[2198] 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.

[2199] 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.

[2200] [Fourth embodiment]

[2201] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2202] 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.

[2203] 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).

[2204] 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.

[2205] 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.

[2206] 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).

[2207] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2208] 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.

[2209] 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.

[2210] 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.

[2211] 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.

[2212] 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.

[2213] 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."

[2214] This invention is a system that develops optimal training menus for individual users, manages dietary habits, and supports community activities. This system consists of three main components: a server, a terminal, and users.

[2215] Training menu planning / guidance

[2216] server:

[2217] Image reception and analysis module: Receives images of the user's desired body shape and performs image analysis. This analysis extracts body shape characteristics and uses this information to create a training menu.

[2218] Menu generation module: Generates an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[2219] Form check module: Receives video of the user training in real time, checks whether the training is being performed with proper form, and generates correction instructions as necessary.

[2220] Schedule management module: Based on the user's schedule information, it creates a training plan that utilizes their free time.

[2221] Device:

[2222] Training module: During training, the user uses the device's camera to send images to the server and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[2223] User:

[2224] Image transmission: Send an image of the desired body shape from your device to the server.

[2225] Training implementation: Training is carried out according to instructions from the server.

[2226] Dietary management

[2227] server:

[2228] Food image analysis module: Receives food images taken by the user and performs image analysis. This analysis identifies the foods and their amounts contained in the meal and uses this information to calculate calories.

[2229] Calorie calculation module: Calculates the calories of food based on the results of image analysis.

[2230] Menu suggestion module: Generates optimal menus taking into account the user's likes and dislikes and dietary history.

[2231] Device:

[2232] Food record module: The user takes a photo of what they have eaten and sends it to the server.

[2233] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[2234] User:

[2235] Food photography: Take a photo of your food and send it to the server from your device.

[2236] Menu confirmation: Check the menu suggestions from the server and choose the appropriate meal.

[2237] community

[2238] server:

[2239] User Matching Module: Matches users with similar body types and interests, allowing them to work together toward a common goal.

[2240] Event planning module: Plans and announces training sessions and events between matched users.

[2241] Device:

[2242] Community Participation Module: Users can view community information and participate in events.

[2243] Event notification module: Notifies the user of event information sent from the server.

[2244] User:

[2245] Community participation: Become interested in the events you are notified about and participate through the app.

[2246] Socialize: Attend events and connect with other users.

[2247] Specific examples

[2248] 1. Training menu planning / guidance:

[2249] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server analyzes the image and generates an optimal training menu.

[2250] When the user starts training, the smartphone camera sends the video to the server in real time, and the form check module generates appropriate form correction instructions and gives them to the user.

[2251] 2. Dietary Management:

[2252] A user takes a photo of their lunch salad and steak and sends it to a server, which analyzes the image and calculates the calories of each food item.

[2253] Based on the user's likes and dislikes and past eating history, the server suggests a menu for the next meal and displays it on the device.

[2254] 3. Community:

[2255] The server matches users with common goals and interests, and schedules and announces monthly training sessions.

[2256] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[2257] The processing flow will be explained below.

[2258] Training menu planning / guidance

[2259] Step 1:

[2260] The user takes a picture of the body shape they are aiming for on their device and sends it to the server via the app. The device receives the image and uploads it to the server.

[2261] Step 2:

[2262] The image reception and analysis module on the server receives the images and extracts body shape features using an image analysis model.

[2263] Step 3:

[2264] The server's menu generation module generates the optimal training menu for the user based on the results of image analysis.

[2265] Step 4:

[2266] The server transmits the generated training menu to the terminal and displays it to the user.

[2267] Step 5:

[2268] The user starts training and transmits images to the server in real time via the device's camera.

[2269] Step 6:

[2270] The server's form check module receives and analyzes real-time video and generates correction instructions if there are any errors in the user's training form.

[2271] Step 7:

[2272] The server sends the generated correction instructions to the terminal and displays them to the user, who then corrects the training form according to the instructions.

[2273] Step 8:

[2274] The server's schedule management module creates a training plan that utilizes the user's free time based on the user's schedule information and sends it to the terminal. The user then carries out the training according to the displayed plan.

[2275] Dietary management

[2276] Step 1:

[2277] The user takes a photo of their meal and sends it from their device to the server, which then uploads the photo of the meal to the server.

[2278] Step 2:

[2279] The server's food image analysis module receives the image and uses image analysis models to recognize the food content, identifying the type and quantity of food.

[2280] Step 3:

[2281] The server's calorie calculation module calculates the calories of each food item based on the results of image analysis.

[2282] Step 4:

[2283] The server generates advice for the next meal based on the calorie calculation results, and creates menu suggestions that take into account the user's preferences and past meal history.

[2284] Step 5:

[2285] The server generates a menu suggestion, which is sent to the terminal and displayed to the user. The user then checks the menu and selects their next meal.

[2286] community

[2287] Step 1:

[2288] The server's user matching module analyzes the user's desired body type and hobbies and preferences, and performs matching based on this.

[2289] Step 2:

[2290] The server's event planning module plans training sessions and events based on the matching results.

[2291] Step 3:

[2292] The server generates event information planned by the user and sends it to the terminal, notifying the user of events that match their interests.

[2293] Step 4:

[2294] An event notification module of the terminal receives the event information sent from the server and notifies the user of the event information.

[2295] Step 5:

[2296] The user checks the notification content and registers to participate in events of interest.

[2297] Step 6:

[2298] On the day of the event, users will participate in training sessions and offline meetups at designated locations or online to deepen their interactions with other users.

[2299] Example 1

[2300] 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."

[2301] In today's busy lifestyles, it is difficult to develop optimal training programs for individual users, manage their diets, and support community activities. Conventional systems lack the advanced analytical capabilities to address individual needs or the ability to provide real-time feedback. This makes it difficult for users to self-manage and maintain motivation. The present invention aims to solve these challenges and support users in maintaining their health and building communities.

[2302] 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.

[2303] In this invention, the server includes means for receiving images of a desired body shape and analyzing the images using a machine learning model, means for generating an optimal training menu using a genetic algorithm based on the image analysis results, means for receiving video of a user performing a workout in real time and generating training form correction instructions using posture analysis technology, means for formulating a training plan for spare time based on the user's schedule information, means for receiving images of meals taken by the user and analyzing the meal contents using image recognition technology, means for calculating calories by referencing a food composition database based on the image analysis results, means for generating an optimal menu taking into account the user's likes and dislikes using a recommendation algorithm, means for matching users with similar desired body shapes and hobbies and preferences using a clustering algorithm, and means for planning and notifying training sessions and events for matched users. This enables the provision of training menus tailored to individual user needs, appropriate dietary management, and support for community activities.

[2304] "Image analysis" is a technology that processes image data to understand and recognize its contents.

[2305] A "machine learning model" is a collection of algorithms that learn from large amounts of data and perform specific tasks automatically.

[2306] A "genetic algorithm" is a computational method for finding optimal solutions by imitating the evolutionary process of living organisms.

[2307] "Posture analysis technology" is a technology that analyzes a person's body movements and poses and identifies their posture.

[2308] The "Food Composition Database" is a database that systematically organizes and provides nutritional information on various foods.

[2309] A "recommendation algorithm" is an algorithm that analyzes user preferences and behavioral history to make optimal suggestions to individual users.

[2310] A "clustering algorithm" is a method for grouping data based on similarity.

[2311] "Real-time" refers to data processing and transmission occurring almost simultaneously with the real time axis.

[2312] A "training menu" is a collection of movements or exercises designed to achieve a specific goal or objective.

[2313] "Schedule information" is information including plans and timetables set by the user.

[2314] "Meal contents" refers to the types and amounts of ingredients and dishes consumed by the user.

[2315] "Calorie calculation" is a calculation to calculate the amount of energy contained in food.

[2316] "Matching" refers to linking multiple elements (e.g., users) based on specific conditions.

[2317] "Event notification" is the act of communicating information to interested parties about a particular occurrence or activity.

[2318] The present invention is a system that develops optimal training menus for individual users, manages their diet, and supports community activities. To implement this system, the following specific hardware and software are required.

[2319] Training menu planning / guidance

[2320] server:

[2321] Image reception and analysis module: The server receives an image of the user's desired body shape and performs image analysis using a machine learning model (e.g., TensorFlow). This analysis extracts body shape features (such as muscle distribution and fat distribution).

[2322] Menu generation module: The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The generated menu is created taking into account the user's individual goals and current physical condition.

[2323] Form check module: The server receives real-time video of the user training and uses posture analysis technology (e.g., OpenPose) to check whether the training is being performed with proper form, generating correction instructions as necessary.

[2324] Schedule management module: The server creates a training plan that utilizes the user's free time based on the user's schedule information.

[2325] Device:

[2326] Training module: The user uses the device's camera to transmit images of themselves training to the server, and receives real-time guidance on their form. The module also displays training menus and correction instructions sent from the server.

[2327] User:

[2328] Image transmission: The user sends an image of the desired body shape from their smartphone to the server. For example, they can take a photo of a fitness model and send it.

[2329] Training implementation: The user implements the training according to the instructions from the server.

[2330] Dietary management

[2331] server:

[2332] Food image analysis module: The server receives food images taken by the user and analyzes the food contents using image recognition technology (e.g., ResNet). This analysis identifies the foods contained in the meal and their amounts.

[2333] Calorie calculation module: The server calculates calories based on the image analysis results and references a food composition database (e.g., USDA food composition database).

[2334] Menu suggestion module: The server uses a recommendation algorithm (e.g., collaborative filtering) to generate an optimal menu, taking into account the user's likes and dislikes and dietary history.

[2335] Device:

[2336] Meal Recording Module: The user takes a photo of the meal and sends it to the server.

[2337] Menu display module: Displays the menu sent from the server to the user and suggests the next meal.

[2338] User:

[2339] Food photography: A user takes a photo of their meal with their smartphone and sends it to the server from the device. For example, they take a photo of their lunch or dinner.

[2340] Menu confirmation: The user checks the menu suggestions from the server and selects the appropriate meal.

[2341] Community Activities

[2342] server:

[2343] User matching module: The server uses a clustering algorithm (e.g., K-Means) to match users with similar desired body types and hobbies and preferences.

[2344] Event planning module: The server plans training sessions and events for matched users and notifies them of the information.

[2345] Device:

[2346] Community participation module: Users can check community information and participate in events.

[2347] Event notification module: Notifies the user of event information sent from the server.

[2348] User:

[2349] Community participation: Users are interested in events they are notified about and participate through the app, for example, by attending a monthly training session.

[2350] Socialize: Users attend events, interact with other users, and train together.

[2351] Specific examples

[2352] 1. Training menu planning / guidance:

[2353] Users take a picture of the body shape they want to achieve (for example, a photo of a fitness model) with their smartphone and send it to the server via the app. The server then analyzes the image using TensorFlow and generates an optimal training menu.

[2354] When the user starts training, the smartphone camera sends images to the server in real time, and the form check module using OpenPose generates appropriate form correction instructions and provides them to the user.

[2355] 2. Dietary Management:

[2356] A user takes a photo of their lunch salad and steak and sends it to the server, which analyzes the image using ResNet and calculates the calories of each food item from the USDA Food Composition Database.

[2357] The server uses collaborative filtering to suggest the next meal menu based on the user's likes and dislikes and past eating history, and displays it on the device.

[2358] 3. Community Activities:

[2359] The server uses clustering to match users with common goals and hobbies, and then plans and notifies them of monthly training sessions.

[2360] Users receive notifications, become interested, and attend events, where they can interact with other users and train together.

[2361] Prompt Sentence Examples

[2362] "How can I send you an image of the body shape I'm aiming for?"

[2363] "I want to make sure my form is correct during my workouts. How can I do that?"

[2364] "I'd like you to calculate the calories in today's lunch. I took a photo and sent it to you."

[2365] "I would like to participate in events where I can interact with people who share the same hobbies."

[2366] The above is a specific embodiment of the present invention. This system makes it possible to provide training menus tailored to the needs of individual users, manage their diet appropriately, and support community activities.

[2367] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2368] Training menu planning / guidance

[2369] Step 1:

[2370] The user takes a picture of the body shape they are aiming for with their smartphone and sends it to the server using a dedicated app. The input is the image of the body shape acquired by the user, and the output is the result of sending the image data to the server.

[2371] Step 2:

[2372] The server receives the images and performs image analysis using a machine learning model (TensorFlow). The input is the received image data, and the output is data that extracts body shape features. This analysis allows for the acquisition of body shape features such as muscle distribution and fat distribution.

[2373] Step 3:

[2374] The server uses a genetic algorithm to generate an optimal training menu based on the results of image analysis. The input is the extracted body shape feature data, and the output is an optimized training menu. The menu includes the required exercises, their intensity, frequency, etc.

[2375] Step 4:

[2376] The user starts training and sends the training video to the server in real time using the smartphone camera. The input is the video data during training, and the output is the video transmission result to the server.

[2377] Step 5:

[2378] The server analyzes the video received in real time and uses posture analysis technology such as OpenPose to check whether the correct form is being maintained. The input is real-time video data, and the output is the evaluation result of the form appropriateness. Instructions for correcting the form are generated as needed.

[2379] Step 6:

[2380] The server generates form correction instructions, which are sent to the terminal and displayed to the user. The input is the form correction instruction data, and the output is the display result on the user's terminal. The user performs training according to these instructions.

[2381] Dietary management

[2382] Step 1:

[2383] The user takes a photo of their meal with their smartphone and sends it to the server using a dedicated app. The input is the image data of the meal, and the output is the result of sending the image data to the server.

[2384] Step 2:

[2385] The server receives the food images and performs image analysis using image recognition techniques such as ResNet. The input is the received image data, and the output is the identified foods and their quantities.

[2386] Step 3:

[2387] The server calculates calories based on the image analysis results by checking against the food composition database (USDA food composition database). The input is the identified food and its quantity data, and the output is the calculated calorie value.

[2388] Step 4:

[2389] The server uses a collaborative filtering algorithm to generate a menu for the next meal, taking into account the user's likes and dislikes and dietary history. The input is the user's dietary history and likes and dislikes, and the output is the generated menu.

[2390] Step 5:

[2391] The server sends the generated menu to the user's device and suggests the next meal. The input is the generated menu data, and the output is the display result on the user's device. The user selects an appropriate meal based on the suggestions.

[2392] Community Activities

[2393] Step 1:

[2394] The server analyzes the user's desired body type and hobbies and preferences, and matches similar users using a clustering algorithm (K-Means). The input is the user's goals and preference data, and the output is the matching results.

[2395] Step 2:

[2396] The server plans training sessions and events for matched users and notifies them of the information. The input is the matching result data, and the output is the planned event information data.

[2397] Step 3:

[2398] The server sends planned event information to users' terminals and encourages them to participate in the event. The input is event information data, and the output is the notification result sent to the user terminal.

[2399] Step 4:

[2400] The user checks the event information displayed on the terminal and registers to participate in the events they are interested in. The input is the event information data, and the output is the registration result.

[2401] Step 5:

[2402] On the day of the event, users participate in community activities with other users and deepen their interactions. The input is event participation information, and the output is interaction experience points and feedback.

[2403] (Application example 1)

[2404] 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."

[2405] Conventional training support systems have had the problem of making it difficult to create training menus tailored to each user's physical condition and goals, and of not being able to check or correct form in real time. Furthermore, when it comes to dietary management, calorie calculations and menu suggestions are time-consuming, and measures to address these issues are insufficient. Furthermore, there was a lack of mechanisms to encourage interaction between users with common goals or hobbies or to participate in events, making it difficult to maintain motivation.

[2406] 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.

[2407] In this invention, the server includes: means for receiving images of the desired body shape and analyzing the images; means for generating an optimal training menu based on the image analysis results; means for receiving video of the user's training in real time and generating training form correction instructions; means for formulating a training plan for spare time based on the user's schedule information; means for the user to take images of their meals and send them to the server, which then analyzes the images and calculates calories; and means for matching users with common goals and planning and notifying them of training events inside and outside the store. This enables the formulation of optimal training menus tailored to each user's individual goals, real-time form checks, and smooth calorie management and menu suggestions. Furthermore, it encourages interaction and event participation among users with common goals and hobbies, helping to maintain motivation.

[2408] 1. "Body shape image" is an image that visually shows the ideal body shape that the user is aiming for.

[2409] 2. "Image analysis" is the process of analyzing transmitted image data and extracting necessary information from its contents.

[2410] 3. "Training Menu" means a schedule of exercises and activities required for the user to achieve the desired body shape.

[2411] 4. "Video" refers to video data of a user performing training.

[2412] 5. "Form correction instructions" refers to real-time instruction provided to help users adopt the correct exercise posture.

[2413] 6. "Schedule information" is data that represents a user's daily activities and free time.

[2414] 7. "Spare time" refers to a period of time in a user's schedule when they can engage in an activity even for a short period of time.

[2415] 8. "Meal images" are photographs of food taken by the user.

[2416] 9. "Calorie counting" is the process of calculating the amount of energy intake based on the contents of a meal.

[2417] 10. "Menu suggestion" is a suggestion for the next meal that takes into account the user's preferences and nutritional balance.

[2418] 11. A "common goal" is a training or health-related objective shared by multiple users.

[2419] 12. "Matching" is the process of identifying and pairing or grouping users with common goals or interests.

[2420] 13. A "Training Event" is an opportunity for users with similar goals to come together and exercise together.

[2421] 14. "Notification" means a communication method used to inform users about training events or important information.

[2422] The system of the present invention is designed to provide users with personalized training menus, support dietary management, and promote community activities. The system consists of three main components: a server, a terminal, and users.

[2423] Training menu planning / guidance

[2424] server:

[2425] The server performs the following functions:

[2426] "Image Reception and Analysis Module": Receives images of the user's desired body shape and performs image analysis. This analysis uses software such as the image analysis library "OpenCV." The analysis results are used to extract the characteristics of the user's ideal body shape.

[2427] "Menu generation module": Generates an optimal training menu based on the image analysis results. This uses a generative AI model (e.g., GPT-4).

[2428] "Form Check Module": This module receives real-time video footage of the user training, checks whether the training is being performed with proper form, and generates correction instructions as necessary. This process uses the real-time video processing library "Kinesis Video Streams."

[2429] "Schedule Management Module": Based on the user's schedule information, it creates a training plan that utilizes their free time.

[2430] Device:

[2431] The device is equipped with the following features:

[2432] "Training module": The user uses the device's camera to send images to the server while training, and receives real-time guidance on form. The module also displays training menus and correction instructions sent from the server.

[2433] User:

[2434] The user performs the following actions:

[2435] "Send image": Send an image of the desired body shape from your device to the server.

[2436] "Training": Training is carried out according to instructions from the server.

[2437] Dietary management

[2438] server:

[2439] The server supports the following features:

[2440] "Meal Image Analysis Module": Receives meal images taken by the user and performs image analysis. This analysis uses "Tesseract OCR" to identify the foods contained in the meal and their amounts.

[2441] "Calorie Calculation Module": Calculates the calorie content of food based on the results of image analysis. Uses a dedicated calorie calculation API.

[2442] "Menu suggestion module": Suggests the menu for the next meal, taking into account the user's likes and dislikes and eating history.

[2443] Device:

[2444] The device will be equipped with the following features:

[2445] "Meal Recording Module": The user takes a photo of what they have eaten and sends it to the server.

[2446] "Menu display module": Displays the menu sent from the server to the user and suggests the next meal.

[2447] User:

[2448] The user performs the following actions:

[2449] "Photo of food": Take a photo of your meal and send it from your device to the server.

[2450] "Confirm Menu": Check the menu suggestions from the server and select an appropriate meal.

[2451] community

[2452] server:

[2453] The server provides the following functions:

[2454] "User Matching Module": Matches users with common goals.

[2455] "Event Planning Module": Plans and announces training sessions and events between matched users. Data management uses "MySQL" and "Django."

[2456] Device:

[2457] The device will be equipped with the following features:

[2458] "Community Participation Module": Users check community information and participate in events.

[2459] "Event notification module": Notifies the user of event information sent from the server.

[2460] User:

[2461] The user performs the following actions:

[2462] "Community participation": Become interested in a notified event and participate through the app.

[2463] "Interact": Participate in events and deepen your interactions with other users.

[2464] Prompt Sentence Examples

[2465] 1. Training menu generation

[2466] "Upload an image of the body shape you want to achieve. After analyzing it, the system will suggest the optimal training menu."

[2467] 2. Real-time form checking

[2468] "Please record your training with a camera and send it to us. We will check your form in real time and provide appropriate guidance."

[2469] 3. Dietary Management

[2470] "Take a photo of the food you ate today and upload it. We'll analyze the calories and give you suggestions for your next meal."

[2471] 4. Community Support

[2472] "We will be organizing events for members with common goals. Please check the announcements if you would like to participate."

[2473] The above is a specific embodiment for carrying out the present invention, which makes it possible to provide training guidance and dietary management that is optimized for each individual user, and also to increase motivation through community activities.

[2474] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2475] Step 1:

[2476] The user takes a picture of the body shape they are aiming for using their smartphone and sends it from the device to the server.

[2477] Input: Body image

[2478] Data processing: Image data stored on the device is uploaded to the server via the device's application.

[2479] Output: The body image is sent to the server.

[2480] Step 2:

[2481] The server's image reception and analysis module analyzes the received body shape image.

[2482] Input: Body image

[2483] Data processing: Image features are extracted using the OpenCV library to identify ideal body shape properties.

[2484] Output: Body shape characteristic data is obtained as the analysis result.

[2485] Step 3:

[2486] The server's menu generation module generates an optimal training menu based on the image analysis results.

[2487] Input: Body shape feature data

[2488] Data processing: Using a generative AI model (e.g., GPT-4), a training menu is generated based on the user's goals and current physical condition.

[2489] Output: Customized training menu

[2490] Step 4:

[2491] The user begins training, takes a video of themselves using their smartphone camera, and sends it to the server in real time from the device.

[2492] Input: Video of training

[2493] Data processing: Real-time video data is acquired using the device's camera function.

[2494] Output: Live video is sent to the server.

[2495] Step 5:

[2496] The server's form check module analyzes the real-time video and generates instructions for correcting training form.

[2497] Input: Live footage of training

[2498] Data Processing: Using Kinesis Video Streams and OpenCV, we analyze the user's posture and determine the proper form.

[2499] Output: Form correction instructions

[2500] Step 6:

[2501] The server's instructions are sent to the terminal and displayed on the user's terminal.

[2502] Input: Form correction instruct...

Claims

1. A means for receiving an image of the desired body shape and performing image analysis; A means for generating an optimal training menu based on the image analysis results; a means for receiving a video of a user performing training in real time and generating instructions for correcting the user's training form; A means for formulating a training plan for spare time based on the user's schedule information; A system including:

2. A means for receiving an image of a meal taken by a user and analyzing the image of the meal content; a means for calculating calories based on the image analysis results; A means for generating an optimal menu taking into consideration the likes and dislikes of the user; The system of claim 1 , comprising:

3. A way to match users with similar body types and hobbies, A means to plan and notify training sessions and events between matched users, The system of claim 1 , comprising:

Images