System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and storing default data of a user; means for collecting and storing real-time data of the user; means for analyzing the collected data and suggesting a specific action to achieve a goal of the user; means for notifying the user of the suggested action; means for generating an image of the user after achieving the goal; means for displaying the generated image to the user; means for tracking tasks completed by the user and managing points; and means for providing rewards to the user based on the point management.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] This invention aims to solve the problems users face in the dieting process, such as maintaining motivation, lack of a concrete action plan, and discouragement due to the inability to see results. Specifically, there is a need for a solution that allows users to continue dieting in an enjoyable manner. Some of the problems include diet plans becoming meaningless, the lack of clarity about the specific actions required to achieve goals, and the difficulty in maintaining motivation due to the lack of visualization of results. [Means for solving the problem]

[0005] The present invention provides a system that collects and stores user initial setting data and real-time data, analyzes the data, and proposes specific actions. The system includes the following means:

[0006] 1. Means of collecting and storing user preference data

[0007] 2. Means of collecting and storing real-time user data

[0008] 3. A means of analyzing collected data and suggesting specific actions to help users achieve their goals.

[0009] 4. Means of notifying users of proposed actions

[0010] 5. A way to visualize what the user will look like after achieving their goal

[0011] 6. How to display the generated image to the user

[0012] 7. A way for users to track completed tasks and manage points

[0013] 8. Means of providing rewards to users based on point management

[0014] This allows users to continue their daily exercise and dietary management while enjoying it, and furthermore, by visualizing what they will look like after achieving their goals, they can maintain their motivation. In this way, we provide a system that prevents diet plans from becoming meaningless and supports users in achieving their goals.

[0015] "User's initial setting data" refers to basic information that the user inputs when setting a diet goal, and includes, for example, current weight, target weight, eating habits, exercise habits, and the like.

[0016] "User real-time data" refers to data that records the user's daily activities, such as the amount of exercise, calories burned, dietary content, and sleep patterns.

[0017] "Collection and storage means" means a system, including hardware and software, for collecting user data and storing it temporarily or permanently.

[0018] "Means for analyzing data and suggesting specific actions" refers to a system that uses AI and other algorithms to calculate and suggest effective actions for achieving goals based on collected user data.

[0019] "Means for notifying suggested actions" refers to a system for informing users of suggested actions based on the analysis results, and includes applications and devices with notification functions.

[0020] The "means for generating an image of what the user will look like after achieving the goal" is a system that includes AI and algorithms that generate images to visually represent the physical changes that will occur after the goal is achieved, based on the goal achievement data entered by the user.

[0021] The "means for displaying the generated image to the user" refers to a system including a display device and an application for displaying the visualization data obtained by image generation to the user.

[0022] The "means for tracking tasks and managing points" is a system that records the progress of diet-related tasks performed by the user and manages and adds points according to the completion of the tasks.

[0023] The "means for providing rewards" is a system for providing certain rewards or incentives to users based on the points awarded to them. [Brief explanation of the drawings]

[0024] [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

[0025] 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.

[0026] First, the terms used in the following description will be explained.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] The present invention is a system that uses AI to support the user's dieting process and is designed to allow the user to continue dieting in an enjoyable manner. The following describes an embodiment of the system.

[0046] System configuration

[0047] This system mainly consists of the following components:

[0048] 1. User device: A device such as a smartphone or tablet.

[0049] 2. Server: Cloud server or on-premise data server.

[0050] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0051] Program processing

[0052] Collecting and storing user preference data

[0053] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[0054] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[0055] Server: Saves the received initial setting data in a database.

[0056] Collecting and storing real-time user data

[0057] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[0058] Server: Stores the data received in real time in a database.

[0059] Data analysis and action proposals

[0060] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[0061] Terminal: Notify user of proposed plan of action.

[0062] Users: Get notified and take action.

[0063] Goal image generation and display

[0064] User: Enters data such as target weight and current weight.

[0065] Terminal: Sends these data to the server.

[0066] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[0067] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[0068] Users: Visualize themselves after achieving their goals and increase motivation.

[0069] Implementing gamification elements

[0070] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[0071] Terminal: Notifies the user of tasks and tracks task progress.

[0072] User: When a user completes a task, the information is sent to the server and points are added.

[0073] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[0074] Terminal: Shows reward details and points progress to users.

[0075] These features allow users to continue their daily exercise and dietary management in an enjoyable way, and maintain motivation to achieve their goals. Furthermore, the system is designed to incorporate a competitive element, allowing users to encourage each other as they diet. In this way, it provides an efficient system that can comprehensively solve dieting challenges.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[0079] Step 2:

[0080] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[0081] Step 3:

[0082] Device: Sends saved initial setting data to the server.

[0083] Step 4:

[0084] Server: Analyzes the received initial setting data and stores it in a database.

[0085] Step 5:

[0086] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[0087] Step 6:

[0088] Terminal: Sends collected real-time data to the server.

[0089] Step 7:

[0090] Server: Stores the data received in real time in a database and checks the integrity of the data.

[0091] Step 8:

[0092] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[0093] Step 9:

[0094] Server: Based on the results of the AI ​​analysis, it generates specific action suggestions for the user (e.g., walk 6,000 steps).

[0095] Step 10:

[0096] Device: Notify the user of the proposed plan of action and display details on the screen.

[0097] Step 11:

[0098] Users: Receive notifications and act on proposed action plans.

[0099] Step 12:

[0100] User: Enters data such as target weight and current weight, as well as a current photo.

[0101] Step 13:

[0102] Terminal: Sends the entered data to the server.

[0103] Step 14:

[0104] Server: Using image generation AI, generate what the user will look like when they achieve their target weight.

[0105] Step 15:

[0106] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[0107] Step 16:

[0108] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[0109] Step 17:

[0110] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[0111] Step 18:

[0112] Terminal: Notifies the user of the generated task and displays the task details.

[0113] Step 19:

[0114] User: Confirms and executes the task (e.g., walk 10,000 steps).

[0115] Step 20:

[0116] Terminal: Detects when the user completes a task and sends that information to the server.

[0117] Step 21:

[0118] Server: Receives task completion information and updates user points.

[0119] Step 22:

[0120] Terminal: Notify users of updated points and newly earned rewards.

[0121] Step 23:

[0122] User: Check the points and rewards earned and work on the next task.

[0123] This allows users to continue their daily exercise and dietary management while having fun, and maintain their motivation. Users can also compete with other users to earn points, further increasing motivation.

[0124] Example 1

[0125] 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."

[0126] Conventional diet support systems have the problem of making it difficult for users to continue dieting. Specifically, it is difficult to efficiently collect and store the user's initial setting data and real-time data, and to make appropriate action suggestions based on that data. In addition, there is a lack of a way to visually show the effectiveness of the action suggestions, making it difficult to maintain the user's motivation. Furthermore, there is a need for a system that can provide users with continuous diet support by incorporating game elements.

[0127] 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.

[0128] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goal, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goal, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, means for verifying the accuracy of the real-time data, means for using an AI model to generate a suggested action plan, and means for generating an appearance after achieving the goal using an image generation AI model based on the user's data, which enables the user to enjoy and continue dieting and easily maintain motivation to achieve their goal.

[0129] "Means for collecting and saving user initial setting data" refers to a function that saves basic information entered by the user, such as weight, target weight, eating habits, and exercise habits, on the device and sends that data to the server.

[0130] "Means for collecting and storing real-time user data" refers to a function that allows a device to obtain data such as exercise, sleep, and diet from sensors in wearable devices and smartphones and send it to a server.

[0131] "Means for analyzing collected data and suggesting specific actions to achieve the user's goals" refers to a function that allows the server to analyze accumulated user data and use an AI model to generate an action plan appropriate for the user.

[0132] "Means for notifying the user of suggested actions" refers to push notifications or in-app notifications that inform the user of suggested actions received by the device from the server.

[0133] The "means for generating an image of what the user will look like after achieving their goal" is a function that allows the server to use an image generation AI model based on the user's goal data to generate an image of the user after achieving their goal.

[0134] The "means for displaying the generated image to the user" is a function that enables the terminal to display the image generated by the server to the user.

[0135] "Means for tracking tasks completed by users and managing points" is a function that allows the server to record the task completion status of users and reflect it in the point system.

[0136] The "means for providing rewards to users based on point management" is a function that allows the server to set rewards according to the accumulated points of users and provide the rewards to the users.

[0137] "Means for verifying the accuracy of real-time data" refers to the internal processing performed by the server to verify the validity and accuracy of the real-time data received.

[0138] "Means of using AI models to generate suggested action plans" refers to the use of modern machine learning techniques to analyze user data and automatically generate next steps or exercise plans.

[0139] "A means for generating what the user's goal will look like after it has been achieved using an image generation AI model based on user data" is a function that uses AI to convert the user's goal information into visual data and provides the future image.

[0140] This invention is a system that utilizes AI technology to support users in their dieting process, and is designed to enable users to enjoyably and continuously diet. Detailed embodiments for specifically implementing this system are described below.

[0141] System configuration

[0142] The system consists of the following main components:

[0143] 1. User device: A device such as a smartphone or tablet.

[0144] 2. Server: Cloud server or on-premise data server.

[0145] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0146] Collecting and saving initial setup data

[0147] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[0148] Example: A user inputs "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", and "Exercise 3 times a week".

[0149] 2. Terminal: The entered initial setting data is temporarily stored in local storage and then securely sent to the server using the HTTPS protocol. The software used is a lightweight database such as SQLite.

[0150] Example: Save initial setting data in local storage in a file called "usersettings.db".

[0151] 3. Server: The server stores the received initial configuration data in an RDBMS (e.g., MySQL or PostgreSQL).

[0152] Example: Execute an INSERT statement to store data in the "UserSettings" table in the database.

[0153] Real-time data collection and storage

[0154] 1. Device: The device periodically collects exercise, sleep, dietary data, etc. from sensors in wearable devices and smartphones.

[0155] Example: Obtaining step count and heart rate data from a smartwatch via Bluetooth.

[0156] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[0157] Example: Validating data to ensure it is valid before saving it to the database.

[0158] Data analysis and action proposals

[0159] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model using Python's TensorFlow or PyTorch.

[0160] Example: Generate a suggestion such as "Walk 6000 steps tomorrow" based on data from the past 7 days. An example prompt is as follows:

[0161] "Generate exercise suggestions for the user for the next day based on their exercise data from the past seven days. For example, a suggestion like 'Walk 6,000 steps tomorrow.'"

[0162] 2. On the device: Notify the user of the proposed action plan via push notification.

[0163] Example: A message appears in the notification bar on your smartphone saying, "Walk 6,000 steps tomorrow."

[0164] Goal image generation and display

[0165] 1. User: Enter data such as target weight and current weight.

[0166] Example: A user inputs weight data "Current weight: 70 kg" and "Target weight: 60 kg".

[0167] 2. Terminal: Sends these data to the server.

[0168] 3. Server: Using image generation AI (such as Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[0169] Example: An image generation AI model generates "what it will look like when it weighs 60 kg." The prompt is as follows:

[0170] "The user's current weight is 70 kg, and their target weight is 60 kg. Based on this information, please generate an image of what the user will look like when they reach 60 kg."

[0171] 4. Terminal: displays the generated image to the user.

[0172] Implementing gamification elements

[0173] 1. Server: Generates diet-related tasks and assigns points based on the tasks.

[0174] Example: The server sets a task: "Walk 10,000 steps to get 10 points."

[0175] 2. Device: Notifies the user of tasks and tracks task progress in real time.

[0176] 3. User: When a task is completed, points are earned and the information is sent to the server.

[0177] Example: After a user walks 10,000 steps, the app reports "task completed."

[0178] 4. Server: Manages points and provides rewards based on accumulated points.

[0179] 5. Terminal: Shows rewards and points progress to users.

[0180] Example: Displaying "100 points reached! New rewards earned!" on the in-app dashboard.

[0181] In this way, users can continue their daily exercise and diet management in an enjoyable way and stay motivated to achieve their goals. Also, by incorporating an element of competition with other users, an efficient system is provided where users can encourage each other while dieting.

[0182] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0183] Step 1:

[0184] Collecting and storing user preference data

[0185] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when first launched.

[0186] Input: The user enters the following information into a form: "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", "Exercise 3 times a week".

[0187] Output: The input data is saved in the app.

[0188] 2. Terminal: The entered initial setting data is temporarily saved in local storage and sent to the server using the HTTPS protocol.

[0189] What happens: The app saves the data and sends it to the server via a web request.

[0190] Input: Initial configuration data obtained from the user.

[0191] Output: Initial configuration data sent to the server.

[0192] 3. Server: The server stores the received initial setting data in an RDBMS (such as MySQL or PostgreSQL).

[0193] Specific operation: The INSERT statement is executed on the server side and the data is stored in the "UserSettings" table.

[0194] Input: Initialization data sent from the terminal.

[0195] Output: Initial configuration data stored in the database.

[0196] Step 2:

[0197] Real-time data collection and storage

[0198] 1. Device: The device periodically collects exercise, sleep, and dietary data from sensors in wearable devices and smartphones.

[0199] Specific operation: Obtain data from smartwatch via Bluetooth.

[0200] Input: Real-time data from wearable devices.

[0201] Output: Collected data is saved to the device.

[0202] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[0203] What it does: Validates data accuracy using validation algorithms and filters out invalid data.

[0204] Input: Real-time data sent from the device.

[0205] Output: The validated data is saved in the database.

[0206] Step 3:

[0207] Data analysis and action proposals

[0208] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model (TensorFlow or PyTorch).

[0209] How it works: The AI ​​model performs predictions using a Python script.

[0210] Input: Last 7 days of user data stored in the database.

[0211] Output: Suggested action for the next day (e.g., "Walk 6,000 steps tomorrow").

[0212] 2. On the device: Notify the user of the proposed action plan via push notification.

[0213] Specific action: Proposals are notified using the smartphone's notification function.

[0214] Input: Action suggestions from the server.

[0215] Output: The notification message that will be displayed on the user's smartphone.

[0216] Step 4:

[0217] Goal image generation and display

[0218] 1. User: Enter data such as target weight and current weight.

[0219] Specific action: Enter data into a form within the app.

[0220] Input: User's weight data (e.g. current weight 70kg, target weight 60kg).

[0221] Output: Weight data stored on the device.

[0222] 2. Terminal: Sends these data to the server.

[0223] Specific operation: Issue an HTTPS request and send data to the server.

[0224] Input: User's weight data.

[0225] Output: Weight data sent to the server.

[0226] 3. Server: Using image generation AI (Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[0227] Specific operation: Calls the AI ​​model and executes the image generation process.

[0228] Input: User's weight data.

[0229] Output: The generated goal image.

[0230] 4. Terminal: displays the generated image to the user.

[0231] Specific behavior: Display an image within the app.

[0232] Input: Generated image sent from the server.

[0233] Output: The generated image displayed on a smartphone.

[0234] Step 5:

[0235] Implementing gamification elements

[0236] 1. Server: Generates diet-related tasks and sets points.

[0237] Specific operation: Run the task generation algorithm and add a new task to the database.

[0238] Input: User's exercise data.

[0239] Output: The generated tasks.

[0240] 2. Terminal: Notifies the user of tasks and tracks progress.

[0241] Specific action: Use the smartphone's notification function to notify you of the task.

[0242] Input: Task data sent from the server.

[0243] Output: Task notification.

[0244] 3. User: When a task is completed, points are earned and the information is sent to the server.

[0245] Specific action: Tap the "Complete Task" button within the app to earn points.

[0246] Input: User's task completion information.

[0247] Output: Completion information sent to the server.

[0248] 4. Server: Manages points and provides rewards.

[0249] Specific operation: Calculate rewards using a points management system and provide them to users.

[0250] Input: The user's accumulated points.

[0251] Output: The reward offered.

[0252] 5. Terminal: Shows rewards and points progress to users.

[0253] Specific behavior: Display rewards and points on the in-app dashboard.

[0254] Input: Points and rewards data sent from the server.

[0255] Output: Progress displayed on the user's smartphone.

[0256] (Application example 1)

[0257] 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."

[0258] Conventional diet support systems make it difficult for users to maintain motivation to continue daily exercise and diet management, and there are no systems that can support specific diet action plans or meal optimization. Furthermore, there is a lack of specific support to increase the success rate of dieting by proposing meal menus suitable for users and making them easy to order. This creates a challenge for users, making it difficult to diet in a planned and effective manner.

[0259] 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.

[0260] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, and means for suggesting optimal meal menus based on the user's exercise and dietary status and allowing the user to order those meals. This enables the user to effectively and continuously manage their daily exercise and diet, thereby increasing the success rate of their diet. Furthermore, the ability to easily order appropriate meal menus supports the user in improving their dietary habits and makes their overall dieting efforts more efficient.

[0261] "User's initial setting data" refers to basic information that the user inputs when launching the diet support system for the first time, and includes current weight, target weight, eating habits, and exercise habits.

[0262] "User real-time data" refers to data on a user's daily exercise and dietary habits collected in real time from devices such as wearable devices and smartphones.

[0263] The "means of analysis and suggestion" is a system that analyzes the collected initial setting data and real-time data of the user and suggests specific action plans and meal menus to help the user achieve their goals.

[0264] "Means for notifying actions" refers to a function that notifies the user of suggested action plans and meal menus on their smartphone or other device.

[0265] The "image generation means" is a system that uses AI image generation technology to predict what the user will look like after achieving their target weight and generates an image of that prediction.

[0266] The "image display means" is a function that displays on the terminal the image of the user after achieving the generated target weight.

[0267] A "task tracking tool" is a system that tracks whether a user has carried out an action plan or suggested meal menu and records their progress.

[0268] The "point management means" is a system that grants and manages points based on the tasks that users complete, and provides rewards to users based on those points.

[0269] The "meal menu suggestion method" is a system in which AI suggests the optimal meal menu based on the user's exercise and eating habits, and notifies the user of the suggested menu.

[0270] The "Meal Ordering Method" is a system that allows users to easily order suggested meal menus, and is a function that connects with nearby affiliated restaurants and delivery services.

[0271] This invention is a system that uses AI to support users in their dieting. This system proposes optimal meal menus based on the user's exercise and eating habits, and allows them to easily order them, thereby providing effective and continuous support for the user's diet.

[0272] System configuration

[0273] This system consists of the following main components:

[0274] 1. User device: The device used by the user, such as a smartphone or tablet.

[0275] 2. Server: A cloud server that stores and analyzes collected data.

[0276] 3. Wearable devices: Devices that collect user exercise and sleep data (e.g., smartwatches).

[0277] Program processing

[0278] Collecting and storing user preference data

[0279] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[0280] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[0281] Server: Saves the received initial setting data in a database.

[0282] Collecting and storing real-time user data

[0283] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[0284] Server: Stores the data received in real time in a database.

[0285] Data analysis and action proposals

[0286] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[0287] Terminal: Notify user of proposed plan of action.

[0288] Users: Get notified and take action.

[0289] Goal image generation and display

[0290] User: Enters data such as target weight and current weight.

[0291] Terminal: Sends these data to the server.

[0292] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[0293] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[0294] Users: Visualize themselves after achieving their goals and increase motivation.

[0295] Implementing gamification elements

[0296] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[0297] Terminal: Notifies the user of tasks and tracks task progress.

[0298] User: When a user completes a task, the information is sent to the server and points are added.

[0299] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[0300] Terminal: Shows reward details and points progress to users.

[0301] Hardware and software used

[0302] This system uses the following hardware and software.

[0303] Hardware: Smartphones (iPhone, Android), wearable devices (Apple Watch, Fitbit)

[0304] Software: AWS Lambda, Amazon RDS, Firebase, TensorFlow, React Native

[0305] Specific examples

[0306] 1. When the user does the initial setup:

[0307] Users open the app on their smartphone and enter their current weight, goal weight, dietary habits, and exercise habits as initial settings. The entered data is then sent to a cloud server.

[0308] 2. When collecting data:

[0309] Real-time exercise and sleep data is collected through the wearable device and sent to a server via a smartphone.

[0310] 3. When AI suggests a meal:

[0311] An AI model on the server analyzes the user's exercise and eating habits and suggests the optimal meal menu for the next day.

[0312] 4. When the user receives the suggestion:

[0313] The suggested meal menu will be sent to the user's smartphone, allowing them to order meals directly from affiliated restaurants or delivery services.

[0314] Prompt Sentence Examples

[0315] "Recommend next day's meal plans based on the user's calorie consumption data and eating habits. Show the best choices for the user's weight goal."

[0316] The above is a specific embodiment for carrying out the present invention. This system allows users to continue dieting effectively and enjoyably, and achieve their goals.

[0317] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0318] Step 1: Collect and store user preference data

[0319] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[0320] Input: Initial setting data (current weight, target weight, eating habits, exercise habits)

[0321] Output: Save data to local storage and send to server

[0322] What happens: A user opens the app on their phone and enters the required information into the designated input fields.

[0323] Step 2: Collect and store real-time user data

[0324] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[0325] Input: Exercise, sleep, and diet data from wearable devices

[0326] Output: Data sent to the server in real time

[0327] How it works: The smartphone periodically collects data from the wearable device and uploads it to a server.

[0328] Step 3: Analyze the data and develop an action plan

[0329] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[0330] Input: User initial setting data, real-time data history

[0331] Output: A concrete action plan (e.g., "Let's walk 6,000 steps tomorrow")

[0332] How it works: The AI ​​model on the server analyzes past data and generates an optimal plan of action for the next day.

[0333] Step 4: Communicate your action plan

[0334] Terminal: Notify user of proposed plan of action.

[0335] Input: AI-generated action plan

[0336] Output: Action plan notified to smartphone

[0337] How it works: Once the server generates an action plan, it pushes it to the user's smartphone.

[0338] Step 5: User Action

[0339] Users: Get notified and take action.

[0340] Input: Notified Action Plan

[0341] Output: Perform an action (e.g., walk 6000 steps)

[0342] Action: The user checks the notification on their smartphone and performs the indicated action.

[0343] Step 6: Generate and display the goal image

[0344] User: Enters data such as target weight and current weight.

[0345] Input: Target weight and current weight

[0346] Output: Data sent to the server

[0347] How it works: The user enters their goal weight and current weight in the app and sends them to the server.

[0348] Step 7: Generate images

[0349] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[0350] Input: Target weight and current weight

[0351] Output: The generated goal image

[0352] How it works: The image generation AI on the server generates the user's goal image based on the input data.

[0353] Step 8: Displaying the image

[0354] Terminal: Displays the generated image to the user.

[0355] Input: Generated goal image

[0356] Output: Goal image displayed on a smartphone

[0357] Operation: The generated image is downloaded to a smartphone and displayed.

[0358] Step 9: Task Tracking and Points Management

[0359] Terminal: Tracks the tasks completed by the user and sends them to the server.

[0360] Input: Completed task data

[0361] Output: Task data sent to the server

[0362] How it works: When a user completes a task, their smartphone sends the information to a server.

[0363] Step 10: Awarding points

[0364] Server: Manages points and provides rewards when users reach a certain number of points.

[0365] Input: Task data and point management data

[0366] Output: Reward provided to user

[0367] How it works: The server calculates points based on tracking data and provides rewards.

[0368] Step 11: Meal suggestions

[0369] Server: AI suggests optimal meal menus based on the user's exercise and eating habits.

[0370] Input: Exercise status, diet status, user goals

[0371] Output: Suggested meal menu

[0372] How it works: The AI ​​on the server analyzes the data and generates a meal menu suitable for the user.

[0373] Step 12: Notification of proposed menu and ordering

[0374] Device: Providing users with menu suggestions and allowing them to order meals from partner restaurants and delivery services.

[0375] Input: Suggested meal menu

[0376] Output: Notification to user's smartphone, order process

[0377] How it works: The suggested meal menu is sent to the user's smartphone, and once the user confirms the order, an order is placed with the partner service.

[0378] 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.

[0379] The present invention adds a system that recognizes the user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The following describes in detail the embodiments of the present invention.

[0380] System configuration

[0381] This system consists of the following components:

[0382] 1. User device: A device such as a smartphone or tablet.

[0383] 2. Server: Cloud server or on-premise data server.

[0384] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0385] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[0386] Program processing

[0387] Collecting and storing user preference data

[0388] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[0389] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[0390] Server: Analyzes the received initial setting data and stores it in a database.

[0391] Collecting and storing real-time user data

[0392] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[0393] Server: Stores the data received in real time in a database.

[0394] Collecting and analyzing user emotion data

[0395] Device: Analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[0396] Server: Analyzes the collected emotional data and identifies the user's current emotional state.

[0397] Emotion engine: Generates messages and suggested actions based on emotional data to improve user motivation.

[0398] Data analysis and action proposals

[0399] Server: Analyzes accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, based on data and emotional data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[0400] Terminal: Notify user of proposed plan of action.

[0401] Users: Receive notifications and act on proposed action plans.

[0402] Goal image generation and display

[0403] User: Enters data such as target weight and current weight.

[0404] Terminal: Sends these data to the server.

[0405] Server: Uses image generation AI to generate an image of the user after achieving their goal.

[0406] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[0407] Users: Visualize themselves after achieving their goals and increase motivation.

[0408] Implementing gamification elements

[0409] Server: Generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[0410] Terminal: Notifies the user of the generated task and displays the task details.

[0411] User: Confirms and executes the task (e.g., walk 10,000 steps).

[0412] Terminal: Detects when the user completes a task and sends that information to the server.

[0413] Server: Receives task completion information and updates user points.

[0414] Terminal: Notify users of updated points and newly earned rewards.

[0415] User: Check the points and rewards earned and work on the next task.

[0416] This allows users to continue their daily exercise and diet management while having fun, and maintain their motivation. They can also compete with other users to earn points, which further increases motivation. With the introduction of an emotion engine, users can receive optimal action suggestions that take their emotional state into consideration, allowing them to diet more effectively.

[0417] The processing flow will be explained below.

[0418] Step 1:

[0419] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[0420] Step 2:

[0421] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[0422] Step 3:

[0423] Device: Sends saved initial setting data to the server.

[0424] Step 4:

[0425] Server: Analyzes the received initial setting data and stores it in a database.

[0426] Step 5:

[0427] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[0428] Step 6:

[0429] Terminal: Sends collected real-time data to the server.

[0430] Step 7:

[0431] Server: Stores the data received in real time in a database and checks the integrity of the data.

[0432] Step 8:

[0433] Device: Uses the user's camera and microphone to collect emotional data in real time from facial expressions and tone of voice.

[0434] Step 9:

[0435] Terminal: Sends collected emotion data to the server.

[0436] Step 10:

[0437] Server: Analyzes the received emotion data and identifies the user's emotional state.

[0438] Step 11:

[0439] Server: Based on accumulated user data and emotional data, the AI ​​model is used to create the next day's action plan. For example, based on the data and emotional data from the past seven days, it generates a suggestion such as "Walk 6,000 steps the next day."

[0440] Step 12:

[0441] Server: Based on the analysis results, it adjusts specific action suggestions according to the user's emotional state.

[0442] Step 13:

[0443] Device: Notifies the user of the proposed action plan and emotion-based adjustments, displaying details on the screen.

[0444] Step 14:

[0445] Users: Receive notifications and act on proposed action plans.

[0446] Step 15:

[0447] User: Enter data such as target weight, current weight, and photo.

[0448] Step 16:

[0449] Terminal: Sends the entered data to the server.

[0450] Step 17:

[0451] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[0452] Step 18:

[0453] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[0454] Step 19:

[0455] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[0456] Step 20:

[0457] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[0458] Step 21:

[0459] Terminal: Notifies the user of the generated task and displays the task details.

[0460] Step 22:

[0461] User: Confirms and executes the task (e.g., walk 10,000 steps).

[0462] Step 23:

[0463] Terminal: Detects when the user completes a task and sends that information to the server.

[0464] Step 24:

[0465] Server: Receives task completion information and updates user points.

[0466] Step 25:

[0467] Terminal: Notify users of updated points and newly earned rewards.

[0468] Step 26:

[0469] User: Check the points and rewards earned and work on the next task.

[0470] Example 2

[0471] 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."

[0472] Conventional diet management systems were unable to take into account the user's emotional state, leading to a decline in motivation. Furthermore, behavioral suggestions and goal setting were general, without providing appropriate suggestions based on individual data, making it difficult to diet effectively. Furthermore, they lacked the functionality to provide users with a concrete image of what it would be like to achieve their goals, making it difficult to maintain sustained motivation.

[0473] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0474] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for collecting and analyzing emotional data, means for generating messages and suggested actions to improve motivation based on the emotional data, means for generating an image of what the user will look like after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, and means for providing rewards to the user based on the point management. This makes it possible to provide appropriate suggested actions and motivational measures according to the user's emotional state, thereby supporting effective dieting.

[0475] "Means for collecting and storing user initial setting data" refers to a function that collects basic information such as weight, target weight, eating habits, and exercise habits that a user enters when using the diet management system for the first time, and stores this information in local storage and on the server.

[0476] "Means for collecting and storing real-time user data" refers to a function that collects data on exercise, sleep, diet, etc. obtained from the user's wearable device or smartphone in real time and stores it on a server.

[0477] "Means of analyzing collected data and suggesting specific actions to help users achieve their goals" refers to a function that uses AI models and algorithms based on collected data to generate and suggest specific actions, such as individual exercise plans and meal suggestions for each user.

[0478] "Means for notifying the user of the proposed action" is a function that notifies the user of the generated action suggestion on the user's device such as a smartphone or tablet.

[0479] "Means for collecting and analyzing emotional data" refers to a function that uses the user's camera or microphone to collect facial expressions and tone of voice, and analyzes this to identify the user's emotional state.

[0480] The "means for generating messages and suggested actions to improve motivation based on emotional data" is a function that generates messages and suggested actions to improve motivation, taking into account the user's emotional state, based on analyzed emotional data.

[0481] The "means for generating an image of what the user will look like after achieving their goal" is a function that uses the user's current weight and target weight as input data to generate an image of what the user will look like after achieving their goal.

[0482] "Means for displaying the generated image to the user" refers to a function that displays the generated image of the user after achieving the goal on a device such as a smartphone or tablet.

[0483] "A means for tracking tasks completed by users and managing points" refers to a function that detects exercise- and diet-related tasks that users have completed and assigns and manages the corresponding points.

[0484] The "means for providing rewards to users based on point management" is a function for providing rewards based on points earned by users.

[0485] MODE FOR CARRYING OUT THE INVENTION

[0486] The present invention is a system that recognizes a user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The system is composed of the following components:

[0487] System configuration

[0488] 1. User device: A device such as a smartphone or tablet.

[0489] 2. Server: Cloud server or on-premise data server.

[0490] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0491] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[0492] Program processing

[0493] 1. Collecting and saving initial setup data

[0494] The user installs the diet app and inputs basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[0495] The terminal stores the collected initial setting data in a local storage and transmits it to the server.

[0496] The server analyzes the received initial setting data and stores it in a database.

[0497] 2. Real-time data collection and storage

[0498] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[0499] The server stores the data received in real time in a database.

[0500] 3. Emotional Data Collection and Analysis

[0501] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[0502] The server analyzes the collected emotional data to determine the user's current emotional state.

[0503] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[0504] 4. Data analysis and action proposals

[0505] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, it generates a suggestion such as "walk 6,000 steps the next day" based on the data and emotional data from the past seven days.

[0506] The device notifies the user of the proposed plan of action.

[0507] The user receives a notification and acts on the proposed plan of action.

[0508] 5. Goal image generation and display

[0509] The user inputs data such as a target weight and current weight.

[0510] The terminal transmits this data to the server.

[0511] The server uses image generation AI to generate an image of the user after achieving their goal.

[0512] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[0513] Users can visualize themselves after achieving their goals, which increases motivation.

[0514] 6. Implementing gamification elements

[0515] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[0516] The terminal notifies the user of the created task and displays the task details.

[0517] The user confirms and performs the task (e.g., walk 10,000 steps).

[0518] The device detects when the user completes a task and sends that information to the server.

[0519] The server receives the task completion information and updates the user's points.

[0520] The device will notify the user of updated points and newly earned rewards.

[0521] The user checks the points and rewards they have earned and moves on to the next task.

[0522] Specific examples

[0523] When a user starts a diet, they enter the initial data into the app: "Current weight: 70 kg, target weight: 60 kg, eating habits: three meals a day, exercise habits: three times a week." The device saves this data and sends it to the server. The server analyzes the received data and stores it in a database.

[0524] For example, if a user wears a smartwatch to record their daily exercise, the device will collect data such as the number of steps taken, heart rate, and sleep time, and send it to a server, which then stores this data in a database in real time.

[0525] To analyze the user's emotional state, the device's camera is used to capture a selfie, and the user's facial expression is analyzed to determine emotional states such as "satisfaction" or "stress." Based on the collected emotional data, the emotion engine generates a message such as, "You seem satisfied today! Keep it up!"

[0526] An example of an action suggestion using an AI model is a prompt such as, "Create an action plan for the next day based on the user's exercise and emotional data from the past seven days. For example, if the user walks an average of 5,000 steps, advise them to walk a little more." Based on the analysis results, the server generates a specific action plan for the next day and notifies the user via their device. The user confirms the notification and follows the suggested action plan.

[0527] The above system provides users with appropriate behavioral suggestions and motivational measures based on their emotional state, enabling them to diet effectively.

[0528] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0529] Step 1:

[0530] A user installs a diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[0531] Input: Data about the user's weight and habits

[0532] Output: Save data to the device and prepare it for transmission to the server

[0533] Specific action: The user enters information into a form in the app and presses the submit button.

[0534] Step 2:

[0535] The terminal stores the input initial setting data in local storage and transmits it to the server.

[0536] Input: Initial setting data entered by the user

[0537] Output: Data is sent to the server

[0538] Specific operation: The device temporarily stores the data in local storage and then sends the data to a server via the Internet.

[0539] Step 3:

[0540] The server analyzes the received initial setting data and stores it in a database.

[0541] Input: Initial setting data sent from the terminal

[0542] Output: User information stored in the database

[0543] Specific operation: The server analyzes the data, associates it with the user ID, and stores it in a database.

[0544] Step 4:

[0545] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[0546] Input: Sensor data from wearable devices and smartphones

[0547] Output: Data collected in real time

[0548] What it does: The terminal collects data from devices via Bluetooth and Wi-Fi.

[0549] Step 5:

[0550] The server stores the data received in real time in a database.

[0551] Input: Real-time data sent from the device

[0552] Output: Sensor data stored in a database

[0553] Specific operation: The server receives the data, analyzes it, and stores it in the database.

[0554] Step 6:

[0555] The device analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[0556] Input: facial expression and voice data from camera and microphone

[0557] Output: Emotion data

[0558] Specific operation: The device captures the user's facial expression with a camera and analyzes the tone of the voice using voice recognition software.

[0559] Step 7:

[0560] The server analyzes the collected emotional data to determine the user's current emotional state.

[0561] Input: Emotion data sent from the device

[0562] Output: Emotional state as a result of analysis

[0563] Specific behavior: The emotion engine analyzes the data and identifies the emotional state (e.g., "happy" or "stressed").

[0564] Step 8:

[0565] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[0566] Input: Parsed emotional state

[0567] Output: Motivational messages and action suggestions

[0568] Specific action: The emotion engine generates an appropriate message (e.g., "Keep it up!").

[0569] Step 9:

[0570] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day.

[0571] Input: User data and emotion data

[0572] Output: Action plan for the next day

[0573] Specific actions: The AI ​​model analyzes the data and creates a specific action plan, such as "walk 6,000 steps the next day."

[0574] Step 10:

[0575] The device will notify the user of the proposed plan of action.

[0576] Input: Action plan sent from the server

[0577] Output: User notification

[0578] Specific behavior: The device uses the notification function to display details of the suggested action to the user.

[0579] Step 11:

[0580] The user receives a notification and acts on the proposed plan of action.

[0581] Input: Notifications from your device

[0582] Output: User actions

[0583] Specific Action: The user acknowledges the notification and acts on the suggested exercise and meal plan.

[0584] Step 12:

[0585] The user inputs data such as target weight and current weight.

[0586] Input: Data such as target weight and current weight

[0587] Output: Save data to the device and prepare it for transmission to the server

[0588] Specific action: The user enters information into a form in the app and presses the submit button.

[0589] Step 13:

[0590] The terminal transmits this data to the server.

[0591] Input: Data entered by the user

[0592] Output: Data is sent to the server

[0593] Specific operation: The device sends data to a server via the Internet.

[0594] Step 14:

[0595] The server uses image generation AI to generate an image of the user after achieving their goal.

[0596] Input: Entered target weight and current weight data

[0597] Output: The generated image

[0598] Specific operation: The image generation AI simulates what the goal will look like after it is achieved based on the input data and generates an image.

[0599] Step 15:

[0600] The device displays the generated image to the user.

[0601] Input: Image data sent from the server

[0602] Output: Image displayed to the user

[0603] Specific operation: The device displays the generated image on the screen and shows it to the user.

[0604] Step 16:

[0605] Users can visualize what they will look like after achieving their goals, which increases motivation.

[0606] Input: Displayed image

[0607] Output: Increased user motivation

[0608] Specific action: The user looks at the image and imagines themselves achieving their goal.

[0609] Step 17:

[0610] The server generates diet-related tasks and assigns points to the tasks.

[0611] Input: User data stored on the server

[0612] Output: Generated tasks and point configurations

[0613] Specific operation: The server generates tasks based on user data and assigns appropriate points.

[0614] Step 18:

[0615] The device notifies the user of the generated task and displays the task details.

[0616] Input: Task data sent from the server

[0617] Output: Task notification to user

[0618] Specific behavior: The device uses notifications to display task details to the user.

[0619] Step 19:

[0620] The user confirms and performs a task, for example, walking 10,000 steps.

[0621] Input: Task notification from the device

[0622] Output: Task accomplished

[0623] Specific Action: The user reviews the task details and takes action.

[0624] Step 20:

[0625] The device detects when the user completes a task and sends that information to the server.

[0626] Input: Completed task data

[0627] Output: Completion data sent to the server

[0628] Specific operation: The device detects the completion of the task and sends the data to the server.

[0629] Step 21:

[0630] The server receives the task completion information and updates the user's points.

[0631] Input: Completion data sent from the terminal

[0632] Output: Updated points

[0633] Specific operation: The server receives the data and updates the user points in the database.

[0634] Step 22:

[0635] The device will notify the user of updated points and newly earned rewards.

[0636] Input: Updated point data

[0637] Output: Point reward notification to user

[0638] What it does: The device uses notifications to display points and reward details to the user.

[0639] Step 23:

[0640] Check the points and rewards the user has earned and work on the next task.

[0641] Input: Points and rewards notifications

[0642] Output: Tackling new tasks

[0643] Specific action: The user checks the notification and is motivated to take on a new task.

[0644] The above are the specific processing steps of this system's program. Through this process, users are provided with appropriate behavioral suggestions and motivational measures according to their emotional state, enabling them to effectively diet.

[0645] (Application example 2)

[0646] 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."

[0647] Conventional diet support systems provided messages and suggested actions without considering the user's emotional state, making it difficult to maintain user motivation. Furthermore, in the shopping experience at physical stores, it was difficult to provide individualized support based on the user's emotions and needs, and the system did not sufficiently stimulate purchasing motivation or recommend optimal products. As a result, there were issues with diet continuity and a decrease in satisfaction with the shopping experience.

[0648] 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.

[0649] In this invention, the server includes means for recognizing the emotional state of the user and analyzing the emotional data, means for recommending products and services suitable for the user based on the emotion analysis results, and means for displaying the recommendation results according to the emotional state on the user's mobile terminal in real time. This makes it possible to provide individualized responses based on the emotional state, thereby maintaining the user's motivation and increasing their willingness to purchase.

[0650] "User initial setting data" refers to basic information (e.g., current weight, target weight, eating habits, exercise habits, etc.) that a user enters when they start using the system.

[0651] "Real-time user data" refers to current user activity data, such as exercise, sleep, and diet, obtained from wearable devices and mobile terminals.

[0652] "Means for suggesting specific actions" is a function that presents instructions and actions to users to achieve their goals based on collected and analyzed data.

[0653] "Means for notifying users" refers to a function that notifies users of suggested actions or messages on their mobile devices.

[0654] "Means for generating an image of what the user will look like after achieving their goal" is a function that uses a generative AI model to visualize what the user will look like (such as changes in weight and body shape) if they achieve their goal.

[0655] The "means for displaying the generated image to the user" is a function for displaying the predicted image after the goal is achieved on the user's mobile device.

[0656] "Means for tracking tasks and managing points" refers to a function that allows users to record the tasks they have completed and award and manage points according to their level of completion.

[0657] "Means for providing rewards to users based on point management" is a function that provides rewards and incentives based on the points that users have earned.

[0658] "Means for recognizing emotional state and analyzing emotional data" refers to a function that recognizes and analyzes the user's emotional state from facial expressions, tone of voice, etc.

[0659] "Means for recommending products and services suitable for users based on the results of emotional analysis" is a function that suggests products and services that are best suited to users based on their emotional state.

[0660] "Means for displaying recommendation results according to emotional state on the user's mobile device in real time" is a function for displaying recommendation messages generated based on emotional analysis on the user's mobile device in real time.

[0661] MODE FOR CARRYING OUT THE INVENTION

[0662] System Configuration

[0663] The present invention is implemented by a system comprising the following components:

[0664] 1. User Device

[0665] Using mobile devices such as smartphones and tablets.

[0666] 2. Server

[0667] It uses cloud servers and on-premise data servers, and mainly performs data analysis and runs AI models.

[0668] 3. Wearable devices

[0669] Use devices such as smartwatches and fitness bands to collect users' exercise and sleep data.

[0670] 4. Emotion Engine

[0671] It uses software to analyze the user's facial expressions and tone of voice to recognize their emotional state.

[0672] Program implementation procedure

[0673] 1. Collecting and storing user preference data

[0674] Users install the app and enter basic information such as their current weight, target weight, eating habits, and exercise habits when they first launch it.

[0675] The terminal stores the input initial setting data in local storage and transmits it to the server.

[0676] The server analyzes the received initial setting data and stores it in a database.

[0677] 2. Collecting and storing real-time user data

[0678] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[0679] The server stores the collected real-time data in a database.

[0680] 3. Collecting and analyzing user emotion data

[0681] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[0682] The server analyzes the collected emotional data to determine the user's current emotional state.

[0683] The emotion engine uses emotional data to generate messages to recommend products and services that are appropriate for the user.

[0684] 4. Data analysis and action proposals

[0685] The server analyzes the accumulated user data and sentiment data and uses AI models to recommend the next day's action plan and specific products.

[0686] The device will notify the user with suggested action plans and product recommendations.

[0687] 5. Goal image generation and display

[0688] The user inputs data such as their target weight and current weight.

[0689] The terminal transmits this data to the server.

[0690] The server uses a generative AI model to generate an image of what the goal will look like after it is achieved.

[0691] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[0692] 6. Implementing gamification elements

[0693] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[0694] The device will notify the user of the generated task and display the task details.

[0695] The user confirms and performs the task (e.g., walk 10,000 steps).

[0696] The device detects when the user completes a task and sends that information to the server.

[0697] The server receives the task completion information and updates the user's points.

[0698] The device will notify the user of updated points and newly earned rewards.

[0699] Specific examples

[0700] Example 1: When a user enters a physical store and launches the app, facial recognition detects fatigue and the AI ​​notifies them, "Here's a tea that will help you refresh yourself!"

[0701] Example 2: Using step count data, you can appeal to people by saying, "You haven't gotten enough exercise today. Get 20% off protein bars!"

[0702] Prompt Sentence Examples

[0703] "The user appears to be a little tired. Please recommend products that will help them feel refreshed."

[0704] "Recommend appropriate products and services based on the user's goals."

[0705] The hardware used includes smartphones and wearable devices (smartwatches, fitness bands), and the software uses cloud services (AWS Lambda, Amazon SageMaker) and mobile application software (Swift, Kotlin). The database uses Amazon RDS for efficient data management and analysis. This allows optimal action suggestions and product recommendations to be provided in real time based on the user's emotional state, improving both the purchasing experience and diet management.

[0706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0707] Step 1:

[0708] Collecting and storing user preference data

[0709] Input: The user enters basic information (current weight, target weight, dietary habits, and exercise habits) into a smartphone app.

[0710] What happens: A user installs the app and enters basic information on first launch.

[0711] Data processing: The device structures the input data and saves it in local storage. It then sends the saved data to a cloud server.

[0712] Output: The saved initial setting data is sent to the cloud server and stored in the database.

[0713] Step 2:

[0714] Collecting and storing real-time user data

[0715] Input: Exercise data (steps, heart rate, etc.), sleep data, and dietary data from the user's wearable device or smartphone.

[0716] How it works: The device collects data in real time from wearable devices and smartphones.

[0717] Data processing: Each collected data is sent to a cloud server and stored in a database.

[0718] Output: Real-time data stored in a database.

[0719] Step 3:

[0720] Collecting and analyzing user emotion data

[0721] Input: Data about the user's facial expressions and tone of voice.

[0722] How it works: The device uses the smartphone's camera and microphone to collect the user's facial expressions and tone of voice.

[0723] Data processing: The device sends the collected emotion data to a cloud server, where it is analyzed by an emotion engine.

[0724] Output: Identified user emotional state data.

[0725] Step 4:

[0726] Data analysis and action proposals

[0727] Input: Real-time user data and sentiment data.

[0728] Specific operation: The server analyzes the accumulated data using an AI model to generate an action plan for the next day and recommended products.

[0729] Data processing: Generative AI models create action suggestions and product recommendations based on past data and current emotional state.

[0730] Output: A message with suggested actions or product recommendations is generated.

[0731] Step 5:

[0732] Notification of proposed action plans or products

[0733] Input: Generated action suggestions and product recommendations.

[0734] Specific operation: The server notifies the user of the generated message on their smartphone.

[0735] Output: A notification with an action plan and product recommendations will be displayed on the user's device.

[0736] Step 6:

[0737] Goal image generation and display

[0738] Input: User's current weight, goal weight data.

[0739] Specific operation: The server inputs this data into a generative AI model and generates an image of what the robot will look like after achieving the goal.

[0740] Data processing: Images are generated using an AI model and sent from the cloud server to the device.

[0741] Output: The generated image is displayed on the user's device.

[0742] Step 7:

[0743] Implementing gamification elements

[0744] Input: Diet-related tasks and point settings.

[0745] Specific operation: The server generates diet tasks and assigns points to each one.

[0746] Data processing: Each task and point information is saved on the cloud server.

[0747] Output: The task and points are notified to the user's device, and the user completes the task and earns points.

[0748] Step 8:

[0749] Points management and rewards

[0750] Input: Data of the task that the user completed.

[0751] Specific operation: The device sends task completion information to the cloud server and updates points.

[0752] Data processing: The server analyzes the task completion data, updates the user's points, and generates reward information.

[0753] Output: The updated points and rewards are notified to the user's device.

[0754] This series of processes enables personalized action suggestions and product recommendations based on the user's emotional state and real-time data.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] [Second embodiment]

[0759] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0760] 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.

[0761] 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).

[0762] 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.

[0763] 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.

[0764] 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).

[0765] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] In the smart glasses 214, 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.

[0770] 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."

[0771] The present invention is a system that uses AI to support the user's dieting process and is designed to allow the user to continue dieting in an enjoyable manner. The following describes an embodiment of the system.

[0772] System configuration

[0773] This system mainly consists of the following components:

[0774] 1. User device: A device such as a smartphone or tablet.

[0775] 2. Server: Cloud server or on-premise data server.

[0776] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0777] Program processing

[0778] Collecting and storing user preference data

[0779] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[0780] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[0781] Server: Saves the received initial setting data in a database.

[0782] Collecting and storing real-time user data

[0783] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[0784] Server: Stores the data received in real time in a database.

[0785] Data analysis and action proposals

[0786] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[0787] Terminal: Notify user of proposed plan of action.

[0788] Users: Get notified and take action.

[0789] Goal image generation and display

[0790] User: Enters data such as target weight and current weight.

[0791] Terminal: Sends these data to the server.

[0792] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[0793] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[0794] Users: Visualize themselves after achieving their goals and increase motivation.

[0795] Implementing gamification elements

[0796] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[0797] Terminal: Notifies the user of tasks and tracks task progress.

[0798] User: When a user completes a task, the information is sent to the server and points are added.

[0799] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[0800] Terminal: Shows reward details and points progress to users.

[0801] These features allow users to continue their daily exercise and dietary management in an enjoyable way, and maintain motivation to achieve their goals. Furthermore, the system is designed to incorporate a competitive element, allowing users to encourage each other as they diet. In this way, it provides an efficient system that can comprehensively solve dieting challenges.

[0802] The processing flow will be explained below.

[0803] Step 1:

[0804] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[0805] Step 2:

[0806] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[0807] Step 3:

[0808] Device: Sends saved initial setting data to the server.

[0809] Step 4:

[0810] Server: Analyzes the received initial setting data and stores it in a database.

[0811] Step 5:

[0812] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[0813] Step 6:

[0814] Terminal: Sends collected real-time data to the server.

[0815] Step 7:

[0816] Server: Stores the data received in real time in a database and checks the integrity of the data.

[0817] Step 8:

[0818] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[0819] Step 9:

[0820] Server: Based on the results of the AI ​​analysis, it generates specific action suggestions for the user (e.g., walk 6,000 steps).

[0821] Step 10:

[0822] Device: Notify the user of the proposed plan of action and display details on the screen.

[0823] Step 11:

[0824] Users: Receive notifications and act on proposed action plans.

[0825] Step 12:

[0826] User: Enters data such as target weight and current weight, as well as a current photo.

[0827] Step 13:

[0828] Terminal: Sends the entered data to the server.

[0829] Step 14:

[0830] Server: Using image generation AI, generate what the user will look like when they achieve their target weight.

[0831] Step 15:

[0832] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[0833] Step 16:

[0834] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[0835] Step 17:

[0836] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[0837] Step 18:

[0838] Terminal: Notifies the user of the generated task and displays the task details.

[0839] Step 19:

[0840] User: Confirms and executes the task (e.g., walk 10,000 steps).

[0841] Step 20:

[0842] Terminal: Detects when the user completes a task and sends that information to the server.

[0843] Step 21:

[0844] Server: Receives task completion information and updates user points.

[0845] Step 22:

[0846] Terminal: Notify users of updated points and newly earned rewards.

[0847] Step 23:

[0848] User: Check the points and rewards earned and work on the next task.

[0849] This allows users to continue their daily exercise and dietary management while having fun, and maintain their motivation. Users can also compete with other users to earn points, further increasing motivation.

[0850] Example 1

[0851] 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."

[0852] Conventional diet support systems have the problem of making it difficult for users to continue dieting. Specifically, it is difficult to efficiently collect and store the user's initial setting data and real-time data, and to make appropriate action suggestions based on that data. In addition, there is a lack of a way to visually show the effectiveness of the action suggestions, making it difficult to maintain the user's motivation. Furthermore, there is a need for a system that can provide users with continuous diet support by incorporating game elements.

[0853] 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.

[0854] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goal, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goal, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, means for verifying the accuracy of the real-time data, means for using an AI model to generate a suggested action plan, and means for generating an appearance after achieving the goal using an image generation AI model based on the user's data, which enables the user to enjoy and continue dieting and easily maintain motivation to achieve their goal.

[0855] "Means for collecting and saving user initial setting data" refers to a function that saves basic information entered by the user, such as weight, target weight, eating habits, and exercise habits, on the device and sends that data to the server.

[0856] "Means for collecting and storing real-time user data" refers to a function that allows a device to obtain data such as exercise, sleep, and diet from sensors in wearable devices and smartphones and send it to a server.

[0857] "Means for analyzing collected data and suggesting specific actions to achieve the user's goals" refers to a function that allows the server to analyze accumulated user data and use an AI model to generate an action plan appropriate for the user.

[0858] "Means for notifying the user of suggested actions" refers to push notifications or in-app notifications that inform the user of suggested actions received by the device from the server.

[0859] The "means for generating an image of what the user will look like after achieving their goal" is a function that allows the server to use an image generation AI model based on the user's goal data to generate an image of the user after achieving their goal.

[0860] The "means for displaying the generated image to the user" is a function that enables the terminal to display the image generated by the server to the user.

[0861] "Means for tracking tasks completed by users and managing points" is a function that allows the server to record the task completion status of users and reflect it in the point system.

[0862] The "means for providing rewards to users based on point management" is a function that allows the server to set rewards according to the accumulated points of users and provide the rewards to the users.

[0863] "Means for verifying the accuracy of real-time data" refers to the internal processing performed by the server to verify the validity and accuracy of the real-time data received.

[0864] "Means of using AI models to generate suggested action plans" refers to the use of modern machine learning techniques to analyze user data and automatically generate next steps or exercise plans.

[0865] "A means for generating what the user's goal will look like after it has been achieved using an image generation AI model based on user data" is a function that uses AI to convert the user's goal information into visual data and provides the future image.

[0866] This invention is a system that utilizes AI technology to support users in their dieting process, and is designed to enable users to enjoyably and continuously diet. Detailed embodiments for specifically implementing this system are described below.

[0867] System configuration

[0868] The system consists of the following main components:

[0869] 1. User device: A device such as a smartphone or tablet.

[0870] 2. Server: Cloud server or on-premise data server.

[0871] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[0872] Collecting and saving initial setup data

[0873] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[0874] Example: A user inputs "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", and "Exercise 3 times a week".

[0875] 2. Terminal: The entered initial setting data is temporarily stored in local storage and then securely sent to the server using the HTTPS protocol. The software used is a lightweight database such as SQLite.

[0876] Example: Save initial setting data in local storage in a file called "usersettings.db".

[0877] 3. Server: The server stores the received initial configuration data in an RDBMS (e.g., MySQL or PostgreSQL).

[0878] Example: Execute an INSERT statement to store data in the "UserSettings" table in the database.

[0879] Real-time data collection and storage

[0880] 1. Device: The device periodically collects exercise, sleep, dietary data, etc. from sensors in wearable devices and smartphones.

[0881] Example: Obtaining step count and heart rate data from a smartwatch via Bluetooth.

[0882] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[0883] Example: Validating data to ensure it is valid before saving it to the database.

[0884] Data analysis and action proposals

[0885] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model using Python's TensorFlow or PyTorch.

[0886] Example: Generate a suggestion such as "Walk 6000 steps tomorrow" based on data from the past 7 days. An example prompt is as follows:

[0887] "Generate exercise suggestions for the user for the next day based on their exercise data from the past seven days. For example, a suggestion like 'Walk 6,000 steps tomorrow.'"

[0888] 2. On the device: Notify the user of the proposed action plan via push notification.

[0889] Example: A message appears in the notification bar on your smartphone saying, "Walk 6,000 steps tomorrow."

[0890] Goal image generation and display

[0891] 1. User: Enter data such as target weight and current weight.

[0892] Example: A user inputs weight data "Current weight: 70 kg" and "Target weight: 60 kg".

[0893] 2. Terminal: Sends these data to the server.

[0894] 3. Server: Using image generation AI (such as Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[0895] Example: An image generation AI model generates "what it will look like when it weighs 60 kg." The prompt is as follows:

[0896] "The user's current weight is 70 kg, and their target weight is 60 kg. Based on this information, please generate an image of what the user will look like when they reach 60 kg."

[0897] 4. Terminal: displays the generated image to the user.

[0898] Implementing gamification elements

[0899] 1. Server: Generates diet-related tasks and assigns points based on the tasks.

[0900] Example: The server sets a task: "Walk 10,000 steps to get 10 points."

[0901] 2. Device: Notifies the user of tasks and tracks task progress in real time.

[0902] 3. User: When a task is completed, points are earned and the information is sent to the server.

[0903] Example: After a user walks 10,000 steps, the app reports "task completed."

[0904] 4. Server: Manages points and provides rewards based on accumulated points.

[0905] 5. Terminal: Shows rewards and points progress to users.

[0906] Example: Displaying "100 points reached! New rewards earned!" on the in-app dashboard.

[0907] In this way, users can continue their daily exercise and diet management in an enjoyable way and stay motivated to achieve their goals. Also, by incorporating an element of competition with other users, an efficient system is provided where users can encourage each other while dieting.

[0908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0909] Step 1:

[0910] Collecting and storing user preference data

[0911] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when first launched.

[0912] Input: The user enters the following information into a form: "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", "Exercise 3 times a week".

[0913] Output: The input data is saved in the app.

[0914] 2. Terminal: The entered initial setting data is temporarily saved in local storage and sent to the server using the HTTPS protocol.

[0915] What happens: The app saves the data and sends it to the server via a web request.

[0916] Input: Initial configuration data obtained from the user.

[0917] Output: Initial configuration data sent to the server.

[0918] 3. Server: The server stores the received initial setting data in an RDBMS (such as MySQL or PostgreSQL).

[0919] Specific operation: The INSERT statement is executed on the server side and the data is stored in the "UserSettings" table.

[0920] Input: Initialization data sent from the terminal.

[0921] Output: Initial configuration data stored in the database.

[0922] Step 2:

[0923] Real-time data collection and storage

[0924] 1. Device: The device periodically collects exercise, sleep, and dietary data from sensors in wearable devices and smartphones.

[0925] Specific operation: Obtain data from smartwatch via Bluetooth.

[0926] Input: Real-time data from wearable devices.

[0927] Output: Collected data is saved to the device.

[0928] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[0929] What it does: Validates data accuracy using validation algorithms and filters out invalid data.

[0930] Input: Real-time data sent from the device.

[0931] Output: The validated data is saved in the database.

[0932] Step 3:

[0933] Data analysis and action proposals

[0934] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model (TensorFlow or PyTorch).

[0935] How it works: The AI ​​model performs predictions using a Python script.

[0936] Input: Last 7 days of user data stored in the database.

[0937] Output: Suggested action for the next day (e.g., "Walk 6,000 steps tomorrow").

[0938] 2. On the device: Notify the user of the proposed action plan via push notification.

[0939] Specific action: Proposals are notified using the smartphone's notification function.

[0940] Input: Action suggestions from the server.

[0941] Output: The notification message that will be displayed on the user's smartphone.

[0942] Step 4:

[0943] Goal image generation and display

[0944] 1. User: Enter data such as target weight and current weight.

[0945] Specific action: Enter data into a form within the app.

[0946] Input: User's weight data (e.g. current weight 70kg, target weight 60kg).

[0947] Output: Weight data stored on the device.

[0948] 2. Terminal: Sends these data to the server.

[0949] Specific operation: Issue an HTTPS request and send data to the server.

[0950] Input: User's weight data.

[0951] Output: Weight data sent to the server.

[0952] 3. Server: Using image generation AI (Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[0953] Specific operation: Calls the AI ​​model and executes the image generation process.

[0954] Input: User's weight data.

[0955] Output: The generated goal image.

[0956] 4. Terminal: displays the generated image to the user.

[0957] Specific behavior: Display an image within the app.

[0958] Input: Generated image sent from the server.

[0959] Output: The generated image displayed on a smartphone.

[0960] Step 5:

[0961] Implementing gamification elements

[0962] 1. Server: Generates diet-related tasks and sets points.

[0963] Specific operation: Run the task generation algorithm and add a new task to the database.

[0964] Input: User's exercise data.

[0965] Output: The generated tasks.

[0966] 2. Terminal: Notifies the user of tasks and tracks progress.

[0967] Specific action: Use the smartphone's notification function to notify you of the task.

[0968] Input: Task data sent from the server.

[0969] Output: Task notification.

[0970] 3. User: When a task is completed, points are earned and the information is sent to the server.

[0971] Specific action: Tap the "Complete Task" button within the app to earn points.

[0972] Input: User's task completion information.

[0973] Output: Completion information sent to the server.

[0974] 4. Server: Manages points and provides rewards.

[0975] Specific operation: Calculate rewards using a points management system and provide them to users.

[0976] Input: The user's accumulated points.

[0977] Output: The reward offered.

[0978] 5. Terminal: Shows rewards and points progress to users.

[0979] Specific behavior: Display rewards and points on the in-app dashboard.

[0980] Input: Points and rewards data sent from the server.

[0981] Output: Progress displayed on the user's smartphone.

[0982] (Application example 1)

[0983] 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."

[0984] Conventional diet support systems make it difficult for users to maintain motivation to continue daily exercise and diet management, and there are no systems that can support specific diet action plans or meal optimization. Furthermore, there is a lack of specific support to increase the success rate of dieting by proposing meal menus suitable for users and making them easy to order. This creates a challenge for users, making it difficult to diet in a planned and effective manner.

[0985] 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.

[0986] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, and means for suggesting optimal meal menus based on the user's exercise and dietary status and allowing the user to order those meals. This enables the user to effectively and continuously manage their daily exercise and diet, thereby increasing the success rate of their diet. Furthermore, the ability to easily order appropriate meal menus supports the user in improving their dietary habits and makes their overall dieting efforts more efficient.

[0987] "User's initial setting data" refers to basic information that the user inputs when launching the diet support system for the first time, and includes current weight, target weight, eating habits, and exercise habits.

[0988] "User real-time data" refers to data on a user's daily exercise and dietary habits collected in real time from devices such as wearable devices and smartphones.

[0989] The "means of analysis and suggestion" is a system that analyzes the collected initial setting data and real-time data of the user and suggests specific action plans and meal menus to help the user achieve their goals.

[0990] "Means for notifying actions" refers to a function that notifies the user of suggested action plans and meal menus on their smartphone or other device.

[0991] The "image generation means" is a system that uses AI image generation technology to predict what the user will look like after achieving their target weight and generates an image of that prediction.

[0992] The "image display means" is a function that displays on the terminal the image of the user after achieving the generated target weight.

[0993] A "task tracking tool" is a system that tracks whether a user has carried out an action plan or suggested meal menu and records their progress.

[0994] The "point management means" is a system that grants and manages points based on the tasks that users complete, and provides rewards to users based on those points.

[0995] The "meal menu suggestion method" is a system in which AI suggests the optimal meal menu based on the user's exercise and eating habits, and notifies the user of the suggested menu.

[0996] The "Meal Ordering Method" is a system that allows users to easily order suggested meal menus, and is a function that connects with nearby affiliated restaurants and delivery services.

[0997] This invention is a system that uses AI to support users in their dieting. This system proposes optimal meal menus based on the user's exercise and eating habits, and allows them to easily order them, thereby providing effective and continuous support for the user's diet.

[0998] System configuration

[0999] This system consists of the following main components:

[1000] 1. User device: The device used by the user, such as a smartphone or tablet.

[1001] 2. Server: A cloud server that stores and analyzes collected data.

[1002] 3. Wearable devices: Devices that collect user exercise and sleep data (e.g., smartwatches).

[1003] Program processing

[1004] Collecting and storing user preference data

[1005] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1006] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[1007] Server: Saves the received initial setting data in a database.

[1008] Collecting and storing real-time user data

[1009] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[1010] Server: Stores the data received in real time in a database.

[1011] Data analysis and action proposals

[1012] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[1013] Terminal: Notify user of proposed plan of action.

[1014] Users: Get notified and take action.

[1015] Goal image generation and display

[1016] User: Enters data such as target weight and current weight.

[1017] Terminal: Sends these data to the server.

[1018] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1019] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[1020] Users: Visualize themselves after achieving their goals and increase motivation.

[1021] Implementing gamification elements

[1022] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[1023] Terminal: Notifies the user of tasks and tracks task progress.

[1024] User: When a user completes a task, the information is sent to the server and points are added.

[1025] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[1026] Terminal: Shows reward details and points progress to users.

[1027] Hardware and software used

[1028] This system uses the following hardware and software.

[1029] Hardware: Smartphones (iPhone, Android), wearable devices (Apple Watch, Fitbit)

[1030] Software: AWS Lambda, Amazon RDS, Firebase, TensorFlow, React Native

[1031] Specific examples

[1032] 1. When the user does the initial setup:

[1033] Users open the app on their smartphone and enter their current weight, goal weight, dietary habits, and exercise habits as initial settings. The entered data is then sent to a cloud server.

[1034] 2. When collecting data:

[1035] Real-time exercise and sleep data is collected through the wearable device and sent to a server via a smartphone.

[1036] 3. When AI suggests a meal:

[1037] An AI model on the server analyzes the user's exercise and eating habits and suggests the optimal meal menu for the next day.

[1038] 4. When the user receives the suggestion:

[1039] The suggested meal menu will be sent to the user's smartphone, allowing them to order meals directly from affiliated restaurants or delivery services.

[1040] Prompt Sentence Examples

[1041] "Recommend next day's meal plans based on the user's calorie consumption data and eating habits. Show the best choices for the user's weight goal."

[1042] The above is a specific embodiment for carrying out the present invention. This system allows users to continue dieting effectively and enjoyably, and achieve their goals.

[1043] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1044] Step 1: Collect and store user preference data

[1045] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1046] Input: Initial setting data (current weight, target weight, eating habits, exercise habits)

[1047] Output: Save data to local storage and send to server

[1048] What happens: A user opens the app on their phone and enters the required information into the designated input fields.

[1049] Step 2: Collect and store real-time user data

[1050] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[1051] Input: Exercise, sleep, and diet data from wearable devices

[1052] Output: Data sent to the server in real time

[1053] How it works: The smartphone periodically collects data from the wearable device and uploads it to a server.

[1054] Step 3: Analyze the data and develop an action plan

[1055] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[1056] Input: User initial setting data, real-time data history

[1057] Output: A concrete action plan (e.g., "Let's walk 6,000 steps tomorrow")

[1058] How it works: The AI ​​model on the server analyzes past data and generates an optimal plan of action for the next day.

[1059] Step 4: Communicate your action plan

[1060] Terminal: Notify user of proposed plan of action.

[1061] Input: AI-generated action plan

[1062] Output: Action plan notified to smartphone

[1063] How it works: Once the server generates an action plan, it pushes it to the user's smartphone.

[1064] Step 5: User Action

[1065] Users: Get notified and take action.

[1066] Input: Notified Action Plan

[1067] Output: Perform an action (e.g., walk 6000 steps)

[1068] Action: The user checks the notification on their smartphone and performs the indicated action.

[1069] Step 6: Generate and display the goal image

[1070] User: Enters data such as target weight and current weight.

[1071] Input: Target weight and current weight

[1072] Output: Data sent to the server

[1073] How it works: The user enters their goal weight and current weight in the app and sends them to the server.

[1074] Step 7: Generate images

[1075] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1076] Input: Target weight and current weight

[1077] Output: The generated goal image

[1078] How it works: The image generation AI on the server generates the user's goal image based on the input data.

[1079] Step 8: Displaying the image

[1080] Terminal: Displays the generated image to the user.

[1081] Input: Generated goal image

[1082] Output: Goal image displayed on a smartphone

[1083] Operation: The generated image is downloaded to a smartphone and displayed.

[1084] Step 9: Task Tracking and Points Management

[1085] Terminal: Tracks the tasks completed by the user and sends them to the server.

[1086] Input: Completed task data

[1087] Output: Task data sent to the server

[1088] How it works: When a user completes a task, their smartphone sends the information to a server.

[1089] Step 10: Awarding points

[1090] Server: Manages points and provides rewards when users reach a certain number of points.

[1091] Input: Task data and point management data

[1092] Output: Reward provided to user

[1093] How it works: The server calculates points based on tracking data and provides rewards.

[1094] Step 11: Meal suggestions

[1095] Server: AI suggests optimal meal menus based on the user's exercise and eating habits.

[1096] Input: Exercise status, diet status, user goals

[1097] Output: Suggested meal menu

[1098] How it works: The AI ​​on the server analyzes the data and generates a meal menu suitable for the user.

[1099] Step 12: Notification of proposed menu and ordering

[1100] Device: Providing users with menu suggestions and allowing them to order meals from partner restaurants and delivery services.

[1101] Input: Suggested meal menu

[1102] Output: Notification to user's smartphone, order process

[1103] How it works: The suggested meal menu is sent to the user's smartphone, and once the user confirms the order, an order is placed with the partner service.

[1104] 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.

[1105] The present invention adds a system that recognizes the user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The following describes in detail the embodiments of the present invention.

[1106] System configuration

[1107] This system consists of the following components:

[1108] 1. User device: A device such as a smartphone or tablet.

[1109] 2. Server: Cloud server or on-premise data server.

[1110] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1111] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[1112] Program processing

[1113] Collecting and storing user preference data

[1114] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1115] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[1116] Server: Analyzes the received initial setting data and stores it in a database.

[1117] Collecting and storing real-time user data

[1118] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[1119] Server: Stores the data received in real time in a database.

[1120] Collecting and analyzing user emotion data

[1121] Device: Analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[1122] Server: Analyzes the collected emotional data and identifies the user's current emotional state.

[1123] Emotion engine: Generates messages and suggested actions based on emotional data to improve user motivation.

[1124] Data analysis and action proposals

[1125] Server: Analyzes accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, based on data and emotional data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[1126] Terminal: Notify user of proposed plan of action.

[1127] Users: Receive notifications and act on proposed action plans.

[1128] Goal image generation and display

[1129] User: Enters data such as target weight and current weight.

[1130] Terminal: Sends these data to the server.

[1131] Server: Uses image generation AI to generate an image of the user after achieving their goal.

[1132] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[1133] Users: Visualize themselves after achieving their goals and increase motivation.

[1134] Implementing gamification elements

[1135] Server: Generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[1136] Terminal: Notifies the user of the generated task and displays the task details.

[1137] User: Confirms and executes the task (e.g., walk 10,000 steps).

[1138] Terminal: Detects when the user completes a task and sends that information to the server.

[1139] Server: Receives task completion information and updates user points.

[1140] Terminal: Notify users of updated points and newly earned rewards.

[1141] User: Check the points and rewards earned and work on the next task.

[1142] This allows users to continue their daily exercise and diet management while having fun, and maintain their motivation. They can also compete with other users to earn points, which further increases motivation. With the introduction of an emotion engine, users can receive optimal action suggestions that take their emotional state into consideration, allowing them to diet more effectively.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[1146] Step 2:

[1147] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[1148] Step 3:

[1149] Device: Sends saved initial setting data to the server.

[1150] Step 4:

[1151] Server: Analyzes the received initial setting data and stores it in a database.

[1152] Step 5:

[1153] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[1154] Step 6:

[1155] Terminal: Sends collected real-time data to the server.

[1156] Step 7:

[1157] Server: Stores the data received in real time in a database and checks the integrity of the data.

[1158] Step 8:

[1159] Device: Uses the user's camera and microphone to collect emotional data in real time from facial expressions and tone of voice.

[1160] Step 9:

[1161] Terminal: Sends collected emotion data to the server.

[1162] Step 10:

[1163] Server: Analyzes the received emotion data and identifies the user's emotional state.

[1164] Step 11:

[1165] Server: Based on accumulated user data and emotional data, the AI ​​model is used to create the next day's action plan. For example, based on the data and emotional data from the past seven days, it generates a suggestion such as "Walk 6,000 steps the next day."

[1166] Step 12:

[1167] Server: Based on the analysis results, it adjusts specific action suggestions according to the user's emotional state.

[1168] Step 13:

[1169] Device: Notifies the user of the proposed action plan and emotion-based adjustments, displaying details on the screen.

[1170] Step 14:

[1171] Users: Receive notifications and act on proposed action plans.

[1172] Step 15:

[1173] User: Enter data such as target weight, current weight, and photo.

[1174] Step 16:

[1175] Terminal: Sends the entered data to the server.

[1176] Step 17:

[1177] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1178] Step 18:

[1179] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[1180] Step 19:

[1181] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[1182] Step 20:

[1183] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[1184] Step 21:

[1185] Terminal: Notifies the user of the generated task and displays the task details.

[1186] Step 22:

[1187] User: Confirms and executes the task (e.g., walk 10,000 steps).

[1188] Step 23:

[1189] Terminal: Detects when the user completes a task and sends that information to the server.

[1190] Step 24:

[1191] Server: Receives task completion information and updates user points.

[1192] Step 25:

[1193] Terminal: Notify users of updated points and newly earned rewards.

[1194] Step 26:

[1195] User: Check the points and rewards earned and work on the next task.

[1196] Example 2

[1197] 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."

[1198] Conventional diet management systems were unable to take into account the user's emotional state, leading to a decline in motivation. Furthermore, behavioral suggestions and goal setting were general, without providing appropriate suggestions based on individual data, making it difficult to diet effectively. Furthermore, they lacked the functionality to provide users with a concrete image of what it would be like to achieve their goals, making it difficult to maintain sustained motivation.

[1199] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1200] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for collecting and analyzing emotional data, means for generating messages and suggested actions to improve motivation based on the emotional data, means for generating an image of what the user will look like after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, and means for providing rewards to the user based on the point management. This makes it possible to provide appropriate suggested actions and motivational measures according to the user's emotional state, thereby supporting effective dieting.

[1201] "Means for collecting and storing user initial setting data" refers to a function that collects basic information such as weight, target weight, eating habits, and exercise habits that a user enters when using the diet management system for the first time, and stores this information in local storage and on the server.

[1202] "Means for collecting and storing real-time user data" refers to a function that collects data on exercise, sleep, diet, etc. obtained from the user's wearable device or smartphone in real time and stores it on a server.

[1203] "Means of analyzing collected data and suggesting specific actions to help users achieve their goals" refers to a function that uses AI models and algorithms based on collected data to generate and suggest specific actions, such as individual exercise plans and meal suggestions for each user.

[1204] "Means for notifying the user of the proposed action" is a function that notifies the user of the generated action suggestion on the user's device such as a smartphone or tablet.

[1205] "Means for collecting and analyzing emotional data" refers to a function that uses the user's camera or microphone to collect facial expressions and tone of voice, and analyzes this to identify the user's emotional state.

[1206] The "means for generating messages and suggested actions to improve motivation based on emotional data" is a function that generates messages and suggested actions to improve motivation, taking into account the user's emotional state, based on analyzed emotional data.

[1207] The "means for generating an image of what the user will look like after achieving their goal" is a function that uses the user's current weight and target weight as input data to generate an image of what the user will look like after achieving their goal.

[1208] "Means for displaying the generated image to the user" refers to a function that displays the generated image of the user after achieving the goal on a device such as a smartphone or tablet.

[1209] "A means for tracking tasks completed by users and managing points" refers to a function that detects exercise- and diet-related tasks that users have completed and assigns and manages the corresponding points.

[1210] The "means for providing rewards to users based on point management" is a function for providing rewards based on points earned by users.

[1211] MODE FOR CARRYING OUT THE INVENTION

[1212] The present invention is a system that recognizes a user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The system is composed of the following components:

[1213] System configuration

[1214] 1. User device: A device such as a smartphone or tablet.

[1215] 2. Server: Cloud server or on-premise data server.

[1216] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1217] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[1218] Program processing

[1219] 1. Collecting and saving initial setup data

[1220] The user installs the diet app and inputs basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[1221] The terminal stores the collected initial setting data in a local storage and transmits it to the server.

[1222] The server analyzes the received initial setting data and stores it in a database.

[1223] 2. Real-time data collection and storage

[1224] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[1225] The server stores the data received in real time in a database.

[1226] 3. Emotional Data Collection and Analysis

[1227] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[1228] The server analyzes the collected emotional data to determine the user's current emotional state.

[1229] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[1230] 4. Data analysis and action proposals

[1231] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, it generates a suggestion such as "walk 6,000 steps the next day" based on the data and emotional data from the past seven days.

[1232] The device notifies the user of the proposed plan of action.

[1233] The user receives a notification and acts on the proposed plan of action.

[1234] 5. Goal image generation and display

[1235] The user inputs data such as a target weight and current weight.

[1236] The terminal transmits this data to the server.

[1237] The server uses image generation AI to generate an image of the user after achieving their goal.

[1238] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[1239] Users can visualize themselves after achieving their goals, which increases motivation.

[1240] 6. Implementing gamification elements

[1241] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[1242] The terminal notifies the user of the created task and displays the task details.

[1243] The user confirms and performs the task (e.g., walk 10,000 steps).

[1244] The device detects when the user completes a task and sends that information to the server.

[1245] The server receives the task completion information and updates the user's points.

[1246] The device will notify the user of updated points and newly earned rewards.

[1247] The user checks the points and rewards they have earned and moves on to the next task.

[1248] Specific examples

[1249] When a user starts a diet, they enter the initial data into the app: "Current weight: 70 kg, target weight: 60 kg, eating habits: three meals a day, exercise habits: three times a week." The device saves this data and sends it to the server. The server analyzes the received data and stores it in a database.

[1250] For example, if a user wears a smartwatch to record their daily exercise, the device will collect data such as the number of steps taken, heart rate, and sleep time, and send it to a server, which then stores this data in a database in real time.

[1251] To analyze the user's emotional state, the device's camera is used to capture a selfie, and the user's facial expression is analyzed to determine emotional states such as "satisfaction" or "stress." Based on the collected emotional data, the emotion engine generates a message such as, "You seem satisfied today! Keep it up!"

[1252] An example of an action suggestion using an AI model is a prompt such as, "Create an action plan for the next day based on the user's exercise and emotional data from the past seven days. For example, if the user walks an average of 5,000 steps, advise them to walk a little more." Based on the analysis results, the server generates a specific action plan for the next day and notifies the user via their device. The user confirms the notification and follows the suggested action plan.

[1253] The above system provides users with appropriate behavioral suggestions and motivational measures based on their emotional state, enabling them to diet effectively.

[1254] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1255] Step 1:

[1256] A user installs a diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[1257] Input: Data about the user's weight and habits

[1258] Output: Save data to the device and prepare it for transmission to the server

[1259] Specific action: The user enters information into a form in the app and presses the submit button.

[1260] Step 2:

[1261] The terminal stores the input initial setting data in local storage and transmits it to the server.

[1262] Input: Initial setting data entered by the user

[1263] Output: Data is sent to the server

[1264] Specific operation: The device temporarily stores the data in local storage and then sends the data to a server via the Internet.

[1265] Step 3:

[1266] The server analyzes the received initial setting data and stores it in a database.

[1267] Input: Initial setting data sent from the terminal

[1268] Output: User information stored in the database

[1269] Specific operation: The server analyzes the data, associates it with the user ID, and stores it in a database.

[1270] Step 4:

[1271] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[1272] Input: Sensor data from wearable devices and smartphones

[1273] Output: Data collected in real time

[1274] What it does: The terminal collects data from devices via Bluetooth and Wi-Fi.

[1275] Step 5:

[1276] The server stores the data received in real time in a database.

[1277] Input: Real-time data sent from the device

[1278] Output: Sensor data stored in a database

[1279] Specific operation: The server receives the data, analyzes it, and stores it in the database.

[1280] Step 6:

[1281] The device analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[1282] Input: facial expression and voice data from camera and microphone

[1283] Output: Emotion data

[1284] Specific operation: The device captures the user's facial expression with a camera and analyzes the tone of the voice using voice recognition software.

[1285] Step 7:

[1286] The server analyzes the collected emotional data to determine the user's current emotional state.

[1287] Input: Emotion data sent from the device

[1288] Output: Emotional state as a result of analysis

[1289] Specific behavior: The emotion engine analyzes the data and identifies the emotional state (e.g., "happy" or "stressed").

[1290] Step 8:

[1291] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[1292] Input: Parsed emotional state

[1293] Output: Motivational messages and action suggestions

[1294] Specific action: The emotion engine generates an appropriate message (e.g., "Keep it up!").

[1295] Step 9:

[1296] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day.

[1297] Input: User data and emotion data

[1298] Output: Action plan for the next day

[1299] Specific actions: The AI ​​model analyzes the data and creates a specific action plan, such as "walk 6,000 steps the next day."

[1300] Step 10:

[1301] The device will notify the user of the proposed plan of action.

[1302] Input: Action plan sent from the server

[1303] Output: User notification

[1304] Specific behavior: The device uses the notification function to display details of the suggested action to the user.

[1305] Step 11:

[1306] The user receives a notification and acts on the proposed plan of action.

[1307] Input: Notifications from your device

[1308] Output: User actions

[1309] Specific Action: The user acknowledges the notification and acts on the suggested exercise and meal plan.

[1310] Step 12:

[1311] The user inputs data such as target weight and current weight.

[1312] Input: Data such as target weight and current weight

[1313] Output: Save data to the device and prepare it for transmission to the server

[1314] Specific action: The user enters information into a form in the app and presses the submit button.

[1315] Step 13:

[1316] The terminal transmits this data to the server.

[1317] Input: Data entered by the user

[1318] Output: Data is sent to the server

[1319] Specific operation: The device sends data to a server via the Internet.

[1320] Step 14:

[1321] The server uses image generation AI to generate an image of the user after achieving their goal.

[1322] Input: Entered target weight and current weight data

[1323] Output: The generated image

[1324] Specific operation: The image generation AI simulates what the goal will look like after it is achieved based on the input data and generates an image.

[1325] Step 15:

[1326] The device displays the generated image to the user.

[1327] Input: Image data sent from the server

[1328] Output: Image displayed to the user

[1329] Specific operation: The device displays the generated image on the screen and shows it to the user.

[1330] Step 16:

[1331] Users can visualize what they will look like after achieving their goals, which increases motivation.

[1332] Input: Displayed image

[1333] Output: Increased user motivation

[1334] Specific action: The user looks at the image and imagines themselves achieving their goal.

[1335] Step 17:

[1336] The server generates diet-related tasks and assigns points to the tasks.

[1337] Input: User data stored on the server

[1338] Output: Generated tasks and point configurations

[1339] Specific operation: The server generates tasks based on user data and assigns appropriate points.

[1340] Step 18:

[1341] The device notifies the user of the generated task and displays the task details.

[1342] Input: Task data sent from the server

[1343] Output: Task notification to user

[1344] Specific behavior: The device uses notifications to display task details to the user.

[1345] Step 19:

[1346] The user confirms and performs a task, for example, walking 10,000 steps.

[1347] Input: Task notification from the device

[1348] Output: Task accomplished

[1349] Specific Action: The user reviews the task details and takes action.

[1350] Step 20:

[1351] The device detects when the user completes a task and sends that information to the server.

[1352] Input: Completed task data

[1353] Output: Completion data sent to the server

[1354] Specific operation: The device detects the completion of the task and sends the data to the server.

[1355] Step 21:

[1356] The server receives the task completion information and updates the user's points.

[1357] Input: Completion data sent from the terminal

[1358] Output: Updated points

[1359] Specific operation: The server receives the data and updates the user points in the database.

[1360] Step 22:

[1361] The device will notify the user of updated points and newly earned rewards.

[1362] Input: Updated point data

[1363] Output: Point reward notification to user

[1364] What it does: The device uses notifications to display points and reward details to the user.

[1365] Step 23:

[1366] Check the points and rewards the user has earned and work on the next task.

[1367] Input: Points and rewards notifications

[1368] Output: Tackling new tasks

[1369] Specific action: The user checks the notification and is motivated to take on a new task.

[1370] The above are the specific processing steps of this system's program. Through this process, users are provided with appropriate behavioral suggestions and motivational measures according to their emotional state, enabling them to effectively diet.

[1371] (Application example 2)

[1372] 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."

[1373] Conventional diet support systems provided messages and suggested actions without considering the user's emotional state, making it difficult to maintain user motivation. Furthermore, in the shopping experience at physical stores, it was difficult to provide individualized support based on the user's emotions and needs, and the system did not sufficiently stimulate purchasing motivation or recommend optimal products. As a result, there were issues with diet continuity and a decrease in satisfaction with the shopping experience.

[1374] 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.

[1375] In this invention, the server includes means for recognizing the emotional state of the user and analyzing the emotional data, means for recommending products and services suitable for the user based on the emotion analysis results, and means for displaying the recommendation results according to the emotional state on the user's mobile terminal in real time. This makes it possible to provide individualized responses based on the emotional state, thereby maintaining the user's motivation and increasing their willingness to purchase.

[1376] "User initial setting data" refers to basic information (e.g., current weight, target weight, eating habits, exercise habits, etc.) that a user enters when they start using the system.

[1377] "Real-time user data" refers to current user activity data, such as exercise, sleep, and diet, obtained from wearable devices and mobile terminals.

[1378] "Means for suggesting specific actions" is a function that presents instructions and actions to users to achieve their goals based on collected and analyzed data.

[1379] "Means for notifying users" refers to a function that notifies users of suggested actions or messages on their mobile devices.

[1380] "Means for generating an image of what the user will look like after achieving their goal" is a function that uses a generative AI model to visualize what the user will look like (such as changes in weight and body shape) if they achieve their goal.

[1381] The "means for displaying the generated image to the user" is a function for displaying the predicted image after the goal is achieved on the user's mobile device.

[1382] "Means for tracking tasks and managing points" refers to a function that allows users to record the tasks they have completed and award and manage points according to their level of completion.

[1383] "Means for providing rewards to users based on point management" is a function that provides rewards and incentives based on the points that users have earned.

[1384] "Means for recognizing emotional state and analyzing emotional data" refers to a function that recognizes and analyzes the user's emotional state from facial expressions, tone of voice, etc.

[1385] "Means for recommending products and services suitable for users based on the results of emotional analysis" is a function that suggests products and services that are best suited to users based on their emotional state.

[1386] "Means for displaying recommendation results according to emotional state on the user's mobile device in real time" is a function for displaying recommendation messages generated based on emotional analysis on the user's mobile device in real time.

[1387] MODE FOR CARRYING OUT THE INVENTION

[1388] System Configuration

[1389] The present invention is implemented by a system comprising the following components:

[1390] 1. User Device

[1391] Using mobile devices such as smartphones and tablets.

[1392] 2. Server

[1393] It uses cloud servers and on-premise data servers, and mainly performs data analysis and runs AI models.

[1394] 3. Wearable devices

[1395] Use devices such as smartwatches and fitness bands to collect users' exercise and sleep data.

[1396] 4. Emotion Engine

[1397] It uses software to analyze the user's facial expressions and tone of voice to recognize their emotional state.

[1398] Program implementation procedure

[1399] 1. Collecting and storing user preference data

[1400] Users install the app and enter basic information such as their current weight, target weight, eating habits, and exercise habits when they first launch it.

[1401] The terminal stores the input initial setting data in local storage and transmits it to the server.

[1402] The server analyzes the received initial setting data and stores it in a database.

[1403] 2. Collecting and storing real-time user data

[1404] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[1405] The server stores the collected real-time data in a database.

[1406] 3. Collecting and analyzing user emotion data

[1407] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[1408] The server analyzes the collected emotional data to determine the user's current emotional state.

[1409] The emotion engine uses emotional data to generate messages to recommend products and services that are appropriate for the user.

[1410] 4. Data analysis and action proposals

[1411] The server analyzes the accumulated user data and sentiment data and uses AI models to recommend the next day's action plan and specific products.

[1412] The device will notify the user with suggested action plans and product recommendations.

[1413] 5. Goal image generation and display

[1414] The user inputs data such as their target weight and current weight.

[1415] The terminal transmits this data to the server.

[1416] The server uses a generative AI model to generate an image of what the goal will look like after it is achieved.

[1417] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[1418] 6. Implementing gamification elements

[1419] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[1420] The device will notify the user of the generated task and display the task details.

[1421] The user confirms and performs the task (e.g., walk 10,000 steps).

[1422] The device detects when the user completes a task and sends that information to the server.

[1423] The server receives the task completion information and updates the user's points.

[1424] The device will notify the user of updated points and newly earned rewards.

[1425] Specific examples

[1426] Example 1: When a user enters a physical store and launches the app, facial recognition detects fatigue and the AI ​​notifies them, "Here's a tea that will help you refresh yourself!"

[1427] Example 2: Using step count data, you can appeal to people by saying, "You haven't gotten enough exercise today. Get 20% off protein bars!"

[1428] Prompt Sentence Examples

[1429] "The user appears to be a little tired. Please recommend products that will help them feel refreshed."

[1430] "Recommend appropriate products and services based on the user's goals."

[1431] The hardware used includes smartphones and wearable devices (smartwatches, fitness bands), and the software uses cloud services (AWS Lambda, Amazon SageMaker) and mobile application software (Swift, Kotlin). The database uses Amazon RDS for efficient data management and analysis. This allows optimal action suggestions and product recommendations to be provided in real time based on the user's emotional state, improving both the purchasing experience and diet management.

[1432] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1433] Step 1:

[1434] Collecting and storing user preference data

[1435] Input: The user enters basic information (current weight, target weight, dietary habits, and exercise habits) into a smartphone app.

[1436] What happens: A user installs the app and enters basic information on first launch.

[1437] Data processing: The device structures the input data and saves it in local storage. It then sends the saved data to a cloud server.

[1438] Output: The saved initial setting data is sent to the cloud server and stored in the database.

[1439] Step 2:

[1440] Collecting and storing real-time user data

[1441] Input: Exercise data (steps, heart rate, etc.), sleep data, and dietary data from the user's wearable device or smartphone.

[1442] How it works: The device collects data in real time from wearable devices and smartphones.

[1443] Data processing: Each collected data is sent to a cloud server and stored in a database.

[1444] Output: Real-time data stored in a database.

[1445] Step 3:

[1446] Collecting and analyzing user emotion data

[1447] Input: Data about the user's facial expressions and tone of voice.

[1448] How it works: The device uses the smartphone's camera and microphone to collect the user's facial expressions and tone of voice.

[1449] Data processing: The device sends the collected emotion data to a cloud server, where it is analyzed by an emotion engine.

[1450] Output: Identified user emotional state data.

[1451] Step 4:

[1452] Data analysis and action proposals

[1453] Input: Real-time user data and sentiment data.

[1454] Specific operation: The server analyzes the accumulated data using an AI model to generate an action plan for the next day and recommended products.

[1455] Data processing: Generative AI models create action suggestions and product recommendations based on past data and current emotional state.

[1456] Output: A message with suggested actions or product recommendations is generated.

[1457] Step 5:

[1458] Notification of proposed action plans or products

[1459] Input: Generated action suggestions and product recommendations.

[1460] Specific operation: The server notifies the user of the generated message on their smartphone.

[1461] Output: A notification with an action plan and product recommendations will be displayed on the user's device.

[1462] Step 6:

[1463] Goal image generation and display

[1464] Input: User's current weight, goal weight data.

[1465] Specific operation: The server inputs this data into a generative AI model and generates an image of what the robot will look like after achieving the goal.

[1466] Data processing: Images are generated using an AI model and sent from the cloud server to the device.

[1467] Output: The generated image is displayed on the user's device.

[1468] Step 7:

[1469] Implementing gamification elements

[1470] Input: Diet-related tasks and point settings.

[1471] Specific operation: The server generates diet tasks and assigns points to each one.

[1472] Data processing: Each task and point information is saved on the cloud server.

[1473] Output: The task and points are notified to the user's device, and the user completes the task and earns points.

[1474] Step 8:

[1475] Points management and rewards

[1476] Input: Data of the task that the user completed.

[1477] Specific operation: The device sends task completion information to the cloud server and updates points.

[1478] Data processing: The server analyzes the task completion data, updates the user's points, and generates reward information.

[1479] Output: The updated points and rewards are notified to the user's device.

[1480] This series of processes enables personalized action suggestions and product recommendations based on the user's emotional state and real-time data.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] [Third embodiment]

[1485] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1486] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1487] 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).

[1488] 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.

[1489] 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.

[1490] 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).

[1491] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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."

[1497] The present invention is a system that uses AI to support the user's dieting process and is designed to allow the user to continue dieting in an enjoyable manner. The following describes an embodiment of the system.

[1498] System configuration

[1499] This system mainly consists of the following components:

[1500] 1. User device: A device such as a smartphone or tablet.

[1501] 2. Server: Cloud server or on-premise data server.

[1502] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1503] Program processing

[1504] Collecting and storing user preference data

[1505] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1506] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[1507] Server: Saves the received initial setting data in a database.

[1508] Collecting and storing real-time user data

[1509] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[1510] Server: Stores the data received in real time in a database.

[1511] Data analysis and action proposals

[1512] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[1513] Terminal: Notify user of proposed plan of action.

[1514] Users: Get notified and take action.

[1515] Goal image generation and display

[1516] User: Enters data such as target weight and current weight.

[1517] Terminal: Sends these data to the server.

[1518] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1519] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[1520] Users: Visualize themselves after achieving their goals and increase motivation.

[1521] Implementing gamification elements

[1522] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[1523] Terminal: Notifies the user of tasks and tracks task progress.

[1524] User: When a user completes a task, the information is sent to the server and points are added.

[1525] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[1526] Terminal: Shows reward details and points progress to users.

[1527] These features allow users to continue their daily exercise and dietary management in an enjoyable way, and maintain motivation to achieve their goals. Furthermore, the system is designed to incorporate a competitive element, allowing users to encourage each other as they diet. In this way, it provides an efficient system that can comprehensively solve dieting challenges.

[1528] The processing flow will be explained below.

[1529] Step 1:

[1530] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[1531] Step 2:

[1532] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[1533] Step 3:

[1534] Device: Sends saved initial setting data to the server.

[1535] Step 4:

[1536] Server: Analyzes the received initial setting data and stores it in a database.

[1537] Step 5:

[1538] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[1539] Step 6:

[1540] Terminal: Sends collected real-time data to the server.

[1541] Step 7:

[1542] Server: Stores the data received in real time in a database and checks the integrity of the data.

[1543] Step 8:

[1544] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[1545] Step 9:

[1546] Server: Based on the results of the AI ​​analysis, it generates specific action suggestions for the user (e.g., walk 6,000 steps).

[1547] Step 10:

[1548] Device: Notify the user of the proposed plan of action and display details on the screen.

[1549] Step 11:

[1550] Users: Receive notifications and act on proposed action plans.

[1551] Step 12:

[1552] User: Enters data such as target weight and current weight, as well as a current photo.

[1553] Step 13:

[1554] Terminal: Sends the entered data to the server.

[1555] Step 14:

[1556] Server: Using image generation AI, generate what the user will look like when they achieve their target weight.

[1557] Step 15:

[1558] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[1559] Step 16:

[1560] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[1561] Step 17:

[1562] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[1563] Step 18:

[1564] Terminal: Notifies the user of the generated task and displays the task details.

[1565] Step 19:

[1566] User: Confirms and executes the task (e.g., walk 10,000 steps).

[1567] Step 20:

[1568] Terminal: Detects when the user completes a task and sends that information to the server.

[1569] Step 21:

[1570] Server: Receives task completion information and updates user points.

[1571] Step 22:

[1572] Terminal: Notify users of updated points and newly earned rewards.

[1573] Step 23:

[1574] User: Check the points and rewards earned and work on the next task.

[1575] This allows users to continue their daily exercise and dietary management while having fun, and maintain their motivation. Users can also compete with other users to earn points, further increasing motivation.

[1576] Example 1

[1577] 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."

[1578] Conventional diet support systems have the problem of making it difficult for users to continue dieting. Specifically, it is difficult to efficiently collect and store the user's initial setting data and real-time data, and to make appropriate action suggestions based on that data. In addition, there is a lack of a way to visually show the effectiveness of the action suggestions, making it difficult to maintain the user's motivation. Furthermore, there is a need for a system that can provide users with continuous diet support by incorporating game elements.

[1579] 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.

[1580] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goal, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goal, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, means for verifying the accuracy of the real-time data, means for using an AI model to generate a suggested action plan, and means for generating an appearance after achieving the goal using an image generation AI model based on the user's data, which enables the user to enjoy and continue dieting and easily maintain motivation to achieve their goal.

[1581] "Means for collecting and saving user initial setting data" refers to a function that saves basic information entered by the user, such as weight, target weight, eating habits, and exercise habits, on the device and sends that data to the server.

[1582] "Means for collecting and storing real-time user data" refers to a function that allows a device to obtain data such as exercise, sleep, and diet from sensors in wearable devices and smartphones and send it to a server.

[1583] "Means for analyzing collected data and suggesting specific actions to achieve the user's goals" refers to a function that allows the server to analyze accumulated user data and use an AI model to generate an action plan appropriate for the user.

[1584] "Means for notifying the user of suggested actions" refers to push notifications or in-app notifications that inform the user of suggested actions received by the device from the server.

[1585] The "means for generating an image of what the user will look like after achieving their goal" is a function that allows the server to use an image generation AI model based on the user's goal data to generate an image of the user after achieving their goal.

[1586] The "means for displaying the generated image to the user" is a function that enables the terminal to display the image generated by the server to the user.

[1587] "Means for tracking tasks completed by users and managing points" is a function that allows the server to record the task completion status of users and reflect it in the point system.

[1588] The "means for providing rewards to users based on point management" is a function that allows the server to set rewards according to the accumulated points of users and provide the rewards to the users.

[1589] "Means for verifying the accuracy of real-time data" refers to the internal processing performed by the server to verify the validity and accuracy of the real-time data received.

[1590] "Means of using AI models to generate suggested action plans" refers to the use of modern machine learning techniques to analyze user data and automatically generate next steps or exercise plans.

[1591] "A means for generating what the user's goal will look like after it has been achieved using an image generation AI model based on user data" is a function that uses AI to convert the user's goal information into visual data and provides the future image.

[1592] This invention is a system that utilizes AI technology to support users in their dieting process, and is designed to enable users to enjoyably and continuously diet. Detailed embodiments for specifically implementing this system are described below.

[1593] System configuration

[1594] The system consists of the following main components:

[1595] 1. User device: A device such as a smartphone or tablet.

[1596] 2. Server: Cloud server or on-premise data server.

[1597] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1598] Collecting and saving initial setup data

[1599] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[1600] Example: A user inputs "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", and "Exercise 3 times a week".

[1601] 2. Terminal: The entered initial setting data is temporarily stored in local storage and then securely sent to the server using the HTTPS protocol. The software used is a lightweight database such as SQLite.

[1602] Example: Save initial setting data in local storage in a file called "usersettings.db".

[1603] 3. Server: The server stores the received initial configuration data in an RDBMS (e.g., MySQL or PostgreSQL).

[1604] Example: Execute an INSERT statement to store data in the "UserSettings" table in the database.

[1605] Real-time data collection and storage

[1606] 1. Device: The device periodically collects exercise, sleep, dietary data, etc. from sensors in wearable devices and smartphones.

[1607] Example: Obtaining step count and heart rate data from a smartwatch via Bluetooth.

[1608] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[1609] Example: Validating data to ensure it is valid before saving it to the database.

[1610] Data analysis and action proposals

[1611] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model using Python's TensorFlow or PyTorch.

[1612] Example: Generate a suggestion such as "Walk 6000 steps tomorrow" based on data from the past 7 days. An example prompt is as follows:

[1613] "Generate exercise suggestions for the user for the next day based on their exercise data from the past seven days. For example, a suggestion like 'Walk 6,000 steps tomorrow.'"

[1614] 2. On the device: Notify the user of the proposed action plan via push notification.

[1615] Example: A message appears in the notification bar on your smartphone saying, "Walk 6,000 steps tomorrow."

[1616] Goal image generation and display

[1617] 1. User: Enter data such as target weight and current weight.

[1618] Example: A user inputs weight data "Current weight: 70 kg" and "Target weight: 60 kg".

[1619] 2. Terminal: Sends these data to the server.

[1620] 3. Server: Using image generation AI (such as Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[1621] Example: An image generation AI model generates "what it will look like when it weighs 60 kg." The prompt is as follows:

[1622] "The user's current weight is 70 kg, and their target weight is 60 kg. Based on this information, please generate an image of what the user will look like when they reach 60 kg."

[1623] 4. Terminal: displays the generated image to the user.

[1624] Implementing gamification elements

[1625] 1. Server: Generates diet-related tasks and assigns points based on the tasks.

[1626] Example: The server sets a task: "Walk 10,000 steps to get 10 points."

[1627] 2. Device: Notifies the user of tasks and tracks task progress in real time.

[1628] 3. User: When a task is completed, points are earned and the information is sent to the server.

[1629] Example: After a user walks 10,000 steps, the app reports "task completed."

[1630] 4. Server: Manages points and provides rewards based on accumulated points.

[1631] 5. Terminal: Shows rewards and points progress to users.

[1632] Example: Displaying "100 points reached! New rewards earned!" on the in-app dashboard.

[1633] In this way, users can continue their daily exercise and diet management in an enjoyable way and stay motivated to achieve their goals. Also, by incorporating an element of competition with other users, an efficient system is provided where users can encourage each other while dieting.

[1634] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1635] Step 1:

[1636] Collecting and storing user preference data

[1637] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when first launched.

[1638] Input: The user enters the following information into a form: "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", "Exercise 3 times a week".

[1639] Output: The input data is saved in the app.

[1640] 2. Terminal: The entered initial setting data is temporarily saved in local storage and sent to the server using the HTTPS protocol.

[1641] What happens: The app saves the data and sends it to the server via a web request.

[1642] Input: Initial configuration data obtained from the user.

[1643] Output: Initial configuration data sent to the server.

[1644] 3. Server: The server stores the received initial setting data in an RDBMS (such as MySQL or PostgreSQL).

[1645] Specific operation: The INSERT statement is executed on the server side and the data is stored in the "UserSettings" table.

[1646] Input: Initialization data sent from the terminal.

[1647] Output: Initial configuration data stored in the database.

[1648] Step 2:

[1649] Real-time data collection and storage

[1650] 1. Device: The device periodically collects exercise, sleep, and dietary data from sensors in wearable devices and smartphones.

[1651] Specific operation: Obtain data from smartwatch via Bluetooth.

[1652] Input: Real-time data from wearable devices.

[1653] Output: Collected data is saved to the device.

[1654] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[1655] What it does: Validates data accuracy using validation algorithms and filters out invalid data.

[1656] Input: Real-time data sent from the device.

[1657] Output: The validated data is saved in the database.

[1658] Step 3:

[1659] Data analysis and action proposals

[1660] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model (TensorFlow or PyTorch).

[1661] How it works: The AI ​​model performs predictions using a Python script.

[1662] Input: Last 7 days of user data stored in the database.

[1663] Output: Suggested action for the next day (e.g., "Walk 6,000 steps tomorrow").

[1664] 2. On the device: Notify the user of the proposed action plan via push notification.

[1665] Specific action: Proposals are notified using the smartphone's notification function.

[1666] Input: Action suggestions from the server.

[1667] Output: The notification message that will be displayed on the user's smartphone.

[1668] Step 4:

[1669] Goal image generation and display

[1670] 1. User: Enter data such as target weight and current weight.

[1671] Specific action: Enter data into a form within the app.

[1672] Input: User's weight data (e.g. current weight 70kg, target weight 60kg).

[1673] Output: Weight data stored on the device.

[1674] 2. Terminal: Sends these data to the server.

[1675] Specific operation: Issue an HTTPS request and send data to the server.

[1676] Input: User's weight data.

[1677] Output: Weight data sent to the server.

[1678] 3. Server: Using image generation AI (Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[1679] Specific operation: Calls the AI ​​model and executes the image generation process.

[1680] Input: User's weight data.

[1681] Output: The generated goal image.

[1682] 4. Terminal: displays the generated image to the user.

[1683] Specific behavior: Display an image within the app.

[1684] Input: Generated image sent from the server.

[1685] Output: The generated image displayed on a smartphone.

[1686] Step 5:

[1687] Implementing gamification elements

[1688] 1. Server: Generates diet-related tasks and sets points.

[1689] Specific operation: Run the task generation algorithm and add a new task to the database.

[1690] Input: User's exercise data.

[1691] Output: The generated tasks.

[1692] 2. Terminal: Notifies the user of tasks and tracks progress.

[1693] Specific action: Use the smartphone's notification function to notify you of the task.

[1694] Input: Task data sent from the server.

[1695] Output: Task notification.

[1696] 3. User: When a task is completed, points are earned and the information is sent to the server.

[1697] Specific action: Tap the "Complete Task" button within the app to earn points.

[1698] Input: User's task completion information.

[1699] Output: Completion information sent to the server.

[1700] 4. Server: Manages points and provides rewards.

[1701] Specific operation: Calculate rewards using a points management system and provide them to users.

[1702] Input: The user's accumulated points.

[1703] Output: The reward offered.

[1704] 5. Terminal: Shows rewards and points progress to users.

[1705] Specific behavior: Display rewards and points on the in-app dashboard.

[1706] Input: Points and rewards data sent from the server.

[1707] Output: Progress displayed on the user's smartphone.

[1708] (Application example 1)

[1709] 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."

[1710] Conventional diet support systems make it difficult for users to maintain motivation to continue daily exercise and diet management, and there are no systems that can support specific diet action plans or meal optimization. Furthermore, there is a lack of specific support to increase the success rate of dieting by proposing meal menus suitable for users and making them easy to order. This creates a challenge for users, making it difficult to diet in a planned and effective manner.

[1711] 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.

[1712] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, and means for suggesting optimal meal menus based on the user's exercise and dietary status and allowing the user to order those meals. This enables the user to effectively and continuously manage their daily exercise and diet, thereby increasing the success rate of their diet. Furthermore, the ability to easily order appropriate meal menus supports the user in improving their dietary habits and makes their overall dieting efforts more efficient.

[1713] "User's initial setting data" refers to basic information that the user inputs when launching the diet support system for the first time, and includes current weight, target weight, eating habits, and exercise habits.

[1714] "User real-time data" refers to data on a user's daily exercise and dietary habits collected in real time from devices such as wearable devices and smartphones.

[1715] The "means of analysis and suggestion" is a system that analyzes the collected initial setting data and real-time data of the user and suggests specific action plans and meal menus to help the user achieve their goals.

[1716] "Means for notifying actions" refers to a function that notifies the user of suggested action plans and meal menus on their smartphone or other device.

[1717] The "image generation means" is a system that uses AI image generation technology to predict what the user will look like after achieving their target weight and generates an image of that prediction.

[1718] The "image display means" is a function that displays on the terminal the image of the user after achieving the generated target weight.

[1719] A "task tracking tool" is a system that tracks whether a user has carried out an action plan or suggested meal menu and records their progress.

[1720] The "point management means" is a system that grants and manages points based on the tasks that users complete, and provides rewards to users based on those points.

[1721] The "meal menu suggestion method" is a system in which AI suggests the optimal meal menu based on the user's exercise and eating habits, and notifies the user of the suggested menu.

[1722] The "Meal Ordering Method" is a system that allows users to easily order suggested meal menus, and is a function that connects with nearby affiliated restaurants and delivery services.

[1723] This invention is a system that uses AI to support users in their dieting. This system proposes optimal meal menus based on the user's exercise and eating habits, and allows them to easily order them, thereby providing effective and continuous support for the user's diet.

[1724] System configuration

[1725] This system consists of the following main components:

[1726] 1. User device: The device used by the user, such as a smartphone or tablet.

[1727] 2. Server: A cloud server that stores and analyzes collected data.

[1728] 3. Wearable devices: Devices that collect user exercise and sleep data (e.g., smartwatches).

[1729] Program processing

[1730] Collecting and storing user preference data

[1731] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1732] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[1733] Server: Saves the received initial setting data in a database.

[1734] Collecting and storing real-time user data

[1735] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[1736] Server: Stores the data received in real time in a database.

[1737] Data analysis and action proposals

[1738] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[1739] Terminal: Notify user of proposed plan of action.

[1740] Users: Get notified and take action.

[1741] Goal image generation and display

[1742] User: Enters data such as target weight and current weight.

[1743] Terminal: Sends these data to the server.

[1744] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1745] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[1746] Users: Visualize themselves after achieving their goals and increase motivation.

[1747] Implementing gamification elements

[1748] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[1749] Terminal: Notifies the user of tasks and tracks task progress.

[1750] User: When a user completes a task, the information is sent to the server and points are added.

[1751] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[1752] Terminal: Shows reward details and points progress to users.

[1753] Hardware and software used

[1754] This system uses the following hardware and software.

[1755] Hardware: Smartphones (iPhone, Android), wearable devices (Apple Watch, Fitbit)

[1756] Software: AWS Lambda, Amazon RDS, Firebase, TensorFlow, React Native

[1757] Specific examples

[1758] 1. When the user does the initial setup:

[1759] Users open the app on their smartphone and enter their current weight, goal weight, dietary habits, and exercise habits as initial settings. The entered data is then sent to a cloud server.

[1760] 2. When collecting data:

[1761] Real-time exercise and sleep data is collected through the wearable device and sent to a server via a smartphone.

[1762] 3. When AI suggests a meal:

[1763] An AI model on the server analyzes the user's exercise and eating habits and suggests the optimal meal menu for the next day.

[1764] 4. When the user receives the suggestion:

[1765] The suggested meal menu will be sent to the user's smartphone, allowing them to order meals directly from affiliated restaurants or delivery services.

[1766] Prompt Sentence Examples

[1767] "Recommend next day's meal plans based on the user's calorie consumption data and eating habits. Show the best choices for the user's weight goal."

[1768] The above is a specific embodiment for carrying out the present invention. This system allows users to continue dieting effectively and enjoyably, and achieve their goals.

[1769] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1770] Step 1: Collect and store user preference data

[1771] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1772] Input: Initial setting data (current weight, target weight, eating habits, exercise habits)

[1773] Output: Save data to local storage and send to server

[1774] What happens: A user opens the app on their phone and enters the required information into the designated input fields.

[1775] Step 2: Collect and store real-time user data

[1776] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[1777] Input: Exercise, sleep, and diet data from wearable devices

[1778] Output: Data sent to the server in real time

[1779] How it works: The smartphone periodically collects data from the wearable device and uploads it to a server.

[1780] Step 3: Analyze the data and develop an action plan

[1781] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[1782] Input: User initial setting data, real-time data history

[1783] Output: A concrete action plan (e.g., "Let's walk 6,000 steps tomorrow")

[1784] How it works: The AI ​​model on the server analyzes past data and generates an optimal plan of action for the next day.

[1785] Step 4: Communicate your action plan

[1786] Terminal: Notify user of proposed plan of action.

[1787] Input: AI-generated action plan

[1788] Output: Action plan notified to smartphone

[1789] How it works: Once the server generates an action plan, it pushes it to the user's smartphone.

[1790] Step 5: User Action

[1791] Users: Get notified and take action.

[1792] Input: Notified Action Plan

[1793] Output: Perform an action (e.g., walk 6000 steps)

[1794] Action: The user checks the notification on their smartphone and performs the indicated action.

[1795] Step 6: Generate and display the goal image

[1796] User: Enters data such as target weight and current weight.

[1797] Input: Target weight and current weight

[1798] Output: Data sent to the server

[1799] How it works: The user enters their goal weight and current weight in the app and sends them to the server.

[1800] Step 7: Generate images

[1801] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1802] Input: Target weight and current weight

[1803] Output: The generated goal image

[1804] How it works: The image generation AI on the server generates the user's goal image based on the input data.

[1805] Step 8: Displaying the image

[1806] Terminal: Displays the generated image to the user.

[1807] Input: Generated goal image

[1808] Output: Goal image displayed on a smartphone

[1809] Operation: The generated image is downloaded to a smartphone and displayed.

[1810] Step 9: Task Tracking and Points Management

[1811] Terminal: Tracks the tasks completed by the user and sends them to the server.

[1812] Input: Completed task data

[1813] Output: Task data sent to the server

[1814] How it works: When a user completes a task, their smartphone sends the information to a server.

[1815] Step 10: Awarding points

[1816] Server: Manages points and provides rewards when users reach a certain number of points.

[1817] Input: Task data and point management data

[1818] Output: Reward provided to user

[1819] How it works: The server calculates points based on tracking data and provides rewards.

[1820] Step 11: Meal suggestions

[1821] Server: AI suggests optimal meal menus based on the user's exercise and eating habits.

[1822] Input: Exercise status, diet status, user goals

[1823] Output: Suggested meal menu

[1824] How it works: The AI ​​on the server analyzes the data and generates a meal menu suitable for the user.

[1825] Step 12: Notification of proposed menu and ordering

[1826] Device: Providing users with menu suggestions and allowing them to order meals from partner restaurants and delivery services.

[1827] Input: Suggested meal menu

[1828] Output: Notification to user's smartphone, order process

[1829] How it works: The suggested meal menu is sent to the user's smartphone, and once the user confirms the order, an order is placed with the partner service.

[1830] 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.

[1831] The present invention adds a system that recognizes the user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The following describes in detail the embodiments of the present invention.

[1832] System configuration

[1833] This system consists of the following components:

[1834] 1. User device: A device such as a smartphone or tablet.

[1835] 2. Server: Cloud server or on-premise data server.

[1836] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1837] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[1838] Program processing

[1839] Collecting and storing user preference data

[1840] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[1841] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[1842] Server: Analyzes the received initial setting data and stores it in a database.

[1843] Collecting and storing real-time user data

[1844] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[1845] Server: Stores the data received in real time in a database.

[1846] Collecting and analyzing user emotion data

[1847] Device: Analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[1848] Server: Analyzes the collected emotional data and identifies the user's current emotional state.

[1849] Emotion engine: Generates messages and suggested actions based on emotional data to improve user motivation.

[1850] Data analysis and action proposals

[1851] Server: Analyzes accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, based on data and emotional data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[1852] Terminal: Notify user of proposed plan of action.

[1853] Users: Receive notifications and act on proposed action plans.

[1854] Goal image generation and display

[1855] User: Enters data such as target weight and current weight.

[1856] Terminal: Sends these data to the server.

[1857] Server: Uses image generation AI to generate an image of the user after achieving their goal.

[1858] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[1859] Users: Visualize themselves after achieving their goals and increase motivation.

[1860] Implementing gamification elements

[1861] Server: Generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[1862] Terminal: Notifies the user of the generated task and displays the task details.

[1863] User: Confirms and executes the task (e.g., walk 10,000 steps).

[1864] Terminal: Detects when the user completes a task and sends that information to the server.

[1865] Server: Receives task completion information and updates user points.

[1866] Terminal: Notify users of updated points and newly earned rewards.

[1867] User: Check the points and rewards earned and work on the next task.

[1868] This allows users to continue their daily exercise and diet management while having fun, and maintain their motivation. They can also compete with other users to earn points, which further increases motivation. With the introduction of an emotion engine, users can receive optimal action suggestions that take their emotional state into consideration, allowing them to diet more effectively.

[1869] The processing flow will be explained below.

[1870] Step 1:

[1871] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[1872] Step 2:

[1873] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[1874] Step 3:

[1875] Device: Sends saved initial setting data to the server.

[1876] Step 4:

[1877] Server: Analyzes the received initial setting data and stores it in a database.

[1878] Step 5:

[1879] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[1880] Step 6:

[1881] Terminal: Sends collected real-time data to the server.

[1882] Step 7:

[1883] Server: Stores the data received in real time in a database and checks the integrity of the data.

[1884] Step 8:

[1885] Device: Uses the user's camera and microphone to collect emotional data in real time from facial expressions and tone of voice.

[1886] Step 9:

[1887] Terminal: Sends collected emotion data to the server.

[1888] Step 10:

[1889] Server: Analyzes the received emotion data and identifies the user's emotional state.

[1890] Step 11:

[1891] Server: Based on accumulated user data and emotional data, the AI ​​model is used to create the next day's action plan. For example, based on the data and emotional data from the past seven days, it generates a suggestion such as "Walk 6,000 steps the next day."

[1892] Step 12:

[1893] Server: Based on the analysis results, it adjusts specific action suggestions according to the user's emotional state.

[1894] Step 13:

[1895] Device: Notifies the user of the proposed action plan and emotion-based adjustments, displaying details on the screen.

[1896] Step 14:

[1897] Users: Receive notifications and act on proposed action plans.

[1898] Step 15:

[1899] User: Enter data such as target weight, current weight, and photo.

[1900] Step 16:

[1901] Terminal: Sends the entered data to the server.

[1902] Step 17:

[1903] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[1904] Step 18:

[1905] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[1906] Step 19:

[1907] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[1908] Step 20:

[1909] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[1910] Step 21:

[1911] Terminal: Notifies the user of the generated task and displays the task details.

[1912] Step 22:

[1913] User: Confirms and executes the task (e.g., walk 10,000 steps).

[1914] Step 23:

[1915] Terminal: Detects when the user completes a task and sends that information to the server.

[1916] Step 24:

[1917] Server: Receives task completion information and updates user points.

[1918] Step 25:

[1919] Terminal: Notify users of updated points and newly earned rewards.

[1920] Step 26:

[1921] User: Check the points and rewards earned and work on the next task.

[1922] Example 2

[1923] 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."

[1924] Conventional diet management systems were unable to take into account the user's emotional state, leading to a decline in motivation. Furthermore, behavioral suggestions and goal setting were general, without providing appropriate suggestions based on individual data, making it difficult to diet effectively. Furthermore, they lacked the functionality to provide users with a concrete image of what it would be like to achieve their goals, making it difficult to maintain sustained motivation.

[1925] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1926] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for collecting and analyzing emotional data, means for generating messages and suggested actions to improve motivation based on the emotional data, means for generating an image of what the user will look like after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, and means for providing rewards to the user based on the point management. This makes it possible to provide appropriate suggested actions and motivational measures according to the user's emotional state, thereby supporting effective dieting.

[1927] "Means for collecting and storing user initial setting data" refers to a function that collects basic information such as weight, target weight, eating habits, and exercise habits that a user enters when using the diet management system for the first time, and stores this information in local storage and on the server.

[1928] "Means for collecting and storing real-time user data" refers to a function that collects data on exercise, sleep, diet, etc. obtained from the user's wearable device or smartphone in real time and stores it on a server.

[1929] "Means of analyzing collected data and suggesting specific actions to help users achieve their goals" refers to a function that uses AI models and algorithms based on collected data to generate and suggest specific actions, such as individual exercise plans and meal suggestions for each user.

[1930] "Means for notifying the user of the proposed action" is a function that notifies the user of the generated action suggestion on the user's device such as a smartphone or tablet.

[1931] "Means for collecting and analyzing emotional data" refers to a function that uses the user's camera or microphone to collect facial expressions and tone of voice, and analyzes this to identify the user's emotional state.

[1932] The "means for generating messages and suggested actions to improve motivation based on emotional data" is a function that generates messages and suggested actions to improve motivation, taking into account the user's emotional state, based on analyzed emotional data.

[1933] The "means for generating an image of what the user will look like after achieving their goal" is a function that uses the user's current weight and target weight as input data to generate an image of what the user will look like after achieving their goal.

[1934] "Means for displaying the generated image to the user" refers to a function that displays the generated image of the user after achieving the goal on a device such as a smartphone or tablet.

[1935] "A means for tracking tasks completed by users and managing points" refers to a function that detects exercise- and diet-related tasks that users have completed and assigns and manages the corresponding points.

[1936] The "means for providing rewards to users based on point management" is a function for providing rewards based on points earned by users.

[1937] MODE FOR CARRYING OUT THE INVENTION

[1938] The present invention is a system that recognizes a user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The system is composed of the following components:

[1939] System configuration

[1940] 1. User device: A device such as a smartphone or tablet.

[1941] 2. Server: Cloud server or on-premise data server.

[1942] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[1943] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[1944] Program processing

[1945] 1. Collecting and saving initial setup data

[1946] The user installs the diet app and inputs basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[1947] The terminal stores the collected initial setting data in a local storage and transmits it to the server.

[1948] The server analyzes the received initial setting data and stores it in a database.

[1949] 2. Real-time data collection and storage

[1950] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[1951] The server stores the data received in real time in a database.

[1952] 3. Emotional Data Collection and Analysis

[1953] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[1954] The server analyzes the collected emotional data to determine the user's current emotional state.

[1955] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[1956] 4. Data analysis and action proposals

[1957] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, it generates a suggestion such as "walk 6,000 steps the next day" based on the data and emotional data from the past seven days.

[1958] The device notifies the user of the proposed plan of action.

[1959] The user receives a notification and acts on the proposed plan of action.

[1960] 5. Goal image generation and display

[1961] The user inputs data such as a target weight and current weight.

[1962] The terminal transmits this data to the server.

[1963] The server uses image generation AI to generate an image of the user after achieving their goal.

[1964] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[1965] Users can visualize themselves after achieving their goals, which increases motivation.

[1966] 6. Implementing gamification elements

[1967] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[1968] The terminal notifies the user of the created task and displays the task details.

[1969] The user confirms and performs the task (e.g., walk 10,000 steps).

[1970] The device detects when the user completes a task and sends that information to the server.

[1971] The server receives the task completion information and updates the user's points.

[1972] The device will notify the user of updated points and newly earned rewards.

[1973] The user checks the points and rewards they have earned and moves on to the next task.

[1974] Specific examples

[1975] When a user starts a diet, they enter the initial data into the app: "Current weight: 70 kg, target weight: 60 kg, eating habits: three meals a day, exercise habits: three times a week." The device saves this data and sends it to the server. The server analyzes the received data and stores it in a database.

[1976] For example, if a user wears a smartwatch to record their daily exercise, the device will collect data such as the number of steps taken, heart rate, and sleep time, and send it to a server, which then stores this data in a database in real time.

[1977] To analyze the user's emotional state, the device's camera is used to capture a selfie, and the user's facial expression is analyzed to determine emotional states such as "satisfaction" or "stress." Based on the collected emotional data, the emotion engine generates a message such as, "You seem satisfied today! Keep it up!"

[1978] An example of an action suggestion using an AI model is a prompt such as, "Create an action plan for the next day based on the user's exercise and emotional data from the past seven days. For example, if the user walks an average of 5,000 steps, advise them to walk a little more." Based on the analysis results, the server generates a specific action plan for the next day and notifies the user via their device. The user confirms the notification and follows the suggested action plan.

[1979] The above system provides users with appropriate behavioral suggestions and motivational measures based on their emotional state, enabling them to diet effectively.

[1980] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1981] Step 1:

[1982] A user installs a diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[1983] Input: Data about the user's weight and habits

[1984] Output: Save data to the device and prepare it for transmission to the server

[1985] Specific action: The user enters information into a form in the app and presses the submit button.

[1986] Step 2:

[1987] The terminal stores the input initial setting data in local storage and transmits it to the server.

[1988] Input: Initial setting data entered by the user

[1989] Output: Data is sent to the server

[1990] Specific operation: The device temporarily stores the data in local storage and then sends the data to a server via the Internet.

[1991] Step 3:

[1992] The server analyzes the received initial setting data and stores it in a database.

[1993] Input: Initial setting data sent from the terminal

[1994] Output: User information stored in the database

[1995] Specific operation: The server analyzes the data, associates it with the user ID, and stores it in a database.

[1996] Step 4:

[1997] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[1998] Input: Sensor data from wearable devices and smartphones

[1999] Output: Data collected in real time

[2000] What it does: The terminal collects data from devices via Bluetooth and Wi-Fi.

[2001] Step 5:

[2002] The server stores the data received in real time in a database.

[2003] Input: Real-time data sent from the device

[2004] Output: Sensor data stored in a database

[2005] Specific operation: The server receives the data, analyzes it, and stores it in the database.

[2006] Step 6:

[2007] The device analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[2008] Input: facial expression and voice data from camera and microphone

[2009] Output: Emotion data

[2010] Specific operation: The device captures the user's facial expression with a camera and analyzes the tone of the voice using voice recognition software.

[2011] Step 7:

[2012] The server analyzes the collected emotional data to determine the user's current emotional state.

[2013] Input: Emotion data sent from the device

[2014] Output: Emotional state as a result of analysis

[2015] Specific behavior: The emotion engine analyzes the data and identifies the emotional state (e.g., "happy" or "stressed").

[2016] Step 8:

[2017] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[2018] Input: Parsed emotional state

[2019] Output: Motivational messages and action suggestions

[2020] Specific action: The emotion engine generates an appropriate message (e.g., "Keep it up!").

[2021] Step 9:

[2022] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day.

[2023] Input: User data and emotion data

[2024] Output: Action plan for the next day

[2025] Specific actions: The AI ​​model analyzes the data and creates a specific action plan, such as "walk 6,000 steps the next day."

[2026] Step 10:

[2027] The device will notify the user of the proposed plan of action.

[2028] Input: Action plan sent from the server

[2029] Output: User notification

[2030] Specific behavior: The device uses the notification function to display details of the suggested action to the user.

[2031] Step 11:

[2032] The user receives a notification and acts on the proposed plan of action.

[2033] Input: Notifications from your device

[2034] Output: User actions

[2035] Specific Action: The user acknowledges the notification and acts on the suggested exercise and meal plan.

[2036] Step 12:

[2037] The user inputs data such as target weight and current weight.

[2038] Input: Data such as target weight and current weight

[2039] Output: Save data to the device and prepare it for transmission to the server

[2040] Specific action: The user enters information into a form in the app and presses the submit button.

[2041] Step 13:

[2042] The terminal transmits this data to the server.

[2043] Input: Data entered by the user

[2044] Output: Data is sent to the server

[2045] Specific operation: The device sends data to a server via the Internet.

[2046] Step 14:

[2047] The server uses image generation AI to generate an image of the user after achieving their goal.

[2048] Input: Entered target weight and current weight data

[2049] Output: The generated image

[2050] Specific operation: The image generation AI simulates what the goal will look like after it is achieved based on the input data and generates an image.

[2051] Step 15:

[2052] The device displays the generated image to the user.

[2053] Input: Image data sent from the server

[2054] Output: Image displayed to the user

[2055] Specific operation: The device displays the generated image on the screen and shows it to the user.

[2056] Step 16:

[2057] Users can visualize what they will look like after achieving their goals, which increases motivation.

[2058] Input: Displayed image

[2059] Output: Increased user motivation

[2060] Specific action: The user looks at the image and imagines themselves achieving their goal.

[2061] Step 17:

[2062] The server generates diet-related tasks and assigns points to the tasks.

[2063] Input: User data stored on the server

[2064] Output: Generated tasks and point configurations

[2065] Specific operation: The server generates tasks based on user data and assigns appropriate points.

[2066] Step 18:

[2067] The device notifies the user of the generated task and displays the task details.

[2068] Input: Task data sent from the server

[2069] Output: Task notification to user

[2070] Specific behavior: The device uses notifications to display task details to the user.

[2071] Step 19:

[2072] The user confirms and performs a task, for example, walking 10,000 steps.

[2073] Input: Task notification from the device

[2074] Output: Task accomplished

[2075] Specific Action: The user reviews the task details and takes action.

[2076] Step 20:

[2077] The device detects when the user completes a task and sends that information to the server.

[2078] Input: Completed task data

[2079] Output: Completion data sent to the server

[2080] Specific operation: The device detects the completion of the task and sends the data to the server.

[2081] Step 21:

[2082] The server receives the task completion information and updates the user's points.

[2083] Input: Completion data sent from the terminal

[2084] Output: Updated points

[2085] Specific operation: The server receives the data and updates the user points in the database.

[2086] Step 22:

[2087] The device will notify the user of updated points and newly earned rewards.

[2088] Input: Updated point data

[2089] Output: Point reward notification to user

[2090] What it does: The device uses notifications to display points and reward details to the user.

[2091] Step 23:

[2092] Check the points and rewards the user has earned and work on the next task.

[2093] Input: Points and rewards notifications

[2094] Output: Tackling new tasks

[2095] Specific action: The user checks the notification and is motivated to take on a new task.

[2096] The above are the specific processing steps of this system's program. Through this process, users are provided with appropriate behavioral suggestions and motivational measures according to their emotional state, enabling them to effectively diet.

[2097] (Application example 2)

[2098] 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."

[2099] Conventional diet support systems provided messages and suggested actions without considering the user's emotional state, making it difficult to maintain user motivation. Furthermore, in the shopping experience at physical stores, it was difficult to provide individualized support based on the user's emotions and needs, and the system did not sufficiently stimulate purchasing motivation or recommend optimal products. As a result, there were issues with diet continuity and a decrease in satisfaction with the shopping experience.

[2100] 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.

[2101] In this invention, the server includes means for recognizing the emotional state of the user and analyzing the emotional data, means for recommending products and services suitable for the user based on the emotion analysis results, and means for displaying the recommendation results according to the emotional state on the user's mobile terminal in real time. This makes it possible to provide individualized responses based on the emotional state, thereby maintaining the user's motivation and increasing their willingness to purchase.

[2102] "User initial setting data" refers to basic information (e.g., current weight, target weight, eating habits, exercise habits, etc.) that a user enters when they start using the system.

[2103] "Real-time user data" refers to current user activity data, such as exercise, sleep, and diet, obtained from wearable devices and mobile terminals.

[2104] "Means for suggesting specific actions" is a function that presents instructions and actions to users to achieve their goals based on collected and analyzed data.

[2105] "Means for notifying users" refers to a function that notifies users of suggested actions or messages on their mobile devices.

[2106] "Means for generating an image of what the user will look like after achieving their goal" is a function that uses a generative AI model to visualize what the user will look like (such as changes in weight and body shape) if they achieve their goal.

[2107] The "means for displaying the generated image to the user" is a function for displaying the predicted image after the goal is achieved on the user's mobile device.

[2108] "Means for tracking tasks and managing points" refers to a function that allows users to record the tasks they have completed and award and manage points according to their level of completion.

[2109] "Means for providing rewards to users based on point management" is a function that provides rewards and incentives based on the points that users have earned.

[2110] "Means for recognizing emotional state and analyzing emotional data" refers to a function that recognizes and analyzes the user's emotional state from facial expressions, tone of voice, etc.

[2111] "Means for recommending products and services suitable for users based on the results of emotional analysis" is a function that suggests products and services that are best suited to users based on their emotional state.

[2112] "Means for displaying recommendation results according to emotional state on the user's mobile device in real time" is a function for displaying recommendation messages generated based on emotional analysis on the user's mobile device in real time.

[2113] MODE FOR CARRYING OUT THE INVENTION

[2114] System Configuration

[2115] The present invention is implemented by a system comprising the following components:

[2116] 1. User Device

[2117] Using mobile devices such as smartphones and tablets.

[2118] 2. Server

[2119] It uses cloud servers and on-premise data servers, and mainly performs data analysis and runs AI models.

[2120] 3. Wearable devices

[2121] Use devices such as smartwatches and fitness bands to collect users' exercise and sleep data.

[2122] 4. Emotion Engine

[2123] It uses software to analyze the user's facial expressions and tone of voice to recognize their emotional state.

[2124] Program implementation procedure

[2125] 1. Collecting and storing user preference data

[2126] Users install the app and enter basic information such as their current weight, target weight, eating habits, and exercise habits when they first launch it.

[2127] The terminal stores the input initial setting data in local storage and transmits it to the server.

[2128] The server analyzes the received initial setting data and stores it in a database.

[2129] 2. Collecting and storing real-time user data

[2130] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[2131] The server stores the collected real-time data in a database.

[2132] 3. Collecting and analyzing user emotion data

[2133] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[2134] The server analyzes the collected emotional data to determine the user's current emotional state.

[2135] The emotion engine uses emotional data to generate messages to recommend products and services that are appropriate for the user.

[2136] 4. Data analysis and action proposals

[2137] The server analyzes the accumulated user data and sentiment data and uses AI models to recommend the next day's action plan and specific products.

[2138] The device will notify the user with suggested action plans and product recommendations.

[2139] 5. Goal image generation and display

[2140] The user inputs data such as their target weight and current weight.

[2141] The terminal transmits this data to the server.

[2142] The server uses a generative AI model to generate an image of what the goal will look like after it is achieved.

[2143] The device displays the generated image to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, the device displays a projection of what the user will weigh when they reach 60 kg.

[2144] 6. Implementing gamification elements

[2145] The server generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[2146] The device will notify the user of the generated task and display the task details.

[2147] The user confirms and performs the task (e.g., walk 10,000 steps).

[2148] The device detects when the user completes a task and sends that information to the server.

[2149] The server receives the task completion information and updates the user's points.

[2150] The device will notify the user of updated points and newly earned rewards.

[2151] Specific examples

[2152] Example 1: When a user enters a physical store and launches the app, facial recognition detects fatigue and the AI ​​notifies them, "Here's a tea that will help you refresh yourself!"

[2153] Example 2: Using step count data, you can appeal to people by saying, "You haven't gotten enough exercise today. Get 20% off protein bars!"

[2154] Prompt Sentence Examples

[2155] "The user appears to be a little tired. Please recommend products that will help them feel refreshed."

[2156] "Recommend appropriate products and services based on the user's goals."

[2157] The hardware used includes smartphones and wearable devices (smartwatches, fitness bands), and the software uses cloud services (AWS Lambda, Amazon SageMaker) and mobile application software (Swift, Kotlin). The database uses Amazon RDS for efficient data management and analysis. This allows optimal action suggestions and product recommendations to be provided in real time based on the user's emotional state, improving both the purchasing experience and diet management.

[2158] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2159] Step 1:

[2160] Collecting and storing user preference data

[2161] Input: The user enters basic information (current weight, target weight, dietary habits, and exercise habits) into a smartphone app.

[2162] What happens: A user installs the app and enters basic information on first launch.

[2163] Data processing: The device structures the input data and saves it in local storage. It then sends the saved data to a cloud server.

[2164] Output: The saved initial setting data is sent to the cloud server and stored in the database.

[2165] Step 2:

[2166] Collecting and storing real-time user data

[2167] Input: Exercise data (steps, heart rate, etc.), sleep data, and dietary data from the user's wearable device or smartphone.

[2168] How it works: The device collects data in real time from wearable devices and smartphones.

[2169] Data processing: Each collected data is sent to a cloud server and stored in a database.

[2170] Output: Real-time data stored in a database.

[2171] Step 3:

[2172] Collecting and analyzing user emotion data

[2173] Input: Data about the user's facial expressions and tone of voice.

[2174] How it works: The device uses the smartphone's camera and microphone to collect the user's facial expressions and tone of voice.

[2175] Data processing: The device sends the collected emotion data to a cloud server, where it is analyzed by an emotion engine.

[2176] Output: Identified user emotional state data.

[2177] Step 4:

[2178] Data analysis and action proposals

[2179] Input: Real-time user data and sentiment data.

[2180] Specific operation: The server analyzes the accumulated data using an AI model to generate an action plan for the next day and recommended products.

[2181] Data processing: Generative AI models create action suggestions and product recommendations based on past data and current emotional state.

[2182] Output: A message with suggested actions or product recommendations is generated.

[2183] Step 5:

[2184] Notification of proposed action plans or products

[2185] Input: Generated action suggestions and product recommendations.

[2186] Specific operation: The server notifies the user of the generated message on their smartphone.

[2187] Output: A notification with an action plan and product recommendations will be displayed on the user's device.

[2188] Step 6:

[2189] Goal image generation and display

[2190] Input: User's current weight, goal weight data.

[2191] Specific operation: The server inputs this data into a generative AI model and generates an image of what the robot will look like after achieving the goal.

[2192] Data processing: Images are generated using an AI model and sent from the cloud server to the device.

[2193] Output: The generated image is displayed on the user's device.

[2194] Step 7:

[2195] Implementing gamification elements

[2196] Input: Diet-related tasks and point settings.

[2197] Specific operation: The server generates diet tasks and assigns points to each one.

[2198] Data processing: Each task and point information is saved on the cloud server.

[2199] Output: The task and points are notified to the user's device, and the user completes the task and earns points.

[2200] Step 8:

[2201] Points management and rewards

[2202] Input: Data of the task that the user completed.

[2203] Specific operation: The device sends task completion information to the cloud server and updates points.

[2204] Data processing: The server analyzes the task completion data, updates the user's points, and generates reward information.

[2205] Output: The updated points and rewards are notified to the user's device.

[2206] This series of processes enables personalized action suggestions and product recommendations based on the user's emotional state and real-time data.

[2207] 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.

[2208] 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.

[2209] 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.

[2210] [Fourth embodiment]

[2211] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2212] 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.

[2213] 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).

[2214] 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.

[2215] 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.

[2216] 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).

[2217] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2218] 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.

[2219] 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.

[2220] 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.

[2221] 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.

[2222] 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.

[2223] 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."

[2224] The present invention is a system that uses AI to support the user's dieting process and is designed to allow the user to continue dieting in an enjoyable manner. The following describes an embodiment of the system.

[2225] System configuration

[2226] This system mainly consists of the following components:

[2227] 1. User device: A device such as a smartphone or tablet.

[2228] 2. Server: Cloud server or on-premise data server.

[2229] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[2230] Program processing

[2231] Collecting and storing user preference data

[2232] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[2233] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[2234] Server: Saves the received initial setting data in a database.

[2235] Collecting and storing real-time user data

[2236] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[2237] Server: Stores the data received in real time in a database.

[2238] Data analysis and action proposals

[2239] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[2240] Terminal: Notify user of proposed plan of action.

[2241] Users: Get notified and take action.

[2242] Goal image generation and display

[2243] User: Enters data such as target weight and current weight.

[2244] Terminal: Sends these data to the server.

[2245] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[2246] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[2247] Users: Visualize themselves after achieving their goals and increase motivation.

[2248] Implementing gamification elements

[2249] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[2250] Terminal: Notifies the user of tasks and tracks task progress.

[2251] User: When a user completes a task, the information is sent to the server and points are added.

[2252] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[2253] Terminal: Shows reward details and points progress to users.

[2254] These features allow users to continue their daily exercise and dietary management in an enjoyable way, and maintain motivation to achieve their goals. Furthermore, the system is designed to incorporate a competitive element, allowing users to encourage each other as they diet. In this way, it provides an efficient system that can comprehensively solve dieting challenges.

[2255] The processing flow will be explained below.

[2256] Step 1:

[2257] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[2258] Step 2:

[2259] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[2260] Step 3:

[2261] Device: Sends saved initial setting data to the server.

[2262] Step 4:

[2263] Server: Analyzes the received initial setting data and stores it in a database.

[2264] Step 5:

[2265] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[2266] Step 6:

[2267] Terminal: Sends collected real-time data to the server.

[2268] Step 7:

[2269] Server: Stores the data received in real time in a database and checks the integrity of the data.

[2270] Step 8:

[2271] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[2272] Step 9:

[2273] Server: Based on the results of the AI ​​analysis, it generates specific action suggestions for the user (e.g., walk 6,000 steps).

[2274] Step 10:

[2275] Device: Notify the user of the proposed plan of action and display details on the screen.

[2276] Step 11:

[2277] Users: Receive notifications and act on proposed action plans.

[2278] Step 12:

[2279] User: Enters data such as target weight and current weight, as well as a current photo.

[2280] Step 13:

[2281] Terminal: Sends the entered data to the server.

[2282] Step 14:

[2283] Server: Using image generation AI, generate what the user will look like when they achieve their target weight.

[2284] Step 15:

[2285] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[2286] Step 16:

[2287] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[2288] Step 17:

[2289] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[2290] Step 18:

[2291] Terminal: Notifies the user of the generated task and displays the task details.

[2292] Step 19:

[2293] User: Confirms and executes the task (e.g., walk 10,000 steps).

[2294] Step 20:

[2295] Terminal: Detects when the user completes a task and sends that information to the server.

[2296] Step 21:

[2297] Server: Receives task completion information and updates user points.

[2298] Step 22:

[2299] Terminal: Notify users of updated points and newly earned rewards.

[2300] Step 23:

[2301] User: Check the points and rewards earned and work on the next task.

[2302] This allows users to continue their daily exercise and dietary management while having fun, and maintain their motivation. Users can also compete with other users to earn points, further increasing motivation.

[2303] Example 1

[2304] 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."

[2305] Conventional diet support systems have the problem of making it difficult for users to continue dieting. Specifically, it is difficult to efficiently collect and store the user's initial setting data and real-time data, and to make appropriate action suggestions based on that data. In addition, there is a lack of a way to visually show the effectiveness of the action suggestions, making it difficult to maintain the user's motivation. Furthermore, there is a need for a system that can provide users with continuous diet support by incorporating game elements.

[2306] 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.

[2307] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goal, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goal, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, means for verifying the accuracy of the real-time data, means for using an AI model to generate a suggested action plan, and means for generating an appearance after achieving the goal using an image generation AI model based on the user's data, which enables the user to enjoy and continue dieting and easily maintain motivation to achieve their goal.

[2308] "Means for collecting and saving user initial setting data" refers to a function that saves basic information entered by the user, such as weight, target weight, eating habits, and exercise habits, on the device and sends that data to the server.

[2309] "Means for collecting and storing real-time user data" refers to a function that allows a device to obtain data such as exercise, sleep, and diet from sensors in wearable devices and smartphones and send it to a server.

[2310] "Means for analyzing collected data and suggesting specific actions to achieve the user's goals" refers to a function that allows the server to analyze accumulated user data and use an AI model to generate an action plan appropriate for the user.

[2311] "Means for notifying the user of suggested actions" refers to push notifications or in-app notifications that inform the user of suggested actions received by the device from the server.

[2312] The "means for generating an image of what the user will look like after achieving their goal" is a function that allows the server to use an image generation AI model based on the user's goal data to generate an image of the user after achieving their goal.

[2313] The "means for displaying the generated image to the user" is a function that enables the terminal to display the image generated by the server to the user.

[2314] "Means for tracking tasks completed by users and managing points" is a function that allows the server to record the task completion status of users and reflect it in the point system.

[2315] The "means for providing rewards to users based on point management" is a function that allows the server to set rewards according to the accumulated points of users and provide the rewards to the users.

[2316] "Means for verifying the accuracy of real-time data" refers to the internal processing performed by the server to verify the validity and accuracy of the real-time data received.

[2317] "Means of using AI models to generate suggested action plans" refers to the use of modern machine learning techniques to analyze user data and automatically generate next steps or exercise plans.

[2318] "A means for generating what the user's goal will look like after it has been achieved using an image generation AI model based on user data" is a function that uses AI to convert the user's goal information into visual data and provides the future image.

[2319] This invention is a system that utilizes AI technology to support users in their dieting process, and is designed to enable users to enjoyably and continuously diet. Detailed embodiments for specifically implementing this system are described below.

[2320] System configuration

[2321] The system consists of the following main components:

[2322] 1. User device: A device such as a smartphone or tablet.

[2323] 2. Server: Cloud server or on-premise data server.

[2324] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[2325] Collecting and saving initial setup data

[2326] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[2327] Example: A user inputs "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", and "Exercise 3 times a week".

[2328] 2. Terminal: The entered initial setting data is temporarily stored in local storage and then securely sent to the server using the HTTPS protocol. The software used is a lightweight database such as SQLite.

[2329] Example: Save initial setting data in local storage in a file called "usersettings.db".

[2330] 3. Server: The server stores the received initial configuration data in an RDBMS (e.g., MySQL or PostgreSQL).

[2331] Example: Execute an INSERT statement to store data in the "UserSettings" table in the database.

[2332] Real-time data collection and storage

[2333] 1. Device: The device periodically collects exercise, sleep, dietary data, etc. from sensors in wearable devices and smartphones.

[2334] Example: Obtaining step count and heart rate data from a smartwatch via Bluetooth.

[2335] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[2336] Example: Validating data to ensure it is valid before saving it to the database.

[2337] Data analysis and action proposals

[2338] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model using Python's TensorFlow or PyTorch.

[2339] Example: Generate a suggestion such as "Walk 6000 steps tomorrow" based on data from the past 7 days. An example prompt is as follows:

[2340] "Generate exercise suggestions for the user for the next day based on their exercise data from the past seven days. For example, a suggestion like 'Walk 6,000 steps tomorrow.'"

[2341] 2. On the device: Notify the user of the proposed action plan via push notification.

[2342] Example: A message appears in the notification bar on your smartphone saying, "Walk 6,000 steps tomorrow."

[2343] Goal image generation and display

[2344] 1. User: Enter data such as target weight and current weight.

[2345] Example: A user inputs weight data "Current weight: 70 kg" and "Target weight: 60 kg".

[2346] 2. Terminal: Sends these data to the server.

[2347] 3. Server: Using image generation AI (such as Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[2348] Example: An image generation AI model generates "what it will look like when it weighs 60 kg." The prompt is as follows:

[2349] "The user's current weight is 70 kg, and their target weight is 60 kg. Based on this information, please generate an image of what the user will look like when they reach 60 kg."

[2350] 4. Terminal: displays the generated image to the user.

[2351] Implementing gamification elements

[2352] 1. Server: Generates diet-related tasks and assigns points based on the tasks.

[2353] Example: The server sets a task: "Walk 10,000 steps to get 10 points."

[2354] 2. Device: Notifies the user of tasks and tracks task progress in real time.

[2355] 3. User: When a task is completed, points are earned and the information is sent to the server.

[2356] Example: After a user walks 10,000 steps, the app reports "task completed."

[2357] 4. Server: Manages points and provides rewards based on accumulated points.

[2358] 5. Terminal: Shows rewards and points progress to users.

[2359] Example: Displaying "100 points reached! New rewards earned!" on the in-app dashboard.

[2360] In this way, users can continue their daily exercise and diet management in an enjoyable way and stay motivated to achieve their goals. Also, by incorporating an element of competition with other users, an efficient system is provided where users can encourage each other while dieting.

[2361] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2362] Step 1:

[2363] Collecting and storing user preference data

[2364] 1. User: Installs the diet app on a smartphone and enters data such as current weight, target weight, eating habits, and exercise habits when first launched.

[2365] Input: The user enters the following information into a form: "Current weight: 70kg", "Goal weight: 60kg", "3 meals a day", "Exercise 3 times a week".

[2366] Output: The input data is saved in the app.

[2367] 2. Terminal: The entered initial setting data is temporarily saved in local storage and sent to the server using the HTTPS protocol.

[2368] What happens: The app saves the data and sends it to the server via a web request.

[2369] Input: Initial configuration data obtained from the user.

[2370] Output: Initial configuration data sent to the server.

[2371] 3. Server: The server stores the received initial setting data in an RDBMS (such as MySQL or PostgreSQL).

[2372] Specific operation: The INSERT statement is executed on the server side and the data is stored in the "UserSettings" table.

[2373] Input: Initialization data sent from the terminal.

[2374] Output: Initial configuration data stored in the database.

[2375] Step 2:

[2376] Real-time data collection and storage

[2377] 1. Device: The device periodically collects exercise, sleep, and dietary data from sensors in wearable devices and smartphones.

[2378] Specific operation: Obtain data from smartwatch via Bluetooth.

[2379] Input: Real-time data from wearable devices.

[2380] Output: Collected data is saved to the device.

[2381] 2. Server: Validates the accuracy of the data received in real time before storing it in the database.

[2382] What it does: Validates data accuracy using validation algorithms and filters out invalid data.

[2383] Input: Real-time data sent from the device.

[2384] Output: The validated data is saved in the database.

[2385] Step 3:

[2386] Data analysis and action proposals

[2387] 1. Server: Analyzes accumulated user data and generates the next day's action plan using an AI model (TensorFlow or PyTorch).

[2388] How it works: The AI ​​model performs predictions using a Python script.

[2389] Input: Last 7 days of user data stored in the database.

[2390] Output: Suggested action for the next day (e.g., "Walk 6,000 steps tomorrow").

[2391] 2. On the device: Notify the user of the proposed action plan via push notification.

[2392] Specific action: Proposals are notified using the smartphone's notification function.

[2393] Input: Action suggestions from the server.

[2394] Output: The notification message that will be displayed on the user's smartphone.

[2395] Step 4:

[2396] Goal image generation and display

[2397] 1. User: Enter data such as target weight and current weight.

[2398] Specific action: Enter data into a form within the app.

[2399] Input: User's weight data (e.g. current weight 70kg, target weight 60kg).

[2400] Output: Weight data stored on the device.

[2401] 2. Terminal: Sends these data to the server.

[2402] Specific operation: Issue an HTTPS request and send data to the server.

[2403] Input: User's weight data.

[2404] Output: Weight data sent to the server.

[2405] 3. Server: Using image generation AI (Stable Diffusion or DALL-E), generate an image of the user after achieving their goal.

[2406] Specific operation: Calls the AI ​​model and executes the image generation process.

[2407] Input: User's weight data.

[2408] Output: The generated goal image.

[2409] 4. Terminal: displays the generated image to the user.

[2410] Specific behavior: Display an image within the app.

[2411] Input: Generated image sent from the server.

[2412] Output: The generated image displayed on a smartphone.

[2413] Step 5:

[2414] Implementing gamification elements

[2415] 1. Server: Generates diet-related tasks and sets points.

[2416] Specific operation: Run the task generation algorithm and add a new task to the database.

[2417] Input: User's exercise data.

[2418] Output: The generated tasks.

[2419] 2. Terminal: Notifies the user of tasks and tracks progress.

[2420] Specific action: Use the smartphone's notification function to notify you of the task.

[2421] Input: Task data sent from the server.

[2422] Output: Task notification.

[2423] 3. User: When a task is completed, points are earned and the information is sent to the server.

[2424] Specific action: Tap the "Complete Task" button within the app to earn points.

[2425] Input: User's task completion information.

[2426] Output: Completion information sent to the server.

[2427] 4. Server: Manages points and provides rewards.

[2428] Specific operation: Calculate rewards using a points management system and provide them to users.

[2429] Input: The user's accumulated points.

[2430] Output: The reward offered.

[2431] 5. Terminal: Shows rewards and points progress to users.

[2432] Specific behavior: Display rewards and points on the in-app dashboard.

[2433] Input: Points and rewards data sent from the server.

[2434] Output: Progress displayed on the user's smartphone.

[2435] (Application example 1)

[2436] 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."

[2437] Conventional diet support systems make it difficult for users to maintain motivation to continue daily exercise and diet management, and there are no systems that can support specific diet action plans or meal optimization. Furthermore, there is a lack of specific support to increase the success rate of dieting by proposing meal menus suitable for users and making them easy to order. This creates a challenge for users, making it difficult to diet in a planned and effective manner.

[2438] 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.

[2439] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for generating an image of the user's appearance after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, means for providing rewards to the user based on the point management, and means for suggesting optimal meal menus based on the user's exercise and dietary status and allowing the user to order those meals. This enables the user to effectively and continuously manage their daily exercise and diet, thereby increasing the success rate of their diet. Furthermore, the ability to easily order appropriate meal menus supports the user in improving their dietary habits and makes their overall dieting efforts more efficient.

[2440] "User's initial setting data" refers to basic information that the user inputs when launching the diet support system for the first time, and includes current weight, target weight, eating habits, and exercise habits.

[2441] "User real-time data" refers to data on a user's daily exercise and dietary habits collected in real time from devices such as wearable devices and smartphones.

[2442] The "means of analysis and suggestion" is a system that analyzes the collected initial setting data and real-time data of the user and suggests specific action plans and meal menus to help the user achieve their goals.

[2443] "Means for notifying actions" refers to a function that notifies the user of suggested action plans and meal menus on their smartphone or other device.

[2444] The "image generation means" is a system that uses AI image generation technology to predict what the user will look like after achieving their target weight and generates an image of that prediction.

[2445] The "image display means" is a function that displays on the terminal the image of the user after achieving the generated target weight.

[2446] A "task tracking tool" is a system that tracks whether a user has carried out an action plan or suggested meal menu and records their progress.

[2447] The "point management means" is a system that grants and manages points based on the tasks that users complete, and provides rewards to users based on those points.

[2448] The "meal menu suggestion method" is a system in which AI suggests the optimal meal menu based on the user's exercise and eating habits, and notifies the user of the suggested menu.

[2449] The "Meal Ordering Method" is a system that allows users to easily order suggested meal menus, and is a function that connects with nearby affiliated restaurants and delivery services.

[2450] This invention is a system that uses AI to support users in their dieting. This system proposes optimal meal menus based on the user's exercise and eating habits, and allows them to easily order them, thereby providing effective and continuous support for the user's diet.

[2451] System configuration

[2452] This system consists of the following main components:

[2453] 1. User device: The device used by the user, such as a smartphone or tablet.

[2454] 2. Server: A cloud server that stores and analyzes collected data.

[2455] 3. Wearable devices: Devices that collect user exercise and sleep data (e.g., smartwatches).

[2456] Program processing

[2457] Collecting and storing user preference data

[2458] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[2459] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[2460] Server: Saves the received initial setting data in a database.

[2461] Collecting and storing real-time user data

[2462] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[2463] Server: Stores the data received in real time in a database.

[2464] Data analysis and action proposals

[2465] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day. For example, based on data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[2466] Terminal: Notify user of proposed plan of action.

[2467] Users: Get notified and take action.

[2468] Goal image generation and display

[2469] User: Enters data such as target weight and current weight.

[2470] Terminal: Sends these data to the server.

[2471] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[2472] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[2473] Users: Visualize themselves after achieving their goals and increase motivation.

[2474] Implementing gamification elements

[2475] Server: Generates diet-related tasks and assigns points to each task. For example, you can earn 10 points for walking 10,000 steps.

[2476] Terminal: Notifies the user of tasks and tracks task progress.

[2477] User: When a user completes a task, the information is sent to the server and points are added.

[2478] Server: Manages points and provides rewards when users reach a certain number of points. For example, a user can earn a specific reward for every 100 points.

[2479] Terminal: Shows reward details and points progress to users.

[2480] Hardware and software used

[2481] This system uses the following hardware and software.

[2482] Hardware: Smartphones (iPhone, Android), wearable devices (Apple Watch, Fitbit)

[2483] Software: AWS Lambda, Amazon RDS, Firebase, TensorFlow, React Native

[2484] Specific examples

[2485] 1. When the user does the initial setup:

[2486] Users open the app on their smartphone and enter their current weight, goal weight, dietary habits, and exercise habits as initial settings. The entered data is then sent to a cloud server.

[2487] 2. When collecting data:

[2488] Real-time exercise and sleep data is collected through the wearable device and sent to a server via a smartphone.

[2489] 3. When AI suggests a meal:

[2490] An AI model on the server analyzes the user's exercise and eating habits and suggests the optimal meal menu for the next day.

[2491] 4. When the user receives the suggestion:

[2492] The suggested meal menu will be sent to the user's smartphone, allowing them to order meals directly from affiliated restaurants or delivery services.

[2493] Prompt Sentence Examples

[2494] "Recommend next day's meal plans based on the user's calorie consumption data and eating habits. Show the best choices for the user's weight goal."

[2495] The above is a specific embodiment for carrying out the present invention. This system allows users to continue dieting effectively and enjoyably, and achieve their goals.

[2496] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2497] Step 1: Collect and store user preference data

[2498] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[2499] Input: Initial setting data (current weight, target weight, eating habits, exercise habits)

[2500] Output: Save data to local storage and send to server

[2501] What happens: A user opens the app on their phone and enters the required information into the designated input fields.

[2502] Step 2: Collect and store real-time user data

[2503] Device: Collects data such as exercise, sleep, and diet from the user's wearable device or smartphone.

[2504] Input: Exercise, sleep, and diet data from wearable devices

[2505] Output: Data sent to the server in real time

[2506] How it works: The smartphone periodically collects data from the wearable device and uploads it to a server.

[2507] Step 3: Analyze the data and develop an action plan

[2508] Server: Analyzes accumulated user data and uses an AI model to create an action plan for the next day.

[2509] Input: User initial setting data, real-time data history

[2510] Output: A concrete action plan (e.g., "Let's walk 6,000 steps tomorrow")

[2511] How it works: The AI ​​model on the server analyzes past data and generates an optimal plan of action for the next day.

[2512] Step 4: Communicate your action plan

[2513] Terminal: Notify user of proposed plan of action.

[2514] Input: AI-generated action plan

[2515] Output: Action plan notified to smartphone

[2516] How it works: Once the server generates an action plan, it pushes it to the user's smartphone.

[2517] Step 5: User Action

[2518] Users: Get notified and take action.

[2519] Input: Notified Action Plan

[2520] Output: Perform an action (e.g., walk 6000 steps)

[2521] Action: The user checks the notification on their smartphone and performs the indicated action.

[2522] Step 6: Generate and display the goal image

[2523] User: Enters data such as target weight and current weight.

[2524] Input: Target weight and current weight

[2525] Output: Data sent to the server

[2526] How it works: The user enters their goal weight and current weight in the app and sends them to the server.

[2527] Step 7: Generate images

[2528] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[2529] Input: Target weight and current weight

[2530] Output: The generated goal image

[2531] How it works: The image generation AI on the server generates the user's goal image based on the input data.

[2532] Step 8: Displaying the image

[2533] Terminal: Displays the generated image to the user.

[2534] Input: Generated goal image

[2535] Output: Goal image displayed on a smartphone

[2536] Operation: The generated image is downloaded to a smartphone and displayed.

[2537] Step 9: Task Tracking and Points Management

[2538] Terminal: Tracks the tasks completed by the user and sends them to the server.

[2539] Input: Completed task data

[2540] Output: Task data sent to the server

[2541] How it works: When a user completes a task, their smartphone sends the information to a server.

[2542] Step 10: Awarding points

[2543] Server: Manages points and provides rewards when users reach a certain number of points.

[2544] Input: Task data and point management data

[2545] Output: Reward provided to user

[2546] How it works: The server calculates points based on tracking data and provides rewards.

[2547] Step 11: Meal suggestions

[2548] Server: AI suggests optimal meal menus based on the user's exercise and eating habits.

[2549] Input: Exercise status, diet status, user goals

[2550] Output: Suggested meal menu

[2551] How it works: The AI ​​on the server analyzes the data and generates a meal menu suitable for the user.

[2552] Step 12: Notification of proposed menu and ordering

[2553] Device: Providing users with menu suggestions and allowing them to order meals from partner restaurants and delivery services.

[2554] Input: Suggested meal menu

[2555] Output: Notification to user's smartphone, order process

[2556] How it works: The suggested meal menu is sent to the user's smartphone, and once the user confirms the order, an order is placed with the partner service.

[2557] 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.

[2558] The present invention adds a system that recognizes the user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The following describes in detail the embodiments of the present invention.

[2559] System configuration

[2560] This system consists of the following components:

[2561] 1. User device: A device such as a smartphone or tablet.

[2562] 2. Server: Cloud server or on-premise data server.

[2563] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[2564] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[2565] Program processing

[2566] Collecting and storing user preference data

[2567] User: Installs the diet app and enters basic information such as current weight, target weight, eating habits, and exercise habits when first launched.

[2568] Terminal: The collected initial setting data is stored in local storage and sent to the server.

[2569] Server: Analyzes the received initial setting data and stores it in a database.

[2570] Collecting and storing real-time user data

[2571] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[2572] Server: Stores the data received in real time in a database.

[2573] Collecting and analyzing user emotion data

[2574] Device: Analyzes the user's facial expressions and tone of voice through the camera and microphone to collect emotional data.

[2575] Server: Analyzes the collected emotional data and identifies the user's current emotional state.

[2576] Emotion engine: Generates messages and suggested actions based on emotional data to improve user motivation.

[2577] Data analysis and action proposals

[2578] Server: Analyzes accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, based on data and emotional data from the past seven days, it generates suggestions such as "Walk 6,000 steps the next day."

[2579] Terminal: Notify user of proposed plan of action.

[2580] Users: Receive notifications and act on proposed action plans.

[2581] Goal image generation and display

[2582] User: Enters data such as target weight and current weight.

[2583] Terminal: Sends these data to the server.

[2584] Server: Uses image generation AI to generate an image of the user after achieving their goal.

[2585] Device: The generated image is displayed to the user. For example, if the current weight is 70 kg and the target weight is 60 kg, a predicted image of what the user will look like when they reach 60 kg is displayed.

[2586] Users: Visualize themselves after achieving their goals and increase motivation.

[2587] Implementing gamification elements

[2588] Server: Generates diet-related tasks and assigns points to the tasks (e.g., 10 points for 10,000 steps).

[2589] Terminal: Notifies the user of the generated task and displays the task details.

[2590] User: Confirms and executes the task (e.g., walk 10,000 steps).

[2591] Terminal: Detects when the user completes a task and sends that information to the server.

[2592] Server: Receives task completion information and updates user points.

[2593] Terminal: Notify users of updated points and newly earned rewards.

[2594] User: Check the points and rewards earned and work on the next task.

[2595] This allows users to continue their daily exercise and diet management while having fun, and maintain their motivation. They can also compete with other users to earn points, which further increases motivation. With the introduction of an emotion engine, users can receive optimal action suggestions that take their emotional state into consideration, allowing them to diet more effectively.

[2596] The processing flow will be explained below.

[2597] Step 1:

[2598] User: Installs the diet app. When first launched, the user enters basic information such as current weight, target weight, eating habits, and exercise habits.

[2599] Step 2:

[2600] Device: Save the entered initial setup data to local storage and verify that the data has been saved.

[2601] Step 3:

[2602] Device: Sends saved initial setting data to the server.

[2603] Step 4:

[2604] Server: Analyzes the received initial setting data and stores it in a database.

[2605] Step 5:

[2606] Device: Collects exercise, sleep, and diet data in real time from the user's wearable device or smartphone.

[2607] Step 6:

[2608] Terminal: Sends collected real-time data to the server.

[2609] Step 7:

[2610] Server: Stores the data received in real time in a database and checks the integrity of the data.

[2611] Step 8:

[2612] Device: Uses the user's camera and microphone to collect emotional data in real time from facial expressions and tone of voice.

[2613] Step 9:

[2614] Terminal: Sends collected emotion data to the server.

[2615] Step 10:

[2616] Server: Analyzes the received emotion data and identifies the user's emotional state.

[2617] Step 11:

[2618] Server: Based on accumulated user data and emotional data, the AI ​​model is used to create the next day's action plan. For example, based on the data and emotional data from the past seven days, it generates a suggestion such as "Walk 6,000 steps the next day."

[2619] Step 12:

[2620] Server: Based on the analysis results, it adjusts specific action suggestions according to the user's emotional state.

[2621] Step 13:

[2622] Device: Notifies the user of the proposed action plan and emotion-based adjustments, displaying details on the screen.

[2623] Step 14:

[2624] Users: Receive notifications and act on proposed action plans.

[2625] Step 15:

[2626] User: Enter data such as target weight, current weight, and photo.

[2627] Step 16:

[2628] Terminal: Sends the entered data to the server.

[2629] Step 17:

[2630] Server: Using image generation AI, generate what the user will look like after achieving their goal.

[2631] Step 18:

[2632] Device: Displays the generated image to the user and tells them, "This is what you will look like when you achieve your goal."

[2633] Step 19:

[2634] Users: Visualize what it will look like when they achieve their goals and increase their motivation.

[2635] Step 20:

[2636] Server: Generates diet-related tasks and assigns points to each task (e.g., 10 points for 10,000 steps).

[2637] Step 21:

[2638] Terminal: Notifies the user of the generated task and displays the task details.

[2639] Step 22:

[2640] User: Confirms and executes the task (e.g., walk 10,000 steps).

[2641] Step 23:

[2642] Terminal: Detects when the user completes a task and sends that information to the server.

[2643] Step 24:

[2644] Server: Receives task completion information and updates user points.

[2645] Step 25:

[2646] Terminal: Notify users of updated points and newly earned rewards.

[2647] Step 26:

[2648] User: Check the points and rewards earned and work on the next task.

[2649] Example 2

[2650] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2651] Conventional diet management systems were unable to take into account the user's emotional state, leading to a decline in motivation. Furthermore, behavioral suggestions and goal setting were general, without providing appropriate suggestions based on individual data, making it difficult to diet effectively. Furthermore, they lacked the functionality to provide users with a concrete image of what it would be like to achieve their goals, making it difficult to maintain sustained motivation.

[2652] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2653] In this invention, the server includes means for collecting and saving the user's initial setting data, means for collecting and saving the user's real-time data, means for analyzing the collected data and suggesting specific actions for the user to achieve their goals, means for notifying the user of the suggested actions, means for collecting and analyzing emotional data, means for generating messages and suggested actions to improve motivation based on the emotional data, means for generating an image of what the user will look like after achieving their goals, means for displaying the generated image to the user, means for tracking tasks completed by the user and managing points, and means for providing rewards to the user based on the point management. This makes it possible to provide appropriate suggested actions and motivational measures according to the user's emotional state, thereby supporting effective dieting.

[2654] "Means for collecting and storing user initial setting data" refers to a function that collects basic information such as weight, target weight, eating habits, and exercise habits that a user enters when using the diet management system for the first time, and stores this information in local storage and on the server.

[2655] "Means for collecting and storing real-time user data" refers to a function that collects data on exercise, sleep, diet, etc. obtained from the user's wearable device or smartphone in real time and stores it on a server.

[2656] "Means of analyzing collected data and suggesting specific actions to help users achieve their goals" refers to a function that uses AI models and algorithms based on collected data to generate and suggest specific actions, such as individual exercise plans and meal suggestions for each user.

[2657] "Means for notifying the user of the proposed action" is a function that notifies the user of the generated action suggestion on the user's device such as a smartphone or tablet.

[2658] "Means for collecting and analyzing emotional data" refers to a function that uses the user's camera or microphone to collect facial expressions and tone of voice, and analyzes this to identify the user's emotional state.

[2659] The "means for generating messages and suggested actions to improve motivation based on emotional data" is a function that generates messages and suggested actions to improve motivation, taking into account the user's emotional state, based on analyzed emotional data.

[2660] The "means for generating an image of what the user will look like after achieving their goal" is a function that uses the user's current weight and target weight as input data to generate an image of what the user will look like after achieving their goal.

[2661] "Means for displaying the generated image to the user" refers to a function that displays the generated image of the user after achieving the goal on a device such as a smartphone or tablet.

[2662] "A means for tracking tasks completed by users and managing points" refers to a function that detects exercise- and diet-related tasks that users have completed and assigns and manages the corresponding points.

[2663] The "means for providing rewards to users based on point management" is a function for providing rewards based on points earned by users.

[2664] MODE FOR CARRYING OUT THE INVENTION

[2665] The present invention is a system that recognizes a user's emotions and provides diet behavior suggestions and motivation improvement measures based on those emotions. The system is composed of the following components:

[2666] System configuration

[2667] 1. User device: A device such as a smartphone or tablet.

[2668] 2. Server: Cloud server or on-premise data server.

[2669] 3. Wearable devices: devices that collect user exercise and sleep data (e.g., smartwatches).

[2670] 4. Emotion Engine: Software for recognizing and analyzing the user's emotional state.

[2671] Program processing

[2672] 1. Collecting and saving initial setup data

[2673] The user installs the diet app and inputs basic information such as current weight, target weight, eating habits, and exercise habits when launching the app for the first time.

[2674] The terminal stores the collected initial setting data in a local storage and transmits it to the server.

[2675] The server analyzes the received initial setting data and stores it in a database.

[2676] 2. Real-time data collection and storage

[2677] The device collects real-time exercise, sleep, and diet data from the user's wearable device or smartphone.

[2678] The server stores the data received in real time in a database.

[2679] 3. Emotional Data Collection and Analysis

[2680] The device analyzes the user's facial expressions and tone of voice through a camera and microphone to collect emotional data.

[2681] The server analyzes the collected emotional data to determine the user's current emotional state.

[2682] The emotion engine uses emotional data to generate messages and suggested actions to improve user motivation.

[2683] 4. Data analysis and action proposals

[2684] The server analyzes the accumulated user data and emotional data and uses an AI model to create an action plan for the next day. For example, it generates a suggestion such as "walk 6,000 steps the next day" based on the data and emotional data from the past seven days.

[2685] The device notifies the user of the proposed plan of action.

[2686] The user receives a notification and acts on the proposed p...

Claims

1. A means for collecting and storing user preference data; A means of collecting and storing real-time user data; A means of analyzing the collected data and suggesting specific actions to help users achieve their goals; a means of informing the user of the proposed action; A means for generating an image of what the user will look like after achieving their goal; means for displaying the generated image to a user; A way for users to track completed tasks and manage points; a means for providing rewards to users based on point management; A system including:

2. 2. The system according to claim 1, wherein the user inputs information including current weight, target weight, dietary habits, and exercise habits as initial setting data.

3. The system of claim 1 , wherein the system collects exercise, sleep, and diet data in real time from a wearable device.

4. The system of claim 1, wherein the AI ​​model uses the collected data to create a plan of action for the user for the next day.

5. The system according to claim 1, which uses image generation AI to generate what the user will look like when they achieve their target weight.

6. The system according to claim 1, wherein points are awarded for tasks accomplished by a user, and a reward is provided based on the points.

7. The system according to claim 1, wherein a user can compete with other users for points.

Images