System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting health data and dietary history of a user; means for analyzing the collected health data and dietary history to generate an individually optimized diet menu; means for presenting the generated diet menu to the user; and means for collecting feedback from the user and updating the analysis results.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] With today's growing health consciousness and trend toward individualization, it is becoming increasingly important to eat meals with the optimal nutritional balance for each individual's health condition and lifestyle. However, conventional company cafeterias could only provide a uniform menu to all employees, which meant they were unable to accommodate each employee's individual health goals and dietary restrictions. Furthermore, companies found the retention rate of employee cafeteria users low, making stable management difficult. This invention aims to effectively support employee health management by providing individually optimized meals, thereby promoting the use of company cafeterias and ensuring stable management. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting a user's health data and dietary history, a means for analyzing the collected health data and dietary history to generate an individually optimized meal menu, a means for presenting the generated meal menu to the user, and a means for collecting feedback from the user and updating the analysis results. Furthermore, the present invention also includes a means for generating a meal menu that takes external factors into account based on the collected health data and dietary history, a means for filtering meal menus based on allergy information and dietary needs, a means for saving the health data and dietary history entered by the user and continuously learning from it, and a means for suggesting recipes for the user's home cooking. This makes it possible to provide each user with an optimized meal menu and support their daily health management.

[0006] "User Information" refers to data about a User's health, allergy information, preferences, lifestyle, and goals.

[0007] "Health data" refers to physiological information such as a user's weight, heart rate, number of steps, and sleep data.

[0008] "Diet history" refers to a record of the food a user has consumed, including the calories and nutrients.

[0009] "Collection means" refers to means for collecting user information, health data, and dietary history, such as answering questionnaires or inputting data from a wearable device.

[0010] "Analysis means" refers to the means for calculating the optimal meal menu for an individual's health condition and lifestyle based on collected data.

[0011] The "menu generation means" refers to a means for creating a meal menu optimized for each individual user based on the information calculated by the analysis means.

[0012] "Presentation means" refers to a means for presenting the generated meal menu to the user.

[0013] "Feedback collection means" refers to the means for collecting feedback from users and improving the system's analysis results and suggestions.

[0014] "External factors" refer to environmental conditions such as season, weather, and time of day.

[0015] "Allergy information" refers to information that a user has an allergy to a particular food.

[0016] "Diet needs" refers to the user's diet-related requirements such as weight management and calorie restriction.

[0017] "Filtering means" refers to a means for selecting suggested meal menus based on allergy information and dietary needs.

[0018] "Continuous learning measures" refer to measures for continually improving analysis algorithms based on user feedback and new data.

[0019] The "recipe suggestion means" refers to a means for suggesting recipes that can be used as reference when a user cooks at home. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a system that provides personalized optimal meals, and supports users' health management by collecting and analyzing their health data and dietary history, and proposing optimized meal menus based on the results. This system operates in cooperation with a server, terminals, and users.

[0042] Program processing overview

[0043] 1. Collection of User Information

[0044] The user launches the application, answers a questionnaire, and inputs health data from the wearable device.

[0045] The device transmits the collected data to the server in real time.

[0046] The server stores the received data and generates a user profile.

[0047] 2. AI-based learning of eating habits

[0048] Users take photos of their daily meals and upload them to the application.

[0049] The device sends the date and time information along with a photo of the meal to the server.

[0050] The server passes the received photos to AI for image analysis, extracting the type of food, calories, and key nutrients.

[0051] The server stores the analysis results in a database and updates the user's dietary history.

[0052] 3. Generate menu suggestions

[0053] The server generates an optimized meal menu based on the user's profile, meal history, and external factors (season, weather, time of day).

[0054] The terminal notifies the user of the proposed menu and displays it on the application.

[0055] 4. Collecting and analyzing feedback

[0056] After eating, users enter their taste and satisfaction in a feedback form.

[0057] The terminal sends this feedback to the server.

[0058] Based on the feedback received, the server updates the AI's learning data and further optimizes the next menu suggestion.

[0059] 5. Homemade recipe suggestions

[0060] The server generates home cooking recipes based on the user's data and sends them to the device.

[0061] The terminal notifies the user of the recipe and displays it on the application.

[0062] Specific examples

[0063] 1. Collection of User Information

[0064] When a user launches the application for the first time, they enter their age, gender, allergy information, and health goals (e.g., weight loss, muscle gain, etc.).

[0065] For example, if the user is a 40-year-old male with a goal of losing weight and is allergic to nuts, that information will be collected.

[0066] 2. Learning eating habits

[0067] A user eats salad and chicken for lunch and uploads a photo of it to the application, which also includes the date and time stamp.

[0068] The server analyzes this and extracts and stores data such as "salad," "chicken," and "500 kcal."

[0069] 3. Menu suggestions

[0070] The next day, the server analyzes the user's data and, taking into account their calorie goals and allergy information, suggests low-calorie, high-protein dishes such as "Konnyaku and Vegetable Simmered Dish" or "Grilled Chicken Salad."

[0071] 4. Feedback Collection

[0072] The user selects the suggested "grilled chicken salad" and eats it for lunch. After eating, the user enters their satisfaction with the meal and any areas for improvement into the application.

[0073] For example, provide feedback such as "there was too much chicken" or "the dressing was too watered down."

[0074] 5. Recipe suggestions

[0075] Taking into account the user's eating patterns and goals, the server suggests a "tofu steak recipe" for dinner, including instructions for grilling tofu to resemble steak and a list of the ingredients needed.

[0076] Users can access these recipes from the application and use them to prepare meals at home.

[0077] This system provides users with individually optimized meal menus, enabling them to efficiently manage their health. For companies, improving the health of their employees can lead to increased work efficiency and productivity.

[0078] The processing flow will be explained below.

[0079] Program processing steps

[0080] Step 1: Collect user information

[0081] 1. The user launches the application and accesses the initial registration screen.

[0082] 2. The device presents the user with questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects the responses.

[0083] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[0084] 4. The device sends the collected questionnaire answers and health data to the server in real time.

[0085] 5. The server stores the received data and generates an initial user profile.

[0086] Step 2: AI learns eating habits

[0087] 1. The user takes photos of their daily meals and uploads them to the application.

[0088] 2. The device sends the date and time information along with a photo of the meal to the server.

[0089] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[0090] 4. The server stores the extracted information in a database and updates the user's meal history.

[0091] Step 3: Generate menu suggestions

[0092] 1. The server generates an optimized meal menu based on the user's profile (health data and dietary history) and external factors (season, weather, time of day).

[0093] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[0094] 2. Based on the optimized menu, the server generates a daily menu list and sends it to the terminal.

[0095] 3. The device notifies the user of the proposed menu and displays it in the application.

[0096] Step 4: Collect and analyze feedback

[0097] 1. After the user selects the suggested menu and consumes the meal, the application displays a feedback form.

[0098] 2. Users enter information about the taste of the meal, their satisfaction, and areas for improvement in the feedback form.

[0099] 3. The device sends the input feedback to the server.

[0100] 4. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0101] Step 5: Homemade recipe suggestions

[0102] 1. The server generates recipes that can be easily made at home based on the user's profile and past meal data.

[0103] 2. The server sends the generated recipe information to the terminal.

[0104] 3. The device notifies the user of the recipe and displays it on the application.

[0105] 4. Users can check recipes through the application to help them cook at home.

[0106] Through these steps, users can receive individually optimized meal suggestions and efficiently manage their health. Companies can also maintain employee health and improve productivity by providing optimal meals based on employee health data.

[0107] Example 1

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

[0109] Health management has become increasingly important in recent years, but general dietary management systems often fail to provide meal menus that fully consider a user's individual health condition and dietary history. Furthermore, there is a lack of systems that appropriately reflect user feedback and continuously optimize meal menus. Furthermore, there is the challenge of providing recommended meal menus to users while taking into account allergy information and individual nutritional needs.

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

[0111] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for automatically synchronizing health data from the wearable device, means for analyzing food photos to extract nutritional information, means for customizing the menu based on the user's profile and external factors, and means for suggesting recipes that can be cooked at home. This makes it possible to provide an optimized diet menu based on the user's individual health condition and dietary history, and to continue improving the system based on continuous feedback.

[0112] "User's health data" refers to numerical information indicating the user's health condition, such as the user's age, gender, height, weight, heart rate, number of steps, and calories burned.

[0113] "Dietary history" refers to information such as the contents of meals the user has eaten in the past, photos, the date and time of eating, calories, nutrients, etc.

[0114] "Wearable device" refers to a device (e.g., smartwatch, fitness tracker) that is worn by the user to measure and collect health data.

[0115] "Meal menu" refers to information such as the contents, recipes, ingredients, calories, nutrients, etc. of the meals suggested for the user to consume.

[0116] "Feedback" refers to information such as opinions, satisfaction, and areas for improvement provided by users regarding the proposed meal menu.

[0117] "User profile" refers to data that compiles a user's personal information, health data, dietary history, allergy information, health goals, etc.

[0118] "Image analysis" refers to the use of AI to extract specific information from a photo, in this case, the type of food, calories, and macronutrients.

[0119] "External factors" refer to environmental factors that influence a user's food choices, such as season, weather, and time of day.

[0120] A "recipe" is a list of steps and ingredients needed to make a particular dish.

[0121] "Synchronizing" refers to multiple devices or systems sharing and updating the same data.

[0122] This invention is a system that provides a meal menu optimized for each user, and supports the user's health management. This system operates in cooperation with the user, terminal, and server.

[0123] Collection of User Information

[0124] Users first launch the application and enter basic health data such as age, gender, height, weight, health goals (weight loss, muscle gain, etc.), and allergy information. In addition, users sync data from their wearable devices (e.g., smartwatches, fitness trackers) with the application, including heart rate, steps, and calories burned. This data is immediately sent from the device to the server and saved as a user profile.

[0125] For example, a 40-year-old man launches the application, inputs that he weighs 70 kg and has a nut allergy, and provides data from his wearable device showing a heart rate of 70 bpm, 10,000 steps taken per day, and calories burned of 2,200 kcal.

[0126] Learning eating habits using AI

[0127] Users take photos of their daily meals and upload them to the app. The device then sends the photos of the meal along with the date and time information to a server. The server then uses AI to analyze the photos and extract the type of food, calories, and macronutrients (protein, fat, carbohydrates). The results of this analysis are stored in a database, and the user's diet history is updated.

[0128] For example, if a user has salad and chicken for lunch and uploads a photo of it, the server extracts and stores information such as "salad," "chicken," "500kcal," "protein 30g," "fat 10g," and "carbohydrates 40g" from the photo.

[0129] Generate menu suggestions

[0130] The server analyzes data based on the user's profile, meal history, and external factors (season, weather, time of day) to generate an optimized meal menu. The device notifies the user of this menu and displays it on the application.

[0131] For example, the server analyzes the user's data and suggests low-calorie, high-protein dishes such as "Konjac and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[0132] Collecting and analyzing feedback

[0133] After selecting a suggested menu and eating, the user enters their taste, satisfaction, and suggestions for improvement in a feedback form. The device then sends this feedback to the server. The server updates the AI's learning data based on the received feedback, further optimizing the next menu suggestion.

[0134] For example, a user can provide feedback such as "The grilled chicken was tasty, but it was a little bland," and the server can incorporate this information to improve its suggestions next time.

[0135] Homemade recipe suggestions

[0136] The server generates easy-to-make homemade recipes based on the user's data (health goals, dietary history, feedback), and the device notifies the user of the recipes and displays them in the application.

[0137] For example, the server generates a recipe (including ingredients and cooking steps) for making tofu steak for dinner, and the terminal notifies the user of this.

[0138] This invention allows users to efficiently manage their health by providing individually optimized meal menus and recipes, and also enables companies to manage the health status of their employees in an advanced manner, aiming to improve business efficiency and productivity.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1: Collect user information

[0141] Input: A user launches the application and enters their age, gender, height, weight, allergy information, and health goals (e.g., weight loss, muscle gain). Additionally, they sync data from their wearable device (e.g., smartwatch, fitness tracker) such as heart rate, steps, and calories burned.

[0142] Specific operation: The user enters information such as "40-year-old male, weight 70 kg, desire to lose weight, nut allergy" and synchronizes data such as "heart rate 70 bpm, 10,000 steps per day, calories burned 2,200 kcal" from the wearable device.

[0143] Data processing / data calculation: The device collects this information and sends it to the server in real time. The server stores the received data in a database and generates a user profile.

[0144] Output: A user profile is generated and stored on the server.

[0145] Step 2: Learn your eating habits

[0146] Input: Users take photos of their daily meals and upload them to the application.

[0147] What happens: A user uploads a photo of "salad and chicken" for lunch, with date and time information attached.

[0148] Data processing / data calculation: The device sends photos of the meal and date and time information to the server. The server then passes the photos to the AI ​​for image analysis. The AI ​​extracts the type of food, calories, and macronutrients (e.g., protein, fat, carbohydrates).

[0149] Output: The server saves the analysis results in a database and updates the user's food history. Data such as "Salad," "Chicken," "Calories 500kcal," "Protein 30g," "Fat 10g," and "Carbohydrates 40g" are saved.

[0150] Step 3: Generate menu suggestions

[0151] Input: The server analyzes the data based on the user's profile, food history, and external factors (season, weather, time of day).

[0152] Specific operation: The server performs an analysis based on the user's data ("40-year-old male aiming to lose weight") and "eating history of salad and chicken."

[0153] Data processing / data calculation: The server uses AI to generate an optimized meal menu, taking into account calories, allergy information, nutritional balance, etc.

[0154] Output: A suggested menu is generated. Possible options include "Konnyaku and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[0155] Specific operation: The generated menu is sent to the terminal and notified to the user.

[0156] Step 4: Collect and analyze feedback

[0157] Input: The user consumes the suggested menu and, after eating, enters their opinions, satisfaction, and suggestions for improvement in a feedback form on the application.

[0158] What happens: The user enters feedback like, "The grilled chicken was tasty, but it was a little bland."

[0159] Data processing / data calculation: The device sends feedback to the server, which updates the AI's learning data based on the received feedback.

[0160] Output: The server updates the data based on the feedback, and the next menu suggestions will be further optimized.

[0161] Step 5: Homemade recipe suggestions

[0162] Input: The server generates easy-to-make home-cooked recipes based on the user's profile, food history, and feedback.

[0163] Specific behavior: The server generates a "Tofu Steak Recipe (ingredients, cooking instructions)" for dinner.

[0164] Data processing / data calculation: The server selects recipes that suit the user's preferences and nutritional needs, and sends the generated recipes to the terminal.

[0165] Output: The recipe is notified to the user via the device and displayed in the application. Information such as "Tofu, grated daikon radish, soy sauce, cooking steps: 1. Fry the tofu..." is provided.

[0166] (Application example 1)

[0167] 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."

[0168] The main function of conventional dietary management systems is to collect users' health data and dietary history, but they are not sufficient in effectively utilizing this data to propose individually optimized dietary menus. Furthermore, there are only a limited number of systems that can collect user feedback and update analysis results to make more accurate proposals. Furthermore, there are issues with the inability to improve convenience and collect data in real time by utilizing smartphones, smart glasses, and wearable devices. There is a need to provide a system that can solve these issues and efficiently manage users' health.

[0169] 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.

[0170] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for collecting the user's health data in real time using a smartphone, smart glasses, or wearable device, means for analyzing the user's meal photos and extracting macronutrients, a generative AI model for generating a diet menu suited to the user's health goals based on the extracted data, and means for notifying the user's device of the generated menu, thereby enabling efficient health management for the user.

[0171] "User health data" refers to information related to the user's physical condition and health, and includes, for example, data such as heart rate, body temperature, blood pressure, blood sugar level, and sleep patterns.

[0172] "Dietary history" is a record of the meals a user has eaten, and includes information such as the type of meal, the time of intake, calories, and major nutrients.

[0173] "Means of collection" refers to devices or software for acquiring a user's health data and dietary history, such as smartphones, smart glasses, and wearable devices.

[0174] "Means for analysis" refers to technologies and methods for analyzing collected health data and dietary history to extract useful information, including, for example, AI algorithms and database management systems.

[0175] A "personally optimized meal menu" is a specific meal list that provides a meal plan that is best suited to the user based on the user's health condition and dietary history.

[0176] The "presentation means" refers to a device or method for informing the user of the generated meal menu, such as a smartphone app or a smart glasses display.

[0177] "Means for collecting feedback and updating analysis results" refers to methods for collecting opinions and impressions from users and using them to improve the system's analysis algorithms.

[0178] "Means of collecting data in real time" refers to technologies and devices that instantly acquire users' health data and reflect it directly in the system.

[0179] "Means for analyzing photos to extract key nutrients" includes technology that analyzes photos of meals taken by users to identify the nutrients and calories contained therein.

[0180] A "generative AI model" is an artificial intelligence algorithm that automatically generates optimal meal menus based on a user's health data and dietary history.

[0181] "Means for notifying the terminal" refers to techniques or methods for notifying the user of the generated meal menu, and includes, for example, push notifications to a smartphone or smart glasses.

[0182] The present invention is a system for efficiently managing a user's health, which operates in cooperation with a server, a terminal, and a user. Specifically, the system is implemented through the following process.

[0183] 1. Collection of User Information:

[0184] Hardware: Smartphones, smart glasses, wearable devices (e.g., Fitbit, Apple Watch)

[0185] Software: Health management app (e.g., Apple Health, GOOGLE FI (registered trademark))

[0186] Processing: The user launches the application and enters the required health data. Data is also automatically collected from the wearable device. This data is sent to the server in real time, and a user profile is generated.

[0187] 2. Learning eating habits:

[0188] Hardware: Smartphone camera

[0189] Software: Image analysis algorithms (e.g., OpenCV, TENSORFLOW®)

[0190] Processing: The user takes a photo of their meal and uploads it to the application. The server receives the photo and performs image analysis to extract macronutrients, which then updates the user's diet history database.

[0191] 3.Generate menu suggestions:

[0192] Hardware: Server

[0193] Software: Machine learning algorithms (e.g., PyTorch, scikit-learn)

[0194] Processing: The server uses machine learning algorithms to generate a personalized meal plan based on the user's health profile and dietary history. This plan is then sent to the user's device and displayed on the app.

[0195] 4. Feedback collection and analysis:

[0196] Hardware: Smartphone

[0197] Software: Database management system (e.g., PostgreSQL)

[0198] Processing: After the meal, the user provides feedback. They input their satisfaction and impressions of the meal via a smartphone application, which is then sent to the server. The server uses this feedback data to update its AI algorithm and further optimize the menu suggestions for the next meal.

[0199] Specific examples

[0200] For example, a user may have "salad and chicken" for lunch, take a photo of it with their smartphone, and upload it to the application. The server analyzes this meal data, extracts calories and key nutrients, and saves them as a meal history. The next day, the server will suggest "low-calorie, high-protein grilled chicken salad" based on the user's health profile and meal history. This suggestion is notified to the user's smartphone. After the user selects this menu and eats it, they can enter their satisfaction and impressions into the application. This feedback will further improve the next suggestion.

[0201] Prompt Sentence Examples

[0202] By inputting the following prompts into the generative AI model, we can generate the optimal meal menu:

[0203] Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from dietary history and suggest menus that are optimal for achieving health goals. Also, consider whether the menu is easy to prepare. The suggested menus will be notified to the user's smartphone.

[0204] In this way, a system for efficiently managing the user's health is realized.

[0205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0206] Step 1:

[0207] Collection of User Information

[0208] Input: Health data entered by the user (e.g., age, gender, allergy information, health goals) and real-time health data collected from wearable devices (e.g., heart rate, body temperature, blood pressure).

[0209] Processing: The user launches the application and inputs the necessary health data. Further health data is automatically collected from the wearable device. This data is then sent to the server in real time via the device.

[0210] Output: Generated user profile.

[0211] Step 2:

[0212] Learning eating habits

[0213] Input: A photo of a meal taken by the user and uploaded to the application.

[0214] Processing: The server receives the uploaded meal photos and uses image analysis algorithms (e.g., OpenCV, TensorFlow) to identify the ingredients and dishes in the photos and extract macronutrients (e.g., calories, protein, fat, carbohydrates).

[0215] Output: The analyzed dietary data is stored in a dietary history database.

[0216] Step 3:

[0217] Generate menu suggestions

[0218] Input: User's health profile and diet history data.

[0219] Processing: The server uses machine learning algorithms (e.g., PyTorch, scikit-learn) to generate an individually optimized meal menu based on the user's health data, dietary history, and external factors (e.g., season, weather, time of day). The generative AI model uses a prompt: "Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from the dietary history and suggest a menu that best suits the health goals. Also, consider whether the menu is easy to prepare. The suggested menu will be sent to the user's smartphone."

[0220] Output: The generated optimal meal menu.

[0221] Step 4:

[0222] Meal menu notifications

[0223] Input: The generated meal menu.

[0224] Processing: The server sends a push notification to the user's device (e.g., smartphone, smart glasses) with the generated meal menu.

[0225] Output: The meal menu is displayed on the user's device.

[0226] Step 5:

[0227] Collecting and analyzing feedback

[0228] Input: Feedback provided by the user after eating (e.g., satisfaction, areas for improvement, impressions).

[0229] Processing: The user enters feedback into the application and sends it to the server via the device. The server stores the received feedback in a database and uses it to update the AI ​​algorithm and optimize the next menu suggestions.

[0230] Output: The updated parsing algorithm.

[0231] Through these steps, users are provided with a consistently and individually optimized meal menu, enabling efficient health management. By using this system, users' health status can be improved and continuous improvement can be achieved.

[0232] 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.

[0233] This invention is a system that combines and analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, terminals, and users.

[0234] Program processing overview

[0235] 1. Collection of User Information

[0236] The user starts the application and accesses the initial registration screen.

[0237] The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[0238] Users answer questions and also input health data (heart rate, steps, sleep data, etc.) from their wearable device.

[0239] The device transmits the collected data to the server in real time.

[0240] The server stores the received data and generates an initial user profile.

[0241] 2. Collecting and analyzing emotion data

[0242] During everyday mealtimes, the user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine.

[0243] The device collects emotion data and sends it to the server along with date and time information.

[0244] The server stores the received emotion data and generates an emotion profile for the user.

[0245] 3. AI-based learning of eating habits

[0246] Users take photos of their daily meals and upload them to the application.

[0247] The device sends the date and time information along with a photo of the meal to the server.

[0248] The server passes the photo to AI for image analysis, extracting the type of food, calories, and key nutrients.

[0249] The server stores the analysis results in a database and updates the user's dietary history.

[0250] 4. Generate menu suggestions

[0251] The server generates an optimized meal menu based on the user's profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[0252] The terminal notifies the user of the proposed menu and displays it on the application.

[0253] 5. Collecting and analyzing feedback

[0254] After eating, the user uses the emotion engine to input their satisfaction with the meal and their emotional state.

[0255] The terminal transmits the feedback data to the server.

[0256] The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0257] 6. Homemade recipe suggestions

[0258] The server generates recipes that can be easily made at home based on the user's profile, dietary data, and emotional data.

[0259] The terminal notifies the user of the generated recipe and displays it on the application.

[0260] Users can check recipes from the application to help them cook at home.

[0261] Specific examples

[0262] 1. Collection of User Information

[0263] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., wanting to lose weight).

[0264] For example, if the user is a 30-year-old woman and wants to prevent diabetes, that information is collected.

[0265] 2. Collecting and analyzing emotion data

[0266] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using an emotion engine.

[0267] For example, a user inputs into the emotion engine, "I'm feeling stressed because things aren't going well at work."

[0268] 3. Learning eating habits

[0269] A user takes a photo of their lunch, "Salad and Grilled Chicken," and uploads it to the application.

[0270] The server analyzes this, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[0271] 4. Menu suggestions

[0272] The server takes into consideration the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect.

[0273] The terminal notifies the user of the proposed menu and displays it on the application.

[0274] 5. Collecting and analyzing feedback

[0275] The user selects the suggested "green tea and brown rice rice ball" and consumes it for lunch.

[0276] After eating, the emotion engine is used to input feedback such as "satisfied" or "stress reduced."

[0277] The terminal transmits the feedback data to the server.

[0278] 6. Recipe suggestions

[0279] The server considers that the user is looking for a "relaxing effect" and generates a recipe for "soup made with roasted green tea."

[0280] The terminal notifies the user of the recipe and displays it on the application.

[0281] Users can check the recipe through the application and make the soup at home.

[0282] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[0283] The processing flow will be explained below.

[0284] Program processing steps

[0285] Step 1: Collect user information

[0286] 1. The user launches the application and accesses the initial registration screen.

[0287] 2. The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[0288] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[0289] 4. The device sends the collected data to the server in real time.

[0290] 5. The server stores the received data and generates an initial user profile.

[0291] Step 2: Collect and analyze emotion data

[0292] 1. The user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine during everyday mealtimes.

[0293] 2. The device collects emotion data and sends it to the server along with date and time information.

[0294] 3. The server stores the received emotion data and generates an emotion profile for the user.

[0295] Step 3: AI learns eating habits

[0296] 1. The user takes photos of their daily meals and uploads them to the application.

[0297] 2. The device sends the date and time information along with a photo of the meal to the server.

[0298] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[0299] 4. The server stores the extracted information in a database and updates the user's meal history.

[0300] Step 4: Generate menu suggestions

[0301] 1. The server generates an optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day).

[0302] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[0303] 2. The server generates a daily menu list and sends it to the terminal.

[0304] 3. The device notifies the user of the proposed menu and displays it in the application.

[0305] Step 5: Collect and analyze feedback

[0306] 1. After the user selects the suggested menu and consumes the meal, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[0307] 2. The device sends the feedback data to the server.

[0308] 3. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0309] Step 6: Homemade recipe suggestions

[0310] 1. The server generates recipes that can be easily made at home based on the user's profile, past meal data, and emotional data.

[0311] 2. The server sends the generated recipe to the device.

[0312] 3. The device notifies the user of the recipe and displays it on the application.

[0313] 4. Users can check recipes from the application to help them cook at home.

[0314] Specific examples

[0315] Step 1: Collect user information

[0316] 1. The user launches the application for the first time and answers a questionnaire.

[0317] 2. The device sends the information collected from the user (age 30, female, nut allergy, weight loss goal) to the server.

[0318] 3. The server stores the data and generates a user profile.

[0319] Step 2: Collect and analyze emotion data

[0320] 1. The user inputs "I feel stressed" in the lunch scene using the emotion engine.

[0321] 2. The device sends the emotion data and date and time information to the server.

[0322] 3. The server stores the emotion data and generates an emotion profile for the user.

[0323] Step 3: AI learns eating habits

[0324] 1. A user eats "Salad and Grilled Chicken" for lunch, takes a photo, and uploads it to the application.

[0325] 2. The device sends a photo of the meal and date and time information to the server.

[0326] 3. The server uses AI to extract "salad," "grilled chicken," and "400 kcal" and stores them in a database.

[0327] Step 4: Generate menu suggestions

[0328] 1. The server takes into account the emotional data "stress" and generates a menu of "green tea and brown rice rice balls" that is expected to have a relaxing effect.

[0329] 2. The server sends the menu list to the terminal, and the terminal notifies the user of the menu.

[0330] Step 5: Collect and analyze feedback

[0331] 1. The user selects the suggested "rice ball with green tea and brown rice" and, after eating, uses the emotion engine to input feedback such as "satisfied" and "stress reduced."

[0332] 2. The device sends the feedback data to the server.

[0333] 3. The server analyzes the feedback and incorporates it into its next proposal.

[0334] Step 6: Homemade recipe suggestions

[0335] 1. The server generates a recipe called "Soup made with roasted green tea" that emphasizes its relaxing effect.

[0336] 2. The server sends the recipe to the terminal and notifies the user.

[0337] 3. User checks the recipe and makes the soup at home.

[0338] This system allows users to receive optimal meal menus based on their health data, dietary history, and emotional data. By taking emotional data into account, meal suggestions are made that take into account the user's psychological health, allowing for efficient individual health management.

[0339] Example 2

[0340] 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."

[0341] Health management is a very important issue in modern society, and many people are looking for ways to effectively manage their health. However, while conventional systems collect individual health data and dietary history, they are limited in their ability to comprehensively analyze this data and propose individually optimized meal menus. Furthermore, because they are limited to simple data analysis without considering emotional data or external factors, it is difficult to provide suggestions that are tailored to the user's psychological satisfaction or individual circumstances. Therefore, there is a need for multifaceted analysis of data and individually optimized meal suggestions in health management.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting health data, dietary history, and emotional data of the user, means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu, and means for presenting the generated meal menu to the user. This enables more accurate meal menu suggestions based on the individual circumstances of the user. In addition, by including means for inputting the user's emotional state in daily meal situations, means for generating meal menus taking external factors into consideration, means for learning the user's eating habits using AI and updating the meal history, and means for generating recipes that can be made at home, it becomes possible to realize more comprehensive health management that also takes the user's psychological health into consideration.

[0343] "Health data" refers to information related to the user's physical condition and physical status, and specifically includes heart rate, number of steps, sleep data, weight, blood pressure, etc.

[0344] "Diet history" is a record of meals the user has eaten in the past, and specifically includes information about the ingredients, types of food, calories, and nutrients eaten.

[0345] "Emotion data" is information that represents the user's psychological state during everyday mealtimes, and includes emotional states such as "satisfaction," "stress," and "happiness" that are input using the emotion engine.

[0346] "Optimized meal menu" refers to a meal plan that is generated to suit an individual user by analyzing the user's health data, dietary history, and emotional data.

[0347] "Feedback" refers to information users enter about their satisfaction and emotional state after a meal, data the system uses to improve its next menu suggestion.

[0348] "External factors" are environmental factors that are taken into consideration when generating a meal menu, and specifically include the season, weather, time of day, etc.

[0349] An "emotion engine" is an interface that allows users to input their emotional state and is a tool for collecting emotional data such as satisfaction and stress.

[0350] "Image analysis" refers to the technological process of analyzing photos of meals uploaded by users to extract the type of food, calories, and macronutrients.

[0351] "Homemade recipes" refer to suggestions of cooking steps and ingredients that users can easily make at home, and are generated based on health data and dietary history.

[0352] A "profile" is an individual collection of information generated by integrating a user's health data, dietary history, and emotional data, and refers to the basic data used by the system to make optimal suggestions to the user.

[0353] This invention is a system that analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, a terminal, and a user.

[0354] The system first has a means to collect the user's health data, dietary history, and emotional data. Specifically, the user launches the application and accesses the initial registration screen. The device presents the user with questions about their age, gender, allergy information, health goals, etc., which the user answers. The user also inputs health data (heart rate, number of steps, sleep data, etc.) from a wearable device (e.g., a smartwatch). The device transmits this collected data to a server in real time, and the server stores the received data and generates an initial user profile.

[0355] Next, emotional data is collected and analyzed. The user uses the emotion engine to input their emotional state (e.g., satisfaction, stress, happiness, etc.) during everyday mealtimes. The device collects the emotional data and sends it to the server along with date and time information. The server stores the received emotional data and generates an emotional profile for the user.

[0356] Another important feature is the AI's ability to learn eating habits. Users take photos of their daily meals and upload them to the application. The device then sends the photos of the meal along with the date and time information to the server. The server then analyzes the photos using image analysis tools (e.g., Google® Cloud Vision API) to extract data such as the type of food, calories, and macronutrients. The results of this analysis are stored in a database, and the user's eating history is updated.

[0357] Based on this data, the server generates an optimized meal menu taking into account the user profile (health data, dietary history, emotional data) and external factors (season, weather, time of day). The device notifies the user of the generated menu and displays it on the application.

[0358] Users can provide feedback after their meal by inputting their satisfaction with the meal and their emotional state using the emotion engine, and the device sends the feedback data to the server, which analyzes this feedback and stores it as learning data for the AI ​​to further optimize menu suggestions for the next time.

[0359] The server can also generate recipes that can be easily made at home based on the user profile, dietary data, and emotional data. The device notifies the user of the recipes and displays them on the application. The user can check the recipes through the application and use them to prepare meals at home.

[0360] Specific examples

[0361] 1. Collection of User Information

[0362] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., want to lose weight). For example, if the user is a 30-year-old woman who wants to prevent diabetes, that information is collected.

[0363] 2. Collecting and analyzing emotion data

[0364] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using the emotion engine. For example, the user might input, "I'm feeling stressed because things aren't going well at work."

[0365] 3. Learning eating habits

[0366] A user takes a photo of their lunch of "salad and grilled chicken" and uploads it to the app. The server analyzes the photo, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[0367] 4. Menu suggestions

[0368] The server takes into account the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect. The device notifies the user of the suggested menu and displays it on the application.

[0369] 5. Collecting and analyzing feedback

[0370] The user consumes the "green tea and brown rice rice ball" and uses the emotion engine to input feedback such as "satisfied" or "stress reduced." The device then sends the feedback data to the server.

[0371] 6. Recipe suggestions

[0372] The server generates a recipe for "soup using roasted green tea," taking into account the user's desire for a relaxing effect. The device notifies the user of the recipe and displays it on the application. The user then checks the recipe through the application and makes the soup at home.

[0373] Prompt Sentence Examples

[0374] "Please suggest the best lunch menu for a user who is a 30-year-old woman and has a health goal of preventing diabetes."

[0375] "Please suggest a menu that will have a relaxing effect on users who are feeling stressed from work during lunch."

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1: Collect user information

[0378] Input: The user launches the application for the first time, answers questions such as age, gender, allergy information, and health goals, and inputs health data from the wearable device.

[0379] Processing: The device collects the information entered by the user in real time and sends it to the server, which stores the received data and creates an initial user profile.

[0380] Output: A user profile is generated and stored on the server.

[0381] Specific operation: Questions such as "Please enter your age" and "Please select your gender" are displayed on the device screen, and the user answers accordingly. The smartwatch data is also linked to the app.

[0382] Step 2: Collect and analyze emotion data

[0383] Input: The user uses the emotion engine in everyday meal scenarios to input emotional states such as satisfaction, stress, and happiness.

[0384] Processing: The device collects emotion data and sends it to the server along with date and time information. The server stores the received emotion data and creates an emotion profile for the user.

[0385] Output: An emotional profile is generated and stored on the server.

[0386] Specific operation: After a meal, the message "How are you feeling right now?" appears on the device screen, and the user can select from options such as "Satisfied," "Stressed," or "Happy." Another example includes inputting "I'm feeling stressed because things aren't going well at work."

[0387] Step 3: AI learns eating habits

[0388] Input: The user takes photos of their daily meals and uploads the photos and date and time information to the application.

[0389] Processing: The device sends a photo of the meal and the date and time information to the server, which then uses image analysis tools (e.g., Google Cloud Vision API) to analyze the photo and extract the type of food, calories, and macronutrients.

[0390] Output: The analysis results are saved in a database and the user's diet history is updated.

[0391] Specific operation: A prompt appears saying "Please upload a photo of your meal." The user takes a photo of themselves eating "salad and grilled chicken" and uploads it. The server analyzes this and extracts data such as "salad," "grilled chicken," and "400 kcal."

[0392] Step 4: Generate menu suggestions

[0393] Input: User profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[0394] Processing: The server uses AI models to generate an optimized meal menu based on this data, taking into account external factors and making suggestions that match the user's emotional state.

[0395] Output: The generated meal menu is sent to the terminal and displayed to the user on the application.

[0396] Specific operation: The server selects "Green tea and brown rice onigiri" as the most suitable menu item, saying "Generating a menu with a relaxing effect..." The device then notifies the user, "We have the perfect menu item for you! 'Green tea and brown rice onigiri'."

[0397] Step 5: Collect and analyze feedback

[0398] Input: After the user consumes the proposed meal menu, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[0399] Processing: The device sends the feedback data to the server, which analyzes the feedback and stores it as learning data for the AI.

[0400] Output: Feedback is used to further optimize the next menu suggestion.

[0401] Specific operation: The user is satisfied after eating the "Green Tea and Brown Rice Rice Ball" and enters feedback such as "Satisfied" and "Stress reduced." The device displays the message "Sending feedback..." followed by "Sent."

[0402] Step 6: Homemade recipe suggestions

[0403] Input: User profile, dietary data, and emotional data.

[0404] Processing: The server uses this data to generate recipes that can be easily made at home. It also considers the user's emotional state and suggests optimal home-cooked recipes.

[0405] Output: The generated recipe is notified to the terminal and displayed to the user on the application.

[0406] Specific operation: The server generates a recipe for "soup using roasted green tea" with the message "Generating a recipe with a relaxing effect...". The device notifies the user, "A new recipe is available! 'Soup using roasted green tea'." The user checks the recipe through the application and makes the soup at home.

[0407] (Application example 2)

[0408] 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."

[0409] There are currently systems that collect and analyze health data, dietary history, and emotional data separately to suggest optimal meal menus. However, these systems are not linked to food delivery services, making it difficult for users to quickly obtain the suggested meals. Furthermore, they cannot suggest detailed menus that take into account emotional data and health goals, making it impossible to make qualitative suggestions that take psychological health into account. There is a need to solve these issues.

[0410] 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.

[0411] In this invention, the server includes means for collecting a user's health data, dietary history, and emotional data; means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu; means for presenting the generated meal menu to the user and delivering the suggested meals via a food delivery service; and means for collecting feedback from the user, updating the analysis results, and optimizing the next menu proposal. This makes it possible to quickly propose an optimal meal menu suitable for each user and actually deliver the meal. Furthermore, analysis results that take emotional data and external factors into account make it possible to realize high-quality meal proposals that take psychological health into consideration.

[0412] "Health data" is physical information collected through wearable devices and other health monitoring equipment, such as a user's heart rate, number of steps taken, and sleep duration.

[0413] "Dietary history" refers to information such as the contents, calories, and nutrients of the meals a user has eaten, and is a record collected through photographs or manual input.

[0414] "Emotional data" is information that represents the emotional state (e.g., satisfaction, stress, happiness) that a user feels while eating or engaging in an activity, and is data that is collected through manual input or an emotion engine.

[0415] An "individually optimized meal menu" is a meal suggestion generated based on collected health data, dietary history, and emotional data, taking into consideration the optimal nutritional balance and psychological satisfaction for the user.

[0416] "Food delivery service" refers to a delivery service that allows users to quickly obtain suggested meal menus, and is provided by affiliated restaurants and service providers.

[0417] "Feedback" refers to information that is used to input the user's feelings and level of satisfaction after eating, and to update the system's analysis results.

[0418] This invention is a system that collects and analyzes a user's health data, dietary history, and emotional data to provide an individually optimized meal menu, and can deliver meals to the user in cooperation with a food delivery service. Specific embodiments of this system are described below.

[0419] Hardware and Software

[0420] Hardware:

[0421] Smartphone: A device where the user enters data and views menu suggestions.

[0422] Wearable devices (e.g., Apple Watch, Fitbit): devices that collect health data such as a user's heart rate, number of steps, and sleep duration.

[0423] Server: A device for storing collected data, analyzing it, generating menus and processing feedback.

[0424] Network: A communications network for data communication between smartphones, wearable devices, and servers.

[0425] software:

[0426] Mobile application: An application for users to perform initial registration, data entry, menu browsing, emotion data entry, and feedback entry.

[0427] Emotion engine: Software for collecting and analyzing user emotion data.

[0428] Image analysis AI: An AI algorithm that analyzes food photos uploaded by users and extracts the food content and nutrients.

[0429] Server software: Software that stores and analyzes data, generates personalized optimization menus, and collects feedback.

[0430] Data processing and calculation

[0431] User Information Collection:

[0432] Users launch the application using their smartphone and access the initial registration screen. They enter their age, gender, allergy information, health goals, etc., and provide health data from their wearable device. This data is sent to the server in real time and stored.

[0433] Emotion data collection:

[0434] The user inputs their emotional state during daily mealtimes using the emotion engine, and sends the emotional data along with date and time information to the server. The server analyzes the received emotional data and generates an emotional profile for the user.

[0435] Learning eating habits:

[0436] Users take photos of their daily meals and upload them to the application. The server passes the photos to an image analysis AI, which extracts the type of food, calories, and macronutrients. The analysis results are saved as the user's diet history.

[0437] Generate menu suggestions:

[0438] The server generates an individually optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day). The suggested menu is notified to the user via a smartphone application. When the user selects a suggested menu, the meal is delivered via a food delivery service.

[0439] Collecting and analyzing feedback:

[0440] After eating, users input their satisfaction and emotional state using the emotion engine, and this feedback data is sent to the server, analyzed, and used to optimize menu suggestions for future meals.

[0441] Specific examples

[0442] Examples:

[0443] 1. User Information Collection:

[0444] A 30-year-old female user enters her food allergies and health goal (muscle gain) when registering for the first time.

[0445] 2. Health Data Collection:

[0446] Fitbit sends data such as heart rate, steps, and sleep time to the app in real time.

[0447] 3. Emotional Data Collection:

[0448] A user who is feeling stressed because things aren't going well at work enters emotional data into the app.

[0449] 4. Dietary Data Collection:

[0450] Take a photo of your lunch of "salad and salmon fillet" and upload it to the app.

[0451] 5. Menu suggestions:

[0452] The AI ​​analyzes the situation and suggests "hot pot with roasted green tea and plenty of vegetables," which helps reduce stress.

[0453] 6. Food delivery orders:

[0454] Order the suggested menu with one click and have it delivered within 30 minutes.

[0455] 7. Feedback Collection:

[0456] After eating, the participants enter feedback such as "satisfied" and "stress reduced."

[0457] Example prompt sentence:

[0458] The user enters that she is a 30-year-old woman, has no allergies, and her health goal is to gain muscle.

[0459] The wearable device collected real-time data including 120 heart rates, 8,000 steps, and 7 hours of sleep.

[0460] A user inputs emotional data such as "I'm feeling stressed at work." He uploads a photo of himself eating "salad and salmon fillet" for lunch.

[0461] The AI ​​analyzed the data and recommended "Hot Pot with Roasted Green Tea and Lots of Vegetables" to the user. The user ordered the menu with one click and it was delivered in 30 minutes.

[0462] After eating, the user entered feedback such as "I feel satisfied" and "My stress has been reduced."

[0463] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1: Collect user information

[0466] Users launch the smartphone app and access the initial registration screen, where they enter basic information such as age, gender, allergy information, and health goals. The entered information is sent via the device to a server, which then stores the data and creates a user profile.

[0467] Input: Age, Gender, Allergy Information, Health Goals

[0468] Output: User profile stored on the server

[0469] Step 2: Collecting health data

[0470] When a user uses a wearable device (e.g., Fitbit) to go about their daily life, health data such as heart rate, number of steps, and sleep time are collected in real time. This data is sent to a server via the smartphone, and the server adds and stores this data in the user profile.

[0471] Input: Health data from wearable devices

[0472] Output: Updated user profile stored on the server

[0473] Step 3: Collecting emotion data

[0474] After each meal, users input their emotional state (e.g., satisfaction, stress, happiness) using a smartphone app. This emotional data, along with date and time information, is sent to a server, which then generates an emotional profile for the user.

[0475] Input: Date and time information, emotion data

[0476] Output: Emotion profile stored on the server

[0477] Step 4: Collect dietary data

[0478] Users take photos of their daily meals with their smartphones and upload them to the application. The device then sends the photo data to a server, which uses image analysis AI to extract the type of food, calories, and key nutrients from the photo. The extracted data is then saved on the server as the user's diet history.

[0479] Input: Food photo

[0480] Output: Meal history stored on the server

[0481] Step 5: Generate menu suggestions

[0482] The server integrates the user's health data, dietary history, emotional data, and external factors (season, weather, time of day) and uses a generative AI model to generate an individually optimized meal menu, which is then sent to the user via a smartphone application.

[0483] Input: Health data, diet history, emotional data, external factors

[0484] Output: Suggested meal menu

[0485] Step 6: Order food delivery

[0486] When the user checks and selects the meal menu on the smartphone application, the server sends the order information to the partner food delivery service, which then prepares the specified menu and delivers it to the user.

[0487] Input: Selected meal menu

[0488] Output: Delivered meal

[0489] Step 7: Collect and analyze feedback

[0490] After a meal, users use a smartphone app to input feedback about their satisfaction with the meal and their emotional state. The device then sends the feedback data to a server, which analyzes the data and uses it to suggest new menu items for the next meal.

[0491] Input: Feedback data (satisfaction and emotional state)

[0492] Output: Analysis results saved on the server (reflected in the next menu suggestion)

[0493] 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.

[0494] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0495] 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.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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).

[0503] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0508] 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."

[0509] This invention is a system that provides personalized optimal meals, and supports users' health management by collecting and analyzing their health data and dietary history, and proposing optimized meal menus based on the results. This system operates in cooperation with a server, terminals, and users.

[0510] Program processing overview

[0511] 1. Collection of User Information

[0512] The user launches the application, answers a questionnaire, and inputs health data from the wearable device.

[0513] The device transmits the collected data to the server in real time.

[0514] The server stores the received data and generates a user profile.

[0515] 2. AI-based learning of eating habits

[0516] Users take photos of their daily meals and upload them to the application.

[0517] The device sends the date and time information along with a photo of the meal to the server.

[0518] The server passes the received photos to AI for image analysis, extracting the type of food, calories, and key nutrients.

[0519] The server stores the analysis results in a database and updates the user's dietary history.

[0520] 3. Generate menu suggestions

[0521] The server generates an optimized meal menu based on the user's profile, meal history, and external factors (season, weather, time of day).

[0522] The terminal notifies the user of the proposed menu and displays it on the application.

[0523] 4. Collecting and analyzing feedback

[0524] After eating, users enter their taste and satisfaction in a feedback form.

[0525] The terminal sends this feedback to the server.

[0526] Based on the feedback received, the server updates the AI's learning data and further optimizes the next menu suggestion.

[0527] 5. Homemade recipe suggestions

[0528] The server generates home cooking recipes based on the user's data and sends them to the device.

[0529] The terminal notifies the user of the recipe and displays it on the application.

[0530] Specific examples

[0531] 1. Collection of User Information

[0532] When a user launches the application for the first time, they enter their age, gender, allergy information, and health goals (e.g., weight loss, muscle gain, etc.).

[0533] For example, if the user is a 40-year-old male with a goal of losing weight and is allergic to nuts, that information will be collected.

[0534] 2. Learning eating habits

[0535] A user eats salad and chicken for lunch and uploads a photo of it to the application, which also includes the date and time stamp.

[0536] The server analyzes this and extracts and stores data such as "salad," "chicken," and "500 kcal."

[0537] 3. Menu suggestions

[0538] The next day, the server analyzes the user's data and, taking into account their calorie goals and allergy information, suggests low-calorie, high-protein dishes such as "Konnyaku and Vegetable Simmered Dish" or "Grilled Chicken Salad."

[0539] 4. Feedback Collection

[0540] The user selects the suggested "grilled chicken salad" and eats it for lunch. After eating, the user enters their satisfaction with the meal and any areas for improvement into the application.

[0541] For example, provide feedback such as "there was too much chicken" or "the dressing was too watered down."

[0542] 5. Recipe suggestions

[0543] Taking into account the user's eating patterns and goals, the server suggests a "tofu steak recipe" for dinner, including instructions for grilling tofu to resemble steak and a list of the ingredients needed.

[0544] Users can access these recipes from the application and use them to prepare meals at home.

[0545] This system provides users with individually optimized meal menus, enabling them to efficiently manage their health. For companies, improving the health of their employees can lead to increased work efficiency and productivity.

[0546] The processing flow will be explained below.

[0547] Program processing steps

[0548] Step 1: Collect user information

[0549] 1. The user launches the application and accesses the initial registration screen.

[0550] 2. The device presents the user with questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects the responses.

[0551] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[0552] 4. The device sends the collected questionnaire answers and health data to the server in real time.

[0553] 5. The server stores the received data and generates an initial user profile.

[0554] Step 2: AI learns eating habits

[0555] 1. The user takes photos of their daily meals and uploads them to the application.

[0556] 2. The device sends the date and time information along with a photo of the meal to the server.

[0557] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[0558] 4. The server stores the extracted information in a database and updates the user's meal history.

[0559] Step 3: Generate menu suggestions

[0560] 1. The server generates an optimized meal menu based on the user's profile (health data and dietary history) and external factors (season, weather, time of day).

[0561] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[0562] 2. Based on the optimized menu, the server generates a daily menu list and sends it to the terminal.

[0563] 3. The device notifies the user of the proposed menu and displays it in the application.

[0564] Step 4: Collect and analyze feedback

[0565] 1. After the user selects the suggested menu and consumes the meal, the application displays a feedback form.

[0566] 2. Users enter information about the taste of the meal, their satisfaction, and areas for improvement in the feedback form.

[0567] 3. The device sends the input feedback to the server.

[0568] 4. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0569] Step 5: Homemade recipe suggestions

[0570] 1. The server generates recipes that can be easily made at home based on the user's profile and past meal data.

[0571] 2. The server sends the generated recipe information to the terminal.

[0572] 3. The device notifies the user of the recipe and displays it on the application.

[0573] 4. Users can check recipes through the application to help them cook at home.

[0574] Through these steps, users can receive individually optimized meal suggestions and efficiently manage their health. Companies can also maintain employee health and improve productivity by providing optimal meals based on employee health data.

[0575] Example 1

[0576] 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."

[0577] Health management has become increasingly important in recent years, but general dietary management systems often fail to provide meal menus that fully consider a user's individual health condition and dietary history. Furthermore, there is a lack of systems that appropriately reflect user feedback and continuously optimize meal menus. Furthermore, there is the challenge of providing recommended meal menus to users while taking into account allergy information and individual nutritional needs.

[0578] 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.

[0579] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for automatically synchronizing health data from the wearable device, means for analyzing food photos to extract nutritional information, means for customizing the menu based on the user's profile and external factors, and means for suggesting recipes that can be cooked at home. This makes it possible to provide an optimized diet menu based on the user's individual health condition and dietary history, and to continue improving the system based on continuous feedback.

[0580] "User's health data" refers to numerical information indicating the user's health condition, such as the user's age, gender, height, weight, heart rate, number of steps, and calories burned.

[0581] "Dietary history" refers to information such as the contents of meals the user has eaten in the past, photos, the date and time of eating, calories, nutrients, etc.

[0582] "Wearable device" refers to a device (e.g., smartwatch, fitness tracker) that is worn by the user to measure and collect health data.

[0583] "Meal menu" refers to information such as the contents, recipes, ingredients, calories, nutrients, etc. of the meals suggested for the user to consume.

[0584] "Feedback" refers to information such as opinions, satisfaction, and areas for improvement provided by users regarding the proposed meal menu.

[0585] "User profile" refers to data that compiles a user's personal information, health data, dietary history, allergy information, health goals, etc.

[0586] "Image analysis" refers to the use of AI to extract specific information from a photo, in this case, the type of food, calories, and macronutrients.

[0587] "External factors" refer to environmental factors that influence a user's food choices, such as season, weather, and time of day.

[0588] A "recipe" is a list of steps and ingredients needed to make a particular dish.

[0589] "Synchronizing" refers to multiple devices or systems sharing and updating the same data.

[0590] This invention is a system that provides a meal menu optimized for each user, and supports the user's health management. This system operates in cooperation with the user, terminal, and server.

[0591] Collection of User Information

[0592] Users first launch the application and enter basic health data such as age, gender, height, weight, health goals (weight loss, muscle gain, etc.), and allergy information. In addition, users sync data from their wearable devices (e.g., smartwatches, fitness trackers) with the application, including heart rate, steps, and calories burned. This data is immediately sent from the device to the server and saved as a user profile.

[0593] For example, a 40-year-old man launches the application, inputs that he weighs 70 kg and has a nut allergy, and provides data from his wearable device showing a heart rate of 70 bpm, 10,000 steps taken per day, and calories burned of 2,200 kcal.

[0594] Learning eating habits using AI

[0595] Users take photos of their daily meals and upload them to the app. The device then sends the photos of the meal along with the date and time information to a server. The server then uses AI to analyze the photos and extract the type of food, calories, and macronutrients (protein, fat, carbohydrates). The results of this analysis are stored in a database, and the user's diet history is updated.

[0596] For example, if a user has salad and chicken for lunch and uploads a photo of it, the server extracts and stores information such as "salad," "chicken," "500kcal," "protein 30g," "fat 10g," and "carbohydrates 40g" from the photo.

[0597] Generate menu suggestions

[0598] The server analyzes data based on the user's profile, meal history, and external factors (season, weather, time of day) to generate an optimized meal menu. The device notifies the user of this menu and displays it on the application.

[0599] For example, the server analyzes the user's data and suggests low-calorie, high-protein dishes such as "Konjac and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[0600] Collecting and analyzing feedback

[0601] After selecting a suggested menu and eating, the user enters their taste, satisfaction, and suggestions for improvement in a feedback form. The device then sends this feedback to the server. The server updates the AI's learning data based on the received feedback, further optimizing the next menu suggestion.

[0602] For example, a user can provide feedback such as "The grilled chicken was tasty, but it was a little bland," and the server can incorporate this information to improve its suggestions next time.

[0603] Homemade recipe suggestions

[0604] The server generates easy-to-make homemade recipes based on the user's data (health goals, dietary history, feedback), and the device notifies the user of the recipes and displays them in the application.

[0605] For example, the server generates a recipe (including ingredients and cooking steps) for making tofu steak for dinner, and the terminal notifies the user of this.

[0606] This invention allows users to efficiently manage their health by providing individually optimized meal menus and recipes, and also enables companies to manage the health status of their employees in an advanced manner, aiming to improve business efficiency and productivity.

[0607] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0608] Step 1: Collect user information

[0609] Input: A user launches the application and enters their age, gender, height, weight, allergy information, and health goals (e.g., weight loss, muscle gain). Additionally, they sync data from their wearable device (e.g., smartwatch, fitness tracker) such as heart rate, steps, and calories burned.

[0610] Specific operation: The user enters information such as "40-year-old male, weight 70 kg, desire to lose weight, nut allergy" and synchronizes data such as "heart rate 70 bpm, 10,000 steps per day, calories burned 2,200 kcal" from the wearable device.

[0611] Data processing / data calculation: The device collects this information and sends it to the server in real time. The server stores the received data in a database and generates a user profile.

[0612] Output: A user profile is generated and stored on the server.

[0613] Step 2: Learn your eating habits

[0614] Input: Users take photos of their daily meals and upload them to the application.

[0615] What happens: A user uploads a photo of "salad and chicken" for lunch, with date and time information attached.

[0616] Data processing / data calculation: The device sends photos of the meal and date and time information to the server. The server then passes the photos to the AI ​​for image analysis. The AI ​​extracts the type of food, calories, and macronutrients (e.g., protein, fat, carbohydrates).

[0617] Output: The server saves the analysis results in a database and updates the user's food history. Data such as "Salad," "Chicken," "Calories 500kcal," "Protein 30g," "Fat 10g," and "Carbohydrates 40g" are saved.

[0618] Step 3: Generate menu suggestions

[0619] Input: The server analyzes the data based on the user's profile, food history, and external factors (season, weather, time of day).

[0620] Specific operation: The server performs an analysis based on the user's data ("40-year-old male aiming to lose weight") and "eating history of salad and chicken."

[0621] Data processing / data calculation: The server uses AI to generate an optimized meal menu, taking into account calories, allergy information, nutritional balance, etc.

[0622] Output: A suggested menu is generated. Possible options include "Konnyaku and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[0623] Specific operation: The generated menu is sent to the terminal and notified to the user.

[0624] Step 4: Collect and analyze feedback

[0625] Input: The user consumes the suggested menu and, after eating, enters their opinions, satisfaction, and suggestions for improvement in a feedback form on the application.

[0626] What happens: The user enters feedback like, "The grilled chicken was tasty, but it was a little bland."

[0627] Data processing / data calculation: The device sends feedback to the server, which updates the AI's learning data based on the received feedback.

[0628] Output: The server updates the data based on the feedback, and the next menu suggestions will be further optimized.

[0629] Step 5: Homemade recipe suggestions

[0630] Input: The server generates easy-to-make home-cooked recipes based on the user's profile, food history, and feedback.

[0631] Specific behavior: The server generates a "Tofu Steak Recipe (ingredients, cooking instructions)" for dinner.

[0632] Data processing / data calculation: The server selects recipes that suit the user's preferences and nutritional needs, and sends the generated recipes to the terminal.

[0633] Output: The recipe is notified to the user via the device and displayed in the application. Information such as "Tofu, grated daikon radish, soy sauce, cooking steps: 1. Fry the tofu..." is provided.

[0634] (Application example 1)

[0635] 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."

[0636] The main function of conventional dietary management systems is to collect users' health data and dietary history, but they are not sufficient in effectively utilizing this data to propose individually optimized dietary menus. Furthermore, there are only a limited number of systems that can collect user feedback and update analysis results to make more accurate proposals. Furthermore, there are issues with the inability to improve convenience and collect data in real time by utilizing smartphones, smart glasses, and wearable devices. There is a need to provide a system that can solve these issues and efficiently manage users' health.

[0637] 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.

[0638] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for collecting the user's health data in real time using a smartphone, smart glasses, or wearable device, means for analyzing the user's meal photos and extracting macronutrients, a generative AI model for generating a diet menu suited to the user's health goals based on the extracted data, and means for notifying the user's device of the generated menu, thereby enabling efficient health management for the user.

[0639] "User health data" refers to information related to the user's physical condition and health, and includes, for example, data such as heart rate, body temperature, blood pressure, blood sugar level, and sleep patterns.

[0640] "Dietary history" is a record of the meals a user has eaten, and includes information such as the type of meal, the time of intake, calories, and major nutrients.

[0641] "Means of collection" refers to devices or software for acquiring a user's health data and dietary history, such as smartphones, smart glasses, and wearable devices.

[0642] "Means for analysis" refers to technologies and methods for analyzing collected health data and dietary history to extract useful information, including, for example, AI algorithms and database management systems.

[0643] A "personally optimized meal menu" is a specific meal list that provides a meal plan that is best suited to the user based on the user's health condition and dietary history.

[0644] The "presentation means" refers to a device or method for informing the user of the generated meal menu, such as a smartphone app or a smart glasses display.

[0645] "Means for collecting feedback and updating analysis results" refers to methods for collecting opinions and impressions from users and using them to improve the system's analysis algorithms.

[0646] "Means of collecting data in real time" refers to technologies and devices that instantly acquire users' health data and reflect it directly in the system.

[0647] "Means for analyzing photos to extract key nutrients" includes technology that analyzes photos of meals taken by users to identify the nutrients and calories contained therein.

[0648] A "generative AI model" is an artificial intelligence algorithm that automatically generates optimal meal menus based on a user's health data and dietary history.

[0649] "Means for notifying the terminal" refers to techniques or methods for notifying the user of the generated meal menu, and includes, for example, push notifications to a smartphone or smart glasses.

[0650] The present invention is a system for efficiently managing a user's health, which operates in cooperation with a server, a terminal, and a user. Specifically, the system is implemented through the following process.

[0651] 1. Collection of User Information:

[0652] Hardware: Smartphones, smart glasses, wearable devices (e.g., Fitbit, Apple Watch)

[0653] Software: Health management apps (e.g., Apple Health, GOOGLE FIT (registered trademark))

[0654] Processing: The user launches the application and enters the required health data. Data is also automatically collected from the wearable device. This data is sent to the server in real time, and a user profile is generated.

[0655] 2. Learning eating habits:

[0656] Hardware: Smartphone camera

[0657] Software: Image analysis algorithms (e.g., OpenCV, TensorFlow)

[0658] Processing: The user takes a photo of their meal and uploads it to the application. The server receives the photo and performs image analysis to extract macronutrients, which then updates the user's diet history database.

[0659] 3.Generate menu suggestions:

[0660] Hardware: Server

[0661] Software: Machine learning algorithms (e.g., PyTorch, scikit-learn)

[0662] Processing: The server uses machine learning algorithms to generate a personalized meal plan based on the user's health profile and dietary history. This plan is then sent to the user's device and displayed on the app.

[0663] 4. Feedback collection and analysis:

[0664] Hardware: Smartphone

[0665] Software: Database management system (e.g., PostgreSQL)

[0666] Processing: After the meal, the user provides feedback. They input their satisfaction and impressions of the meal via a smartphone application, which is then sent to the server. The server uses this feedback data to update its AI algorithm and further optimize the menu suggestions for the next meal.

[0667] Specific examples

[0668] For example, a user may have "salad and chicken" for lunch, take a photo of it with their smartphone, and upload it to the application. The server analyzes this meal data, extracts calories and key nutrients, and saves them as a meal history. The next day, the server will suggest "low-calorie, high-protein grilled chicken salad" based on the user's health profile and meal history. This suggestion is notified to the user's smartphone. After the user selects this menu and eats it, they can enter their satisfaction and impressions into the application. This feedback will further improve the next suggestion.

[0669] Prompt Sentence Examples

[0670] By inputting the following prompts into the generative AI model, we can generate the optimal meal menu:

[0671] Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from dietary history and suggest menus that are optimal for achieving health goals. Also, consider whether the menu is easy to prepare. The suggested menus will be notified to the user's smartphone.

[0672] In this way, a system for efficiently managing the user's health is realized.

[0673] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0674] Step 1:

[0675] Collection of User Information

[0676] Input: Health data entered by the user (e.g., age, gender, allergy information, health goals) and real-time health data collected from wearable devices (e.g., heart rate, body temperature, blood pressure).

[0677] Processing: The user launches the application and inputs the necessary health data. Further health data is automatically collected from the wearable device. This data is then sent to the server in real time via the device.

[0678] Output: Generated user profile.

[0679] Step 2:

[0680] Learning eating habits

[0681] Input: A photo of a meal taken by the user and uploaded to the application.

[0682] Processing: The server receives the uploaded meal photos and uses image analysis algorithms (e.g., OpenCV, TensorFlow) to identify the ingredients and dishes in the photos and extract macronutrients (e.g., calories, protein, fat, carbohydrates).

[0683] Output: The analyzed dietary data is stored in a dietary history database.

[0684] Step 3:

[0685] Generate menu suggestions

[0686] Input: User's health profile and diet history data.

[0687] Processing: The server uses machine learning algorithms (e.g., PyTorch, scikit-learn) to generate an individually optimized meal menu based on the user's health data, dietary history, and external factors (e.g., season, weather, time of day). The generative AI model uses a prompt: "Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from the dietary history and suggest a menu that best suits the health goals. Also, consider whether the menu is easy to prepare. The suggested menu will be sent to the user's smartphone."

[0688] Output: The generated optimal meal menu.

[0689] Step 4:

[0690] Meal menu notifications

[0691] Input: The generated meal menu.

[0692] Processing: The server sends a push notification to the user's device (e.g., smartphone, smart glasses) with the generated meal menu.

[0693] Output: The meal menu is displayed on the user's device.

[0694] Step 5:

[0695] Collecting and analyzing feedback

[0696] Input: Feedback provided by the user after eating (e.g., satisfaction, areas for improvement, impressions).

[0697] Processing: The user enters feedback into the application and sends it to the server via the device. The server stores the received feedback in a database and uses it to update the AI ​​algorithm and optimize the next menu suggestions.

[0698] Output: The updated parsing algorithm.

[0699] Through these steps, users are provided with a consistently and individually optimized meal menu, enabling efficient health management. By using this system, users' health status can be improved and continuous improvement can be achieved.

[0700] 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.

[0701] This invention is a system that combines and analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, terminals, and users.

[0702] Program processing overview

[0703] 1. Collection of User Information

[0704] The user starts the application and accesses the initial registration screen.

[0705] The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[0706] Users answer questions and also input health data (heart rate, steps, sleep data, etc.) from their wearable device.

[0707] The device transmits the collected data to the server in real time.

[0708] The server stores the received data and generates an initial user profile.

[0709] 2. Collecting and analyzing emotion data

[0710] During everyday mealtimes, the user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine.

[0711] The device collects emotion data and sends it to the server along with date and time information.

[0712] The server stores the received emotion data and generates an emotion profile for the user.

[0713] 3. AI-based learning of eating habits

[0714] Users take photos of their daily meals and upload them to the application.

[0715] The device sends the date and time information along with a photo of the meal to the server.

[0716] The server passes the photo to AI for image analysis, extracting the type of food, calories, and key nutrients.

[0717] The server stores the analysis results in a database and updates the user's dietary history.

[0718] 4. Generate menu suggestions

[0719] The server generates an optimized meal menu based on the user's profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[0720] The terminal notifies the user of the proposed menu and displays it on the application.

[0721] 5. Collecting and analyzing feedback

[0722] After eating, the user uses the emotion engine to input their satisfaction with the meal and their emotional state.

[0723] The terminal transmits the feedback data to the server.

[0724] The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0725] 6. Homemade recipe suggestions

[0726] The server generates recipes that can be easily made at home based on the user's profile, dietary data, and emotional data.

[0727] The terminal notifies the user of the generated recipe and displays it on the application.

[0728] Users can check recipes from the application to help them cook at home.

[0729] Specific examples

[0730] 1. Collection of User Information

[0731] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., wanting to lose weight).

[0732] For example, if the user is a 30-year-old woman and wants to prevent diabetes, that information is collected.

[0733] 2. Collecting and analyzing emotion data

[0734] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using an emotion engine.

[0735] For example, a user inputs into the emotion engine, "I'm feeling stressed because things aren't going well at work."

[0736] 3. Learning eating habits

[0737] A user takes a photo of their lunch, "Salad and Grilled Chicken," and uploads it to the application.

[0738] The server analyzes this, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[0739] 4. Menu suggestions

[0740] The server takes into consideration the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect.

[0741] The terminal notifies the user of the proposed menu and displays it on the application.

[0742] 5. Collecting and analyzing feedback

[0743] The user selects the suggested "green tea and brown rice rice ball" and consumes it for lunch.

[0744] After eating, the emotion engine is used to input feedback such as "satisfied" or "stress reduced."

[0745] The terminal transmits the feedback data to the server.

[0746] 6. Recipe suggestions

[0747] The server considers that the user is looking for a "relaxing effect" and generates a recipe for "soup made with roasted green tea."

[0748] The terminal notifies the user of the recipe and displays it on the application.

[0749] Users can check the recipe through the application and make the soup at home.

[0750] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[0751] The processing flow will be explained below.

[0752] Program processing steps

[0753] Step 1: Collect user information

[0754] 1. The user launches the application and accesses the initial registration screen.

[0755] 2. The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[0756] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[0757] 4. The device sends the collected data to the server in real time.

[0758] 5. The server stores the received data and generates an initial user profile.

[0759] Step 2: Collect and analyze emotion data

[0760] 1. The user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine during everyday mealtimes.

[0761] 2. The device collects emotion data and sends it to the server along with date and time information.

[0762] 3. The server stores the received emotion data and generates an emotion profile for the user.

[0763] Step 3: AI learns eating habits

[0764] 1. The user takes photos of their daily meals and uploads them to the application.

[0765] 2. The device sends the date and time information along with a photo of the meal to the server.

[0766] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[0767] 4. The server stores the extracted information in a database and updates the user's meal history.

[0768] Step 4: Generate menu suggestions

[0769] 1. The server generates an optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day).

[0770] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[0771] 2. The server generates a daily menu list and sends it to the terminal.

[0772] 3. The device notifies the user of the proposed menu and displays it in the application.

[0773] Step 5: Collect and analyze feedback

[0774] 1. After the user selects the suggested menu and consumes the meal, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[0775] 2. The device sends the feedback data to the server.

[0776] 3. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[0777] Step 6: Homemade recipe suggestions

[0778] 1. The server generates recipes that can be easily made at home based on the user's profile, past meal data, and emotional data.

[0779] 2. The server sends the generated recipe to the device.

[0780] 3. The device notifies the user of the recipe and displays it on the application.

[0781] 4. Users can check recipes from the application to help them cook at home.

[0782] Specific examples

[0783] Step 1: Collect user information

[0784] 1. The user launches the application for the first time and answers a questionnaire.

[0785] 2. The device sends the information collected from the user (age 30, female, nut allergy, weight loss goal) to the server.

[0786] 3. The server stores the data and generates a user profile.

[0787] Step 2: Collect and analyze emotion data

[0788] 1. The user inputs "I feel stressed" in the lunch scene using the emotion engine.

[0789] 2. The device sends the emotion data and date and time information to the server.

[0790] 3. The server stores the emotion data and generates an emotion profile for the user.

[0791] Step 3: AI learns eating habits

[0792] 1. A user eats "Salad and Grilled Chicken" for lunch, takes a photo, and uploads it to the application.

[0793] 2. The device sends a photo of the meal and date and time information to the server.

[0794] 3. The server uses AI to extract "salad," "grilled chicken," and "400 kcal" and stores them in a database.

[0795] Step 4: Generate menu suggestions

[0796] 1. The server takes into account the emotional data "stress" and generates a menu of "green tea and brown rice rice balls" that is expected to have a relaxing effect.

[0797] 2. The server sends the menu list to the terminal, and the terminal notifies the user of the menu.

[0798] Step 5: Collect and analyze feedback

[0799] 1. The user selects the suggested "rice ball with green tea and brown rice" and, after eating, uses the emotion engine to input feedback such as "satisfied" and "stress reduced."

[0800] 2. The device sends the feedback data to the server.

[0801] 3. The server analyzes the feedback and incorporates it into its next proposal.

[0802] Step 6: Homemade recipe suggestions

[0803] 1. The server generates a recipe called "Soup made with roasted green tea" that emphasizes its relaxing effect.

[0804] 2. The server sends the recipe to the terminal and notifies the user.

[0805] 3. User checks the recipe and makes the soup at home.

[0806] This system allows users to receive optimal meal menus based on their health data, dietary history, and emotional data. By taking emotional data into account, meal suggestions are made that take into account the user's psychological health, allowing for efficient individual health management.

[0807] Example 2

[0808] 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."

[0809] Health management is a very important issue in modern society, and many people are looking for ways to effectively manage their health. However, while conventional systems collect individual health data and dietary history, they are limited in their ability to comprehensively analyze this data and propose individually optimized meal menus. Furthermore, because they are limited to simple data analysis without considering emotional data or external factors, it is difficult to provide suggestions that are tailored to the user's psychological satisfaction or individual circumstances. Therefore, there is a need for multifaceted analysis of data and individually optimized meal suggestions in health management.

[0810] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting health data, dietary history, and emotional data of the user, means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu, and means for presenting the generated meal menu to the user. This enables more accurate meal menu suggestions based on the individual circumstances of the user. In addition, by including means for inputting the user's emotional state in daily meal situations, means for generating meal menus taking external factors into consideration, means for learning the user's eating habits using AI and updating the meal history, and means for generating recipes that can be made at home, it becomes possible to realize more comprehensive health management that also takes the user's psychological health into consideration.

[0811] "Health data" refers to information related to the user's physical condition and physical status, and specifically includes heart rate, number of steps, sleep data, weight, blood pressure, etc.

[0812] "Diet history" is a record of meals the user has eaten in the past, and specifically includes information about the ingredients, types of food, calories, and nutrients eaten.

[0813] "Emotion data" is information that represents the user's psychological state during everyday mealtimes, and includes emotional states such as "satisfaction," "stress," and "happiness" that are input using the emotion engine.

[0814] "Optimized meal menu" refers to a meal plan that is generated to suit an individual user by analyzing the user's health data, dietary history, and emotional data.

[0815] "Feedback" refers to information users enter about their satisfaction and emotional state after a meal, data the system uses to improve its next menu suggestion.

[0816] "External factors" are environmental factors that are taken into consideration when generating a meal menu, and specifically include the season, weather, time of day, etc.

[0817] An "emotion engine" is an interface that allows users to input their emotional state and is a tool for collecting emotional data such as satisfaction and stress.

[0818] "Image analysis" refers to the technological process of analyzing photos of meals uploaded by users to extract the type of food, calories, and macronutrients.

[0819] "Homemade recipes" refer to suggestions of cooking steps and ingredients that users can easily make at home, and are generated based on health data and dietary history.

[0820] A "profile" is an individual collection of information generated by integrating a user's health data, dietary history, and emotional data, and refers to the basic data used by the system to make optimal suggestions to the user.

[0821] This invention is a system that analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, a terminal, and a user.

[0822] The system first has a means to collect the user's health data, dietary history, and emotional data. Specifically, the user launches the application and accesses the initial registration screen. The device presents the user with questions about their age, gender, allergy information, health goals, etc., which the user answers. The user also inputs health data (heart rate, number of steps, sleep data, etc.) from a wearable device (e.g., a smartwatch). The device transmits this collected data to a server in real time, and the server stores the received data and generates an initial user profile.

[0823] Next, emotional data is collected and analyzed. The user uses the emotion engine to input their emotional state (e.g., satisfaction, stress, happiness, etc.) during everyday mealtimes. The device collects the emotional data and sends it to the server along with date and time information. The server stores the received emotional data and generates an emotional profile for the user.

[0824] Another important feature is the AI's ability to learn eating habits. Users take photos of their daily meals and upload them to the application. The device then sends the photos of the meal along with the date and time information to the server. The server then analyzes the photos using image analysis tools (e.g., Google Cloud Vision API) to extract data such as the type of food, calories, and macronutrients. The results of this analysis are stored in a database, and the user's eating history is updated.

[0825] Based on this data, the server generates an optimized meal menu taking into account the user profile (health data, dietary history, emotional data) and external factors (season, weather, time of day). The device notifies the user of the generated menu and displays it on the application.

[0826] Users can provide feedback after their meal by inputting their satisfaction with the meal and their emotional state using the emotion engine, and the device sends the feedback data to the server, which analyzes this feedback and stores it as learning data for the AI ​​to further optimize menu suggestions for the next time.

[0827] The server can also generate recipes that can be easily made at home based on the user profile, dietary data, and emotional data. The device notifies the user of the recipes and displays them on the application. The user can check the recipes through the application and use them to prepare meals at home.

[0828] Specific examples

[0829] 1. Collection of User Information

[0830] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., want to lose weight). For example, if the user is a 30-year-old woman who wants to prevent diabetes, that information is collected.

[0831] 2. Collecting and analyzing emotion data

[0832] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using the emotion engine. For example, the user might input, "I'm feeling stressed because things aren't going well at work."

[0833] 3. Learning eating habits

[0834] A user takes a photo of their lunch of "salad and grilled chicken" and uploads it to the app. The server analyzes the photo, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[0835] 4. Menu suggestions

[0836] The server takes into account the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect. The device notifies the user of the suggested menu and displays it on the application.

[0837] 5. Collecting and analyzing feedback

[0838] The user consumes the "green tea and brown rice rice ball" and uses the emotion engine to input feedback such as "satisfied" or "stress reduced." The device then sends the feedback data to the server.

[0839] 6. Recipe suggestions

[0840] The server generates a recipe for "soup using roasted green tea," taking into account the user's desire for a relaxing effect. The device notifies the user of the recipe and displays it on the application. The user then checks the recipe through the application and makes the soup at home.

[0841] Prompt Sentence Examples

[0842] "Please suggest the best lunch menu for a user who is a 30-year-old woman and has a health goal of preventing diabetes."

[0843] "Please suggest a menu that will have a relaxing effect on users who are feeling stressed from work during lunch."

[0844] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0845] Step 1: Collect user information

[0846] Input: The user launches the application for the first time, answers questions such as age, gender, allergy information, and health goals, and inputs health data from the wearable device.

[0847] Processing: The device collects the information entered by the user in real time and sends it to the server, which stores the received data and creates an initial user profile.

[0848] Output: A user profile is generated and stored on the server.

[0849] Specific operation: Questions such as "Please enter your age" and "Please select your gender" are displayed on the device screen, and the user answers accordingly. The smartwatch data is also linked to the app.

[0850] Step 2: Collect and analyze emotion data

[0851] Input: The user uses the emotion engine in everyday meal scenarios to input emotional states such as satisfaction, stress, and happiness.

[0852] Processing: The device collects emotion data and sends it to the server along with date and time information. The server stores the received emotion data and creates an emotion profile for the user.

[0853] Output: An emotional profile is generated and stored on the server.

[0854] Specific operation: After a meal, the message "How are you feeling right now?" appears on the device screen, and the user can select from options such as "Satisfied," "Stressed," or "Happy." Another example includes inputting "I'm feeling stressed because things aren't going well at work."

[0855] Step 3: AI learns eating habits

[0856] Input: The user takes photos of their daily meals and uploads the photos and date and time information to the application.

[0857] Processing: The device sends a photo of the meal and the date and time information to the server, which then uses image analysis tools (e.g., Google Cloud Vision API) to analyze the photo and extract the type of food, calories, and macronutrients.

[0858] Output: The analysis results are saved in a database and the user's diet history is updated.

[0859] Specific operation: A prompt appears saying "Please upload a photo of your meal." The user takes a photo of themselves eating "salad and grilled chicken" and uploads it. The server analyzes this and extracts data such as "salad," "grilled chicken," and "400 kcal."

[0860] Step 4: Generate menu suggestions

[0861] Input: User profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[0862] Processing: The server uses AI models to generate an optimized meal menu based on this data, taking into account external factors and making suggestions that match the user's emotional state.

[0863] Output: The generated meal menu is sent to the terminal and displayed to the user on the application.

[0864] Specific operation: The server selects "Green tea and brown rice onigiri" as the most suitable menu item, saying "Generating a menu with a relaxing effect..." The device then notifies the user, "We have the perfect menu item for you! 'Green tea and brown rice onigiri'."

[0865] Step 5: Collect and analyze feedback

[0866] Input: After the user consumes the proposed meal menu, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[0867] Processing: The device sends the feedback data to the server, which analyzes the feedback and stores it as learning data for the AI.

[0868] Output: Feedback is used to further optimize the next menu suggestion.

[0869] Specific operation: The user is satisfied after eating the "Green Tea and Brown Rice Rice Ball" and enters feedback such as "Satisfied" and "Stress reduced." The device displays the message "Sending feedback..." followed by "Sent."

[0870] Step 6: Homemade recipe suggestions

[0871] Input: User profile, dietary data, and emotional data.

[0872] Processing: The server uses this data to generate recipes that can be easily made at home. It also considers the user's emotional state and suggests optimal home-cooked recipes.

[0873] Output: The generated recipe is notified to the terminal and displayed to the user on the application.

[0874] Specific operation: The server generates a recipe for "soup using roasted green tea" with the message "Generating a recipe with a relaxing effect...". The device notifies the user, "A new recipe is available! 'Soup using roasted green tea'." The user checks the recipe through the application and makes the soup at home.

[0875] (Application example 2)

[0876] 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."

[0877] There are currently systems that collect and analyze health data, dietary history, and emotional data separately to suggest optimal meal menus. However, these systems are not linked to food delivery services, making it difficult for users to quickly obtain the suggested meals. Furthermore, they cannot suggest detailed menus that take into account emotional data and health goals, making it impossible to make qualitative suggestions that take psychological health into account. There is a need to solve these issues.

[0878] 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.

[0879] In this invention, the server includes means for collecting a user's health data, dietary history, and emotional data; means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu; means for presenting the generated meal menu to the user and delivering the suggested meals via a food delivery service; and means for collecting feedback from the user, updating the analysis results, and optimizing the next menu proposal. This makes it possible to quickly propose an optimal meal menu suitable for each user and actually deliver the meal. Furthermore, analysis results that take emotional data and external factors into account make it possible to realize high-quality meal proposals that take psychological health into consideration.

[0880] "Health data" is physical information collected through wearable devices and other health monitoring equipment, such as a user's heart rate, number of steps taken, and sleep duration.

[0881] "Dietary history" refers to information such as the contents, calories, and nutrients of the meals a user has eaten, and is a record collected through photographs or manual input.

[0882] "Emotional data" is information that represents the emotional state (e.g., satisfaction, stress, happiness) that a user feels while eating or engaging in an activity, and is data that is collected through manual input or an emotion engine.

[0883] An "individually optimized meal menu" is a meal suggestion generated based on collected health data, dietary history, and emotional data, taking into consideration the optimal nutritional balance and psychological satisfaction for the user.

[0884] "Food delivery service" refers to a delivery service that allows users to quickly obtain suggested meal menus, and is provided by affiliated restaurants and service providers.

[0885] "Feedback" refers to information that is used to input the user's feelings and level of satisfaction after eating, and to update the system's analysis results.

[0886] This invention is a system that collects and analyzes a user's health data, dietary history, and emotional data to provide an individually optimized meal menu, and can deliver meals to the user in cooperation with a food delivery service. Specific embodiments of this system are described below.

[0887] Hardware and Software

[0888] Hardware:

[0889] Smartphone: A device where the user enters data and views menu suggestions.

[0890] Wearable devices (e.g., Apple Watch, Fitbit): devices that collect health data such as a user's heart rate, number of steps, and sleep duration.

[0891] Server: A device for storing collected data, analyzing it, generating menus and processing feedback.

[0892] Network: A communications network for data communication between smartphones, wearable devices, and servers.

[0893] software:

[0894] Mobile application: An application for users to perform initial registration, data entry, menu browsing, emotion data entry, and feedback entry.

[0895] Emotion engine: Software for collecting and analyzing user emotion data.

[0896] Image analysis AI: An AI algorithm that analyzes food photos uploaded by users and extracts the food content and nutrients.

[0897] Server software: Software that stores and analyzes data, generates personalized optimization menus, and collects feedback.

[0898] Data processing and calculation

[0899] User Information Collection:

[0900] Users launch the application using their smartphone and access the initial registration screen. They enter their age, gender, allergy information, health goals, etc., and provide health data from their wearable device. This data is sent to the server in real time and stored.

[0901] Emotion data collection:

[0902] The user inputs their emotional state during daily mealtimes using the emotion engine, and sends the emotional data along with date and time information to the server. The server analyzes the received emotional data and generates an emotional profile for the user.

[0903] Learning eating habits:

[0904] Users take photos of their daily meals and upload them to the application. The server passes the photos to an image analysis AI, which extracts the type of food, calories, and macronutrients. The analysis results are saved as the user's diet history.

[0905] Generate menu suggestions:

[0906] The server generates an individually optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day). The suggested menu is notified to the user via a smartphone application. When the user selects a suggested menu, the meal is delivered via a food delivery service.

[0907] Collecting and analyzing feedback:

[0908] After eating, users input their satisfaction and emotional state using the emotion engine, and this feedback data is sent to the server, analyzed, and used to optimize menu suggestions for future meals.

[0909] Specific examples

[0910] Examples:

[0911] 1. User Information Collection:

[0912] A 30-year-old female user enters her food allergies and health goal (muscle gain) when registering for the first time.

[0913] 2. Health Data Collection:

[0914] Fitbit sends data such as heart rate, steps, and sleep time to the app in real time.

[0915] 3. Emotional Data Collection:

[0916] A user who is feeling stressed because things aren't going well at work enters emotional data into the app.

[0917] 4. Dietary Data Collection:

[0918] Take a photo of your lunch of "salad and salmon fillet" and upload it to the app.

[0919] 5. Menu suggestions:

[0920] The AI ​​analyzes the situation and suggests "hot pot with roasted green tea and plenty of vegetables," which helps reduce stress.

[0921] 6. Food delivery orders:

[0922] Order the suggested menu with one click and have it delivered within 30 minutes.

[0923] 7. Feedback Collection:

[0924] After eating, the participants enter feedback such as "satisfied" and "stress reduced."

[0925] Example prompt sentence:

[0926] The user enters that she is a 30-year-old woman, has no allergies, and her health goal is to gain muscle.

[0927] The wearable device collected real-time data including 120 heart rates, 8,000 steps, and 7 hours of sleep.

[0928] A user inputs emotional data such as "I'm feeling stressed at work." He uploads a photo of himself eating "salad and salmon fillet" for lunch.

[0929] The AI ​​analyzed the data and recommended "Hot Pot with Roasted Green Tea and Lots of Vegetables" to the user. The user ordered the menu with one click and it was delivered in 30 minutes.

[0930] After eating, the user entered feedback such as "I feel satisfied" and "My stress has been reduced."

[0931] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[0932] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0933] Step 1: Collect user information

[0934] Users launch the smartphone app and access the initial registration screen, where they enter basic information such as age, gender, allergy information, and health goals. The entered information is sent via the device to a server, which then stores the data and creates a user profile.

[0935] Input: Age, Gender, Allergy Information, Health Goals

[0936] Output: User profile stored on the server

[0937] Step 2: Collecting health data

[0938] When a user uses a wearable device (e.g., Fitbit) to go about their daily life, health data such as heart rate, number of steps, and sleep time are collected in real time. This data is sent to a server via the smartphone, and the server adds and stores this data in the user profile.

[0939] Input: Health data from wearable devices

[0940] Output: Updated user profile stored on the server

[0941] Step 3: Collecting emotion data

[0942] After each meal, users input their emotional state (e.g., satisfaction, stress, happiness) using a smartphone app. This emotional data, along with date and time information, is sent to a server, which then generates an emotional profile for the user.

[0943] Input: Date and time information, emotion data

[0944] Output: Emotion profile stored on the server

[0945] Step 4: Collect dietary data

[0946] Users take photos of their daily meals with their smartphones and upload them to the application. The device then sends the photo data to a server, which uses image analysis AI to extract the type of food, calories, and key nutrients from the photo. The extracted data is then saved on the server as the user's diet history.

[0947] Input: Food photo

[0948] Output: Meal history stored on the server

[0949] Step 5: Generate menu suggestions

[0950] The server integrates the user's health data, dietary history, emotional data, and external factors (season, weather, time of day) and uses a generative AI model to generate an individually optimized meal menu, which is then sent to the user via a smartphone application.

[0951] Input: Health data, diet history, emotional data, external factors

[0952] Output: Suggested meal menu

[0953] Step 6: Order food delivery

[0954] When the user checks and selects the meal menu on the smartphone application, the server sends the order information to the partner food delivery service, which then prepares the specified menu and delivers it to the user.

[0955] Input: Selected meal menu

[0956] Output: Delivered meal

[0957] Step 7: Collect and analyze feedback

[0958] After a meal, users use a smartphone app to input feedback about their satisfaction with the meal and their emotional state. The device then sends the feedback data to a server, which analyzes the data and uses it to suggest new menu items for the next meal.

[0959] Input: Feedback data (satisfaction and emotional state)

[0960] Output: Analysis results saved on the server (reflected in the next menu suggestion)

[0961] 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.

[0962] 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.

[0963] 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.

[0964] [Third embodiment]

[0965] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0966] 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.

[0967] 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).

[0968] 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.

[0969] 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.

[0970] 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).

[0971] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] 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.

[0976] 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."

[0977] This invention is a system that provides personalized optimal meals, and supports users' health management by collecting and analyzing their health data and dietary history, and proposing optimized meal menus based on the results. This system operates in cooperation with a server, terminals, and users.

[0978] Program processing overview

[0979] 1. Collection of User Information

[0980] The user launches the application, answers a questionnaire, and inputs health data from the wearable device.

[0981] The device transmits the collected data to the server in real time.

[0982] The server stores the received data and generates a user profile.

[0983] 2. AI-based learning of eating habits

[0984] Users take photos of their daily meals and upload them to the application.

[0985] The device sends the date and time information along with a photo of the meal to the server.

[0986] The server passes the received photos to AI for image analysis, extracting the type of food, calories, and key nutrients.

[0987] The server stores the analysis results in a database and updates the user's dietary history.

[0988] 3. Generate menu suggestions

[0989] The server generates an optimized meal menu based on the user's profile, meal history, and external factors (season, weather, time of day).

[0990] The terminal notifies the user of the proposed menu and displays it on the application.

[0991] 4. Collecting and analyzing feedback

[0992] After eating, users enter their taste and satisfaction in a feedback form.

[0993] The terminal sends this feedback to the server.

[0994] Based on the feedback received, the server updates the AI's learning data and further optimizes the next menu suggestion.

[0995] 5. Homemade recipe suggestions

[0996] The server generates home cooking recipes based on the user's data and sends them to the device.

[0997] The terminal notifies the user of the recipe and displays it on the application.

[0998] Specific examples

[0999] 1. Collection of User Information

[1000] When a user launches the application for the first time, they enter their age, gender, allergy information, and health goals (e.g., weight loss, muscle gain, etc.).

[1001] For example, if the user is a 40-year-old male with a goal of losing weight and is allergic to nuts, that information will be collected.

[1002] 2. Learning eating habits

[1003] A user eats salad and chicken for lunch and uploads a photo of it to the application, which also includes the date and time stamp.

[1004] The server analyzes this and extracts and stores data such as "salad," "chicken," and "500 kcal."

[1005] 3. Menu suggestions

[1006] The next day, the server analyzes the user's data and, taking into account their calorie goals and allergy information, suggests low-calorie, high-protein dishes such as "Konnyaku and Vegetable Simmered Dish" or "Grilled Chicken Salad."

[1007] 4. Feedback Collection

[1008] The user selects the suggested "grilled chicken salad" and eats it for lunch. After eating, the user enters their satisfaction with the meal and any areas for improvement into the application.

[1009] For example, provide feedback such as "there was too much chicken" or "the dressing was too watered down."

[1010] 5. Recipe suggestions

[1011] Taking into account the user's eating patterns and goals, the server suggests a "tofu steak recipe" for dinner, including instructions for grilling tofu to resemble steak and a list of the ingredients needed.

[1012] Users can access these recipes from the application and use them to prepare meals at home.

[1013] This system provides users with individually optimized meal menus, enabling them to efficiently manage their health. For companies, improving the health of their employees can lead to increased work efficiency and productivity.

[1014] The processing flow will be explained below.

[1015] Program processing steps

[1016] Step 1: Collect user information

[1017] 1. The user launches the application and accesses the initial registration screen.

[1018] 2. The device presents the user with questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects the responses.

[1019] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[1020] 4. The device sends the collected questionnaire answers and health data to the server in real time.

[1021] 5. The server stores the received data and generates an initial user profile.

[1022] Step 2: AI learns eating habits

[1023] 1. The user takes photos of their daily meals and uploads them to the application.

[1024] 2. The device sends the date and time information along with a photo of the meal to the server.

[1025] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[1026] 4. The server stores the extracted information in a database and updates the user's meal history.

[1027] Step 3: Generate menu suggestions

[1028] 1. The server generates an optimized meal menu based on the user's profile (health data and dietary history) and external factors (season, weather, time of day).

[1029] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[1030] 2. Based on the optimized menu, the server generates a daily menu list and sends it to the terminal.

[1031] 3. The device notifies the user of the proposed menu and displays it in the application.

[1032] Step 4: Collect and analyze feedback

[1033] 1. After the user selects the suggested menu and consumes the meal, the application displays a feedback form.

[1034] 2. Users enter information about the taste of the meal, their satisfaction, and areas for improvement in the feedback form.

[1035] 3. The device sends the input feedback to the server.

[1036] 4. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1037] Step 5: Homemade recipe suggestions

[1038] 1. The server generates recipes that can be easily made at home based on the user's profile and past meal data.

[1039] 2. The server sends the generated recipe information to the terminal.

[1040] 3. The device notifies the user of the recipe and displays it on the application.

[1041] 4. Users can check recipes through the application to help them cook at home.

[1042] Through these steps, users can receive individually optimized meal suggestions and efficiently manage their health. Companies can also maintain employee health and improve productivity by providing optimal meals based on employee health data.

[1043] Example 1

[1044] 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."

[1045] Health management has become increasingly important in recent years, but general dietary management systems often fail to provide meal menus that fully consider a user's individual health condition and dietary history. Furthermore, there is a lack of systems that appropriately reflect user feedback and continuously optimize meal menus. Furthermore, there is the challenge of providing recommended meal menus to users while taking into account allergy information and individual nutritional needs.

[1046] 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.

[1047] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for automatically synchronizing health data from the wearable device, means for analyzing food photos to extract nutritional information, means for customizing the menu based on the user's profile and external factors, and means for suggesting recipes that can be cooked at home. This makes it possible to provide an optimized diet menu based on the user's individual health condition and dietary history, and to continue improving the system based on continuous feedback.

[1048] "User's health data" refers to numerical information indicating the user's health condition, such as the user's age, gender, height, weight, heart rate, number of steps, and calories burned.

[1049] "Dietary history" refers to information such as the contents of meals the user has eaten in the past, photos, the date and time of eating, calories, nutrients, etc.

[1050] "Wearable device" refers to a device (e.g., smartwatch, fitness tracker) that is worn by the user to measure and collect health data.

[1051] "Meal menu" refers to information such as the contents, recipes, ingredients, calories, nutrients, etc. of the meals suggested for the user to consume.

[1052] "Feedback" refers to information such as opinions, satisfaction, and areas for improvement provided by users regarding the proposed meal menu.

[1053] "User profile" refers to data that compiles a user's personal information, health data, dietary history, allergy information, health goals, etc.

[1054] "Image analysis" refers to the use of AI to extract specific information from a photo, in this case, the type of food, calories, and macronutrients.

[1055] "External factors" refer to environmental factors that influence a user's food choices, such as season, weather, and time of day.

[1056] A "recipe" is a list of steps and ingredients needed to make a particular dish.

[1057] "Synchronizing" refers to multiple devices or systems sharing and updating the same data.

[1058] This invention is a system that provides a meal menu optimized for each user, and supports the user's health management. This system operates in cooperation with the user, terminal, and server.

[1059] Collection of User Information

[1060] Users first launch the application and enter basic health data such as age, gender, height, weight, health goals (weight loss, muscle gain, etc.), and allergy information. In addition, users sync data from their wearable devices (e.g., smartwatches, fitness trackers) with the application, including heart rate, steps, and calories burned. This data is immediately sent from the device to the server and saved as a user profile.

[1061] For example, a 40-year-old man launches the application, inputs that he weighs 70 kg and has a nut allergy, and provides data from his wearable device showing a heart rate of 70 bpm, 10,000 steps taken per day, and calories burned of 2,200 kcal.

[1062] Learning eating habits using AI

[1063] Users take photos of their daily meals and upload them to the app. The device then sends the photos of the meal along with the date and time information to a server. The server then uses AI to analyze the photos and extract the type of food, calories, and macronutrients (protein, fat, carbohydrates). The results of this analysis are stored in a database, and the user's diet history is updated.

[1064] For example, if a user has salad and chicken for lunch and uploads a photo of it, the server extracts and stores information such as "salad," "chicken," "500kcal," "protein 30g," "fat 10g," and "carbohydrates 40g" from the photo.

[1065] Generate menu suggestions

[1066] The server analyzes data based on the user's profile, meal history, and external factors (season, weather, time of day) to generate an optimized meal menu. The device notifies the user of this menu and displays it on the application.

[1067] For example, the server analyzes the user's data and suggests low-calorie, high-protein dishes such as "Konjac and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[1068] Collecting and analyzing feedback

[1069] After selecting a suggested menu and eating, the user enters their taste, satisfaction, and suggestions for improvement in a feedback form. The device then sends this feedback to the server. The server updates the AI's learning data based on the received feedback, further optimizing the next menu suggestion.

[1070] For example, a user can provide feedback such as "The grilled chicken was tasty, but it was a little bland," and the server can incorporate this information to improve its suggestions next time.

[1071] Homemade recipe suggestions

[1072] The server generates easy-to-make homemade recipes based on the user's data (health goals, dietary history, feedback), and the device notifies the user of the recipes and displays them in the application.

[1073] For example, the server generates a recipe (including ingredients and cooking steps) for making tofu steak for dinner, and the terminal notifies the user of this.

[1074] This invention allows users to efficiently manage their health by providing individually optimized meal menus and recipes, and also enables companies to manage the health status of their employees in an advanced manner, aiming to improve business efficiency and productivity.

[1075] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1076] Step 1: Collect user information

[1077] Input: A user launches the application and enters their age, gender, height, weight, allergy information, and health goals (e.g., weight loss, muscle gain). Additionally, they sync data from their wearable device (e.g., smartwatch, fitness tracker) such as heart rate, steps, and calories burned.

[1078] Specific operation: The user enters information such as "40-year-old male, weight 70 kg, desire to lose weight, nut allergy" and synchronizes data such as "heart rate 70 bpm, 10,000 steps per day, calories burned 2,200 kcal" from the wearable device.

[1079] Data processing / data calculation: The device collects this information and sends it to the server in real time. The server stores the received data in a database and generates a user profile.

[1080] Output: A user profile is generated and stored on the server.

[1081] Step 2: Learn your eating habits

[1082] Input: Users take photos of their daily meals and upload them to the application.

[1083] What happens: A user uploads a photo of "salad and chicken" for lunch, with date and time information attached.

[1084] Data processing / data calculation: The device sends photos of the meal and date and time information to the server. The server then passes the photos to the AI ​​for image analysis. The AI ​​extracts the type of food, calories, and macronutrients (e.g., protein, fat, carbohydrates).

[1085] Output: The server saves the analysis results in a database and updates the user's food history. Data such as "Salad," "Chicken," "Calories 500kcal," "Protein 30g," "Fat 10g," and "Carbohydrates 40g" are saved.

[1086] Step 3: Generate menu suggestions

[1087] Input: The server analyzes the data based on the user's profile, food history, and external factors (season, weather, time of day).

[1088] Specific operation: The server performs an analysis based on the user's data ("40-year-old male aiming to lose weight") and "eating history of salad and chicken."

[1089] Data processing / data calculation: The server uses AI to generate an optimized meal menu, taking into account calories, allergy information, nutritional balance, etc.

[1090] Output: A suggested menu is generated. Possible options include "Konnyaku and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[1091] Specific operation: The generated menu is sent to the terminal and notified to the user.

[1092] Step 4: Collect and analyze feedback

[1093] Input: The user consumes the suggested menu and, after eating, enters their opinions, satisfaction, and suggestions for improvement in a feedback form on the application.

[1094] What happens: The user enters feedback like, "The grilled chicken was tasty, but it was a little bland."

[1095] Data processing / data calculation: The device sends feedback to the server, which updates the AI's learning data based on the received feedback.

[1096] Output: The server updates the data based on the feedback, and the next menu suggestions will be further optimized.

[1097] Step 5: Homemade recipe suggestions

[1098] Input: The server generates easy-to-make home-cooked recipes based on the user's profile, food history, and feedback.

[1099] Specific behavior: The server generates a "Tofu Steak Recipe (ingredients, cooking instructions)" for dinner.

[1100] Data processing / data calculation: The server selects recipes that suit the user's preferences and nutritional needs, and sends the generated recipes to the terminal.

[1101] Output: The recipe is notified to the user via the device and displayed in the application. Information such as "Tofu, grated daikon radish, soy sauce, cooking steps: 1. Fry the tofu..." is provided.

[1102] (Application example 1)

[1103] 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."

[1104] The main function of conventional dietary management systems is to collect users' health data and dietary history, but they are not sufficient in effectively utilizing this data to propose individually optimized dietary menus. Furthermore, there are only a limited number of systems that can collect user feedback and update analysis results to make more accurate proposals. Furthermore, there are issues with the inability to improve convenience and collect data in real time by utilizing smartphones, smart glasses, and wearable devices. There is a need to provide a system that can solve these issues and efficiently manage users' health.

[1105] 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.

[1106] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for collecting the user's health data in real time using a smartphone, smart glasses, or wearable device, means for analyzing the user's meal photos and extracting macronutrients, a generative AI model for generating a diet menu suited to the user's health goals based on the extracted data, and means for notifying the user's device of the generated menu, thereby enabling efficient health management for the user.

[1107] "User health data" refers to information related to the user's physical condition and health, and includes, for example, data such as heart rate, body temperature, blood pressure, blood sugar level, and sleep patterns.

[1108] "Dietary history" is a record of the meals a user has eaten, and includes information such as the type of meal, the time of intake, calories, and major nutrients.

[1109] "Means of collection" refers to devices or software for acquiring a user's health data and dietary history, such as smartphones, smart glasses, and wearable devices.

[1110] "Means for analysis" refers to technologies and methods for analyzing collected health data and dietary history to extract useful information, including, for example, AI algorithms and database management systems.

[1111] A "personally optimized meal menu" is a specific meal list that provides a meal plan that is best suited to the user based on the user's health condition and dietary history.

[1112] The "presentation means" refers to a device or method for informing the user of the generated meal menu, such as a smartphone app or a smart glasses display.

[1113] "Means for collecting feedback and updating analysis results" refers to methods for collecting opinions and impressions from users and using them to improve the system's analysis algorithms.

[1114] "Means of collecting data in real time" refers to technologies and devices that instantly acquire users' health data and reflect it directly in the system.

[1115] "Means for analyzing photos to extract key nutrients" includes technology that analyzes photos of meals taken by users to identify the nutrients and calories contained therein.

[1116] A "generative AI model" is an artificial intelligence algorithm that automatically generates optimal meal menus based on a user's health data and dietary history.

[1117] "Means for notifying the terminal" refers to techniques or methods for notifying the user of the generated meal menu, and includes, for example, push notifications to a smartphone or smart glasses.

[1118] The present invention is a system for efficiently managing a user's health, which operates in cooperation with a server, a terminal, and a user. Specifically, the system is implemented through the following process.

[1119] 1. Collection of User Information:

[1120] Hardware: Smartphones, smart glasses, wearable devices (e.g., Fitbit, Apple Watch)

[1121] Software: Health management apps (e.g., Apple Health, Google Fit)

[1122] Processing: The user launches the application and enters the required health data. Data is also automatically collected from the wearable device. This data is sent to the server in real time, and a user profile is generated.

[1123] 2. Learning eating habits:

[1124] Hardware: Smartphone camera

[1125] Software: Image analysis algorithms (e.g., OpenCV, TensorFlow)

[1126] Processing: The user takes a photo of their meal and uploads it to the application. The server receives the photo and performs image analysis to extract macronutrients, which then updates the user's diet history database.

[1127] 3.Generate menu suggestions:

[1128] Hardware: Server

[1129] Software: Machine learning algorithms (e.g., PyTorch, scikit-learn)

[1130] Processing: The server uses machine learning algorithms to generate a personalized meal plan based on the user's health profile and dietary history. This plan is then sent to the user's device and displayed on the app.

[1131] 4. Feedback collection and analysis:

[1132] Hardware: Smartphone

[1133] Software: Database management system (e.g., PostgreSQL)

[1134] Processing: After the meal, the user provides feedback. They input their satisfaction and impressions of the meal via a smartphone application, which is then sent to the server. The server uses this feedback data to update its AI algorithm and further optimize the menu suggestions for the next meal.

[1135] Specific examples

[1136] For example, a user may have "salad and chicken" for lunch, take a photo of it with their smartphone, and upload it to the application. The server analyzes this meal data, extracts calories and key nutrients, and saves them as a meal history. The next day, the server will suggest "low-calorie, high-protein grilled chicken salad" based on the user's health profile and meal history. This suggestion is notified to the user's smartphone. After the user selects this menu and eats it, they can enter their satisfaction and impressions into the application. This feedback will further improve the next suggestion.

[1137] Prompt Sentence Examples

[1138] By inputting the following prompts into the generative AI model, we can generate the optimal meal menu:

[1139] Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from dietary history and suggest menus that are optimal for achieving health goals. Also, consider whether the menu is easy to prepare. The suggested menus will be notified to the user's smartphone.

[1140] In this way, a system for efficiently managing the user's health is realized.

[1141] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1142] Step 1:

[1143] Collection of User Information

[1144] Input: Health data entered by the user (e.g., age, gender, allergy information, health goals) and real-time health data collected from wearable devices (e.g., heart rate, body temperature, blood pressure).

[1145] Processing: The user launches the application and inputs the necessary health data. Further health data is automatically collected from the wearable device. This data is then sent to the server in real time via the device.

[1146] Output: Generated user profile.

[1147] Step 2:

[1148] Learning eating habits

[1149] Input: A photo of a meal taken by the user and uploaded to the application.

[1150] Processing: The server receives the uploaded meal photos and uses image analysis algorithms (e.g., OpenCV, TensorFlow) to identify the ingredients and dishes in the photos and extract macronutrients (e.g., calories, protein, fat, carbohydrates).

[1151] Output: The analyzed dietary data is stored in a dietary history database.

[1152] Step 3:

[1153] Generate menu suggestions

[1154] Input: User's health profile and diet history data.

[1155] Processing: The server uses machine learning algorithms (e.g., PyTorch, scikit-learn) to generate an individually optimized meal menu based on the user's health data, dietary history, and external factors (e.g., season, weather, time of day). The generative AI model uses a prompt: "Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from the dietary history and suggest a menu that best suits the health goals. Also, consider whether the menu is easy to prepare. The suggested menu will be sent to the user's smartphone."

[1156] Output: The generated optimal meal menu.

[1157] Step 4:

[1158] Meal menu notifications

[1159] Input: The generated meal menu.

[1160] Processing: The server sends a push notification to the user's device (e.g., smartphone, smart glasses) with the generated meal menu.

[1161] Output: The meal menu is displayed on the user's device.

[1162] Step 5:

[1163] Collecting and analyzing feedback

[1164] Input: Feedback provided by the user after eating (e.g., satisfaction, areas for improvement, impressions).

[1165] Processing: The user enters feedback into the application and sends it to the server via the device. The server stores the received feedback in a database and uses it to update the AI ​​algorithm and optimize the next menu suggestions.

[1166] Output: The updated parsing algorithm.

[1167] Through these steps, users are provided with a consistently and individually optimized meal menu, enabling efficient health management. By using this system, users' health status can be improved and continuous improvement can be achieved.

[1168] 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.

[1169] This invention is a system that combines and analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, terminals, and users.

[1170] Program processing overview

[1171] 1. Collection of User Information

[1172] The user starts the application and accesses the initial registration screen.

[1173] The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[1174] Users answer questions and also input health data (heart rate, steps, sleep data, etc.) from their wearable device.

[1175] The device transmits the collected data to the server in real time.

[1176] The server stores the received data and generates an initial user profile.

[1177] 2. Collecting and analyzing emotion data

[1178] During everyday mealtimes, the user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine.

[1179] The device collects emotion data and sends it to the server along with date and time information.

[1180] The server stores the received emotion data and generates an emotion profile for the user.

[1181] 3. AI-based learning of eating habits

[1182] Users take photos of their daily meals and upload them to the application.

[1183] The device sends the date and time information along with a photo of the meal to the server.

[1184] The server passes the photo to AI for image analysis, extracting the type of food, calories, and key nutrients.

[1185] The server stores the analysis results in a database and updates the user's dietary history.

[1186] 4. Generate menu suggestions

[1187] The server generates an optimized meal menu based on the user's profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[1188] The terminal notifies the user of the proposed menu and displays it on the application.

[1189] 5. Collecting and analyzing feedback

[1190] After eating, the user uses the emotion engine to input their satisfaction with the meal and their emotional state.

[1191] The terminal transmits the feedback data to the server.

[1192] The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1193] 6. Homemade recipe suggestions

[1194] The server generates recipes that can be easily made at home based on the user's profile, dietary data, and emotional data.

[1195] The terminal notifies the user of the generated recipe and displays it on the application.

[1196] Users can check recipes from the application to help them cook at home.

[1197] Specific examples

[1198] 1. Collection of User Information

[1199] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., wanting to lose weight).

[1200] For example, if the user is a 30-year-old woman and wants to prevent diabetes, that information is collected.

[1201] 2. Collecting and analyzing emotion data

[1202] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using an emotion engine.

[1203] For example, a user inputs into the emotion engine, "I'm feeling stressed because things aren't going well at work."

[1204] 3. Learning eating habits

[1205] A user takes a photo of their lunch, "Salad and Grilled Chicken," and uploads it to the application.

[1206] The server analyzes this, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[1207] 4. Menu suggestions

[1208] The server takes into consideration the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect.

[1209] The terminal notifies the user of the proposed menu and displays it on the application.

[1210] 5. Collecting and analyzing feedback

[1211] The user selects the suggested "green tea and brown rice rice ball" and consumes it for lunch.

[1212] After eating, the emotion engine is used to input feedback such as "satisfied" or "stress reduced."

[1213] The terminal transmits the feedback data to the server.

[1214] 6. Recipe suggestions

[1215] The server considers that the user is looking for a "relaxing effect" and generates a recipe for "soup made with roasted green tea."

[1216] The terminal notifies the user of the recipe and displays it on the application.

[1217] Users can check the recipe through the application and make the soup at home.

[1218] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[1219] The processing flow will be explained below.

[1220] Program processing steps

[1221] Step 1: Collect user information

[1222] 1. The user launches the application and accesses the initial registration screen.

[1223] 2. The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[1224] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[1225] 4. The device sends the collected data to the server in real time.

[1226] 5. The server stores the received data and generates an initial user profile.

[1227] Step 2: Collect and analyze emotion data

[1228] 1. The user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine during everyday mealtimes.

[1229] 2. The device collects emotion data and sends it to the server along with date and time information.

[1230] 3. The server stores the received emotion data and generates an emotion profile for the user.

[1231] Step 3: AI learns eating habits

[1232] 1. The user takes photos of their daily meals and uploads them to the application.

[1233] 2. The device sends the date and time information along with a photo of the meal to the server.

[1234] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[1235] 4. The server stores the extracted information in a database and updates the user's meal history.

[1236] Step 4: Generate menu suggestions

[1237] 1. The server generates an optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day).

[1238] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[1239] 2. The server generates a daily menu list and sends it to the terminal.

[1240] 3. The device notifies the user of the proposed menu and displays it in the application.

[1241] Step 5: Collect and analyze feedback

[1242] 1. After the user selects the suggested menu and consumes the meal, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[1243] 2. The device sends the feedback data to the server.

[1244] 3. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1245] Step 6: Homemade recipe suggestions

[1246] 1. The server generates recipes that can be easily made at home based on the user's profile, past meal data, and emotional data.

[1247] 2. The server sends the generated recipe to the device.

[1248] 3. The device notifies the user of the recipe and displays it on the application.

[1249] 4. Users can check recipes from the application to help them cook at home.

[1250] Specific examples

[1251] Step 1: Collect user information

[1252] 1. The user launches the application for the first time and answers a questionnaire.

[1253] 2. The device sends the information collected from the user (age 30, female, nut allergy, weight loss goal) to the server.

[1254] 3. The server stores the data and generates a user profile.

[1255] Step 2: Collect and analyze emotion data

[1256] 1. The user inputs "I feel stressed" in the lunch scene using the emotion engine.

[1257] 2. The device sends the emotion data and date and time information to the server.

[1258] 3. The server stores the emotion data and generates an emotion profile for the user.

[1259] Step 3: AI learns eating habits

[1260] 1. A user eats "Salad and Grilled Chicken" for lunch, takes a photo, and uploads it to the application.

[1261] 2. The device sends a photo of the meal and date and time information to the server.

[1262] 3. The server uses AI to extract "salad," "grilled chicken," and "400 kcal" and stores them in a database.

[1263] Step 4: Generate menu suggestions

[1264] 1. The server takes into account the emotional data "stress" and generates a menu of "green tea and brown rice rice balls" that is expected to have a relaxing effect.

[1265] 2. The server sends the menu list to the terminal, and the terminal notifies the user of the menu.

[1266] Step 5: Collect and analyze feedback

[1267] 1. The user selects the suggested "rice ball with green tea and brown rice" and, after eating, uses the emotion engine to input feedback such as "satisfied" and "stress reduced."

[1268] 2. The device sends the feedback data to the server.

[1269] 3. The server analyzes the feedback and incorporates it into its next proposal.

[1270] Step 6: Homemade recipe suggestions

[1271] 1. The server generates a recipe called "Soup made with roasted green tea" that emphasizes its relaxing effect.

[1272] 2. The server sends the recipe to the terminal and notifies the user.

[1273] 3. User checks the recipe and makes the soup at home.

[1274] This system allows users to receive optimal meal menus based on their health data, dietary history, and emotional data. By taking emotional data into account, meal suggestions are made that take into account the user's psychological health, allowing for efficient individual health management.

[1275] Example 2

[1276] 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."

[1277] Health management is a very important issue in modern society, and many people are looking for ways to effectively manage their health. However, while conventional systems collect individual health data and dietary history, they are limited in their ability to comprehensively analyze this data and propose individually optimized meal menus. Furthermore, because they are limited to simple data analysis without considering emotional data or external factors, it is difficult to provide suggestions that are tailored to the user's psychological satisfaction or individual circumstances. Therefore, there is a need for multifaceted analysis of data and individually optimized meal suggestions in health management.

[1278] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting health data, dietary history, and emotional data of the user, means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu, and means for presenting the generated meal menu to the user. This enables more accurate meal menu suggestions based on the individual circumstances of the user. In addition, by including means for inputting the user's emotional state in daily meal situations, means for generating meal menus taking external factors into consideration, means for learning the user's eating habits using AI and updating the meal history, and means for generating recipes that can be made at home, it becomes possible to realize more comprehensive health management that also takes the user's psychological health into consideration.

[1279] "Health data" refers to information related to the user's physical condition and physical status, and specifically includes heart rate, number of steps, sleep data, weight, blood pressure, etc.

[1280] "Diet history" is a record of meals the user has eaten in the past, and specifically includes information about the ingredients, types of food, calories, and nutrients eaten.

[1281] "Emotion data" is information that represents the user's psychological state during everyday mealtimes, and includes emotional states such as "satisfaction," "stress," and "happiness" that are input using the emotion engine.

[1282] "Optimized meal menu" refers to a meal plan that is generated to suit an individual user by analyzing the user's health data, dietary history, and emotional data.

[1283] "Feedback" refers to information users enter about their satisfaction and emotional state after a meal, data the system uses to improve its next menu suggestion.

[1284] "External factors" are environmental factors that are taken into consideration when generating a meal menu, and specifically include the season, weather, time of day, etc.

[1285] An "emotion engine" is an interface that allows users to input their emotional state and is a tool for collecting emotional data such as satisfaction and stress.

[1286] "Image analysis" refers to the technological process of analyzing photos of meals uploaded by users to extract the type of food, calories, and macronutrients.

[1287] "Homemade recipes" refer to suggestions of cooking steps and ingredients that users can easily make at home, and are generated based on health data and dietary history.

[1288] A "profile" is an individual collection of information generated by integrating a user's health data, dietary history, and emotional data, and refers to the basic data used by the system to make optimal suggestions to the user.

[1289] This invention is a system that analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, a terminal, and a user.

[1290] The system first has a means to collect the user's health data, dietary history, and emotional data. Specifically, the user launches the application and accesses the initial registration screen. The device presents the user with questions about their age, gender, allergy information, health goals, etc., which the user answers. The user also inputs health data (heart rate, number of steps, sleep data, etc.) from a wearable device (e.g., a smartwatch). The device transmits this collected data to a server in real time, and the server stores the received data and generates an initial user profile.

[1291] Next, emotional data is collected and analyzed. The user uses the emotion engine to input their emotional state (e.g., satisfaction, stress, happiness, etc.) during everyday mealtimes. The device collects the emotional data and sends it to the server along with date and time information. The server stores the received emotional data and generates an emotional profile for the user.

[1292] Another important feature is the AI's ability to learn eating habits. Users take photos of their daily meals and upload them to the application. The device then sends the photos of the meal along with the date and time information to the server. The server then analyzes the photos using image analysis tools (e.g., Google Cloud Vision API) to extract data such as the type of food, calories, and macronutrients. The results of this analysis are stored in a database, and the user's eating history is updated.

[1293] Based on this data, the server generates an optimized meal menu taking into account the user profile (health data, dietary history, emotional data) and external factors (season, weather, time of day). The device notifies the user of the generated menu and displays it on the application.

[1294] Users can provide feedback after their meal by inputting their satisfaction with the meal and their emotional state using the emotion engine, and the device sends the feedback data to the server, which analyzes this feedback and stores it as learning data for the AI ​​to further optimize menu suggestions for the next time.

[1295] The server can also generate recipes that can be easily made at home based on the user profile, dietary data, and emotional data. The device notifies the user of the recipes and displays them on the application. The user can check the recipes through the application and use them to prepare meals at home.

[1296] Specific examples

[1297] 1. Collection of User Information

[1298] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., want to lose weight). For example, if the user is a 30-year-old woman who wants to prevent diabetes, that information is collected.

[1299] 2. Collecting and analyzing emotion data

[1300] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using the emotion engine. For example, the user might input, "I'm feeling stressed because things aren't going well at work."

[1301] 3. Learning eating habits

[1302] A user takes a photo of their lunch of "salad and grilled chicken" and uploads it to the app. The server analyzes the photo, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[1303] 4. Menu suggestions

[1304] The server takes into account the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect. The device notifies the user of the suggested menu and displays it on the application.

[1305] 5. Collecting and analyzing feedback

[1306] The user consumes the "green tea and brown rice rice ball" and uses the emotion engine to input feedback such as "satisfied" or "stress reduced." The device then sends the feedback data to the server.

[1307] 6. Recipe suggestions

[1308] The server generates a recipe for "soup using roasted green tea," taking into account the user's desire for a relaxing effect. The device notifies the user of the recipe and displays it on the application. The user then checks the recipe through the application and makes the soup at home.

[1309] Prompt Sentence Examples

[1310] "Please suggest the best lunch menu for a user who is a 30-year-old woman and has a health goal of preventing diabetes."

[1311] "Please suggest a menu that will have a relaxing effect on users who are feeling stressed from work during lunch."

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1: Collect user information

[1314] Input: The user launches the application for the first time, answers questions such as age, gender, allergy information, and health goals, and inputs health data from the wearable device.

[1315] Processing: The device collects the information entered by the user in real time and sends it to the server, which stores the received data and creates an initial user profile.

[1316] Output: A user profile is generated and stored on the server.

[1317] Specific operation: Questions such as "Please enter your age" and "Please select your gender" are displayed on the device screen, and the user answers accordingly. The smartwatch data is also linked to the app.

[1318] Step 2: Collect and analyze emotion data

[1319] Input: The user uses the emotion engine in everyday meal scenarios to input emotional states such as satisfaction, stress, and happiness.

[1320] Processing: The device collects emotion data and sends it to the server along with date and time information. The server stores the received emotion data and creates an emotion profile for the user.

[1321] Output: An emotional profile is generated and stored on the server.

[1322] Specific operation: After a meal, the message "How are you feeling right now?" appears on the device screen, and the user can select from options such as "Satisfied," "Stressed," or "Happy." Another example includes inputting "I'm feeling stressed because things aren't going well at work."

[1323] Step 3: AI learns eating habits

[1324] Input: The user takes photos of their daily meals and uploads the photos and date and time information to the application.

[1325] Processing: The device sends a photo of the meal and the date and time information to the server, which then uses image analysis tools (e.g., Google Cloud Vision API) to analyze the photo and extract the type of food, calories, and macronutrients.

[1326] Output: The analysis results are saved in a database and the user's diet history is updated.

[1327] Specific operation: A prompt appears saying "Please upload a photo of your meal." The user takes a photo of themselves eating "salad and grilled chicken" and uploads it. The server analyzes this and extracts data such as "salad," "grilled chicken," and "400 kcal."

[1328] Step 4: Generate menu suggestions

[1329] Input: User profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[1330] Processing: The server uses AI models to generate an optimized meal menu based on this data, taking into account external factors and making suggestions that match the user's emotional state.

[1331] Output: The generated meal menu is sent to the terminal and displayed to the user on the application.

[1332] Specific operation: The server selects "Green tea and brown rice onigiri" as the most suitable menu item, saying "Generating a menu with a relaxing effect..." The device then notifies the user, "We have the perfect menu item for you! 'Green tea and brown rice onigiri'."

[1333] Step 5: Collect and analyze feedback

[1334] Input: After the user consumes the proposed meal menu, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[1335] Processing: The device sends the feedback data to the server, which analyzes the feedback and stores it as learning data for the AI.

[1336] Output: Feedback is used to further optimize the next menu suggestion.

[1337] Specific operation: The user is satisfied after eating the "Green Tea and Brown Rice Rice Ball" and enters feedback such as "Satisfied" and "Stress reduced." The device displays the message "Sending feedback..." followed by "Sent."

[1338] Step 6: Homemade recipe suggestions

[1339] Input: User profile, dietary data, and emotional data.

[1340] Processing: The server uses this data to generate recipes that can be easily made at home. It also considers the user's emotional state and suggests optimal home-cooked recipes.

[1341] Output: The generated recipe is notified to the terminal and displayed to the user on the application.

[1342] Specific operation: The server generates a recipe for "soup using roasted green tea" with the message "Generating a recipe with a relaxing effect...". The device notifies the user, "A new recipe is available! 'Soup using roasted green tea'." The user checks the recipe through the application and makes the soup at home.

[1343] (Application example 2)

[1344] 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."

[1345] There are currently systems that collect and analyze health data, dietary history, and emotional data separately to suggest optimal meal menus. However, these systems are not linked to food delivery services, making it difficult for users to quickly obtain the suggested meals. Furthermore, they cannot suggest detailed menus that take into account emotional data and health goals, making it impossible to make qualitative suggestions that take psychological health into account. There is a need to solve these issues.

[1346] 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.

[1347] In this invention, the server includes means for collecting a user's health data, dietary history, and emotional data; means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu; means for presenting the generated meal menu to the user and delivering the suggested meals via a food delivery service; and means for collecting feedback from the user, updating the analysis results, and optimizing the next menu proposal. This makes it possible to quickly propose an optimal meal menu suitable for each user and actually deliver the meal. Furthermore, analysis results that take emotional data and external factors into account make it possible to realize high-quality meal proposals that take psychological health into consideration.

[1348] "Health data" is physical information collected through wearable devices and other health monitoring equipment, such as a user's heart rate, number of steps taken, and sleep duration.

[1349] "Dietary history" refers to information such as the contents, calories, and nutrients of the meals a user has eaten, and is a record collected through photographs or manual input.

[1350] "Emotional data" is information that represents the emotional state (e.g., satisfaction, stress, happiness) that a user feels while eating or engaging in an activity, and is data that is collected through manual input or an emotion engine.

[1351] An "individually optimized meal menu" is a meal suggestion generated based on collected health data, dietary history, and emotional data, taking into consideration the optimal nutritional balance and psychological satisfaction for the user.

[1352] "Food delivery service" refers to a delivery service that allows users to quickly obtain suggested meal menus, and is provided by affiliated restaurants and service providers.

[1353] "Feedback" refers to information that is used to input the user's feelings and level of satisfaction after eating, and to update the system's analysis results.

[1354] This invention is a system that collects and analyzes a user's health data, dietary history, and emotional data to provide an individually optimized meal menu, and can deliver meals to the user in cooperation with a food delivery service. Specific embodiments of this system are described below.

[1355] Hardware and Software

[1356] Hardware:

[1357] Smartphone: A device where the user enters data and views menu suggestions.

[1358] Wearable devices (e.g., Apple Watch, Fitbit): devices that collect health data such as a user's heart rate, number of steps, and sleep duration.

[1359] Server: A device for storing collected data, analyzing it, generating menus and processing feedback.

[1360] Network: A communications network for data communication between smartphones, wearable devices, and servers.

[1361] software:

[1362] Mobile application: An application for users to perform initial registration, data entry, menu browsing, emotion data entry, and feedback entry.

[1363] Emotion engine: Software for collecting and analyzing user emotion data.

[1364] Image analysis AI: An AI algorithm that analyzes food photos uploaded by users and extracts the food content and nutrients.

[1365] Server software: Software that stores and analyzes data, generates personalized optimization menus, and collects feedback.

[1366] Data processing and calculation

[1367] User Information Collection:

[1368] Users launch the application using their smartphone and access the initial registration screen. They enter their age, gender, allergy information, health goals, etc., and provide health data from their wearable device. This data is sent to the server in real time and stored.

[1369] Emotion data collection:

[1370] The user inputs their emotional state during daily mealtimes using the emotion engine, and sends the emotional data along with date and time information to the server. The server analyzes the received emotional data and generates an emotional profile for the user.

[1371] Learning eating habits:

[1372] Users take photos of their daily meals and upload them to the application. The server passes the photos to an image analysis AI, which extracts the type of food, calories, and macronutrients. The analysis results are saved as the user's diet history.

[1373] Generate menu suggestions:

[1374] The server generates an individually optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day). The suggested menu is notified to the user via a smartphone application. When the user selects a suggested menu, the meal is delivered via a food delivery service.

[1375] Collecting and analyzing feedback:

[1376] After eating, users input their satisfaction and emotional state using the emotion engine, and this feedback data is sent to the server, analyzed, and used to optimize menu suggestions for future meals.

[1377] Specific examples

[1378] Examples:

[1379] 1. User Information Collection:

[1380] A 30-year-old female user enters her food allergies and health goal (muscle gain) when registering for the first time.

[1381] 2. Health Data Collection:

[1382] Fitbit sends data such as heart rate, steps, and sleep time to the app in real time.

[1383] 3. Emotional Data Collection:

[1384] A user who is feeling stressed because things aren't going well at work enters emotional data into the app.

[1385] 4. Dietary Data Collection:

[1386] Take a photo of your lunch of "salad and salmon fillet" and upload it to the app.

[1387] 5. Menu suggestions:

[1388] The AI ​​analyzes the situation and suggests "hot pot with roasted green tea and plenty of vegetables," which helps reduce stress.

[1389] 6. Food delivery orders:

[1390] Order the suggested menu with one click and have it delivered within 30 minutes.

[1391] 7. Feedback Collection:

[1392] After eating, the participants enter feedback such as "satisfied" and "stress reduced."

[1393] Example prompt sentence:

[1394] The user enters that she is a 30-year-old woman, has no allergies, and her health goal is to gain muscle.

[1395] The wearable device collected real-time data including 120 heart rates, 8,000 steps, and 7 hours of sleep.

[1396] A user inputs emotional data such as "I'm feeling stressed at work." He uploads a photo of himself eating "salad and salmon fillet" for lunch.

[1397] The AI ​​analyzed the data and recommended "Hot Pot with Roasted Green Tea and Lots of Vegetables" to the user. The user ordered the menu with one click and it was delivered in 30 minutes.

[1398] After eating, the user entered feedback such as "I feel satisfied" and "My stress has been reduced."

[1399] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[1400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1401] Step 1: Collect user information

[1402] Users launch the smartphone app and access the initial registration screen, where they enter basic information such as age, gender, allergy information, and health goals. The entered information is sent via the device to a server, which then stores the data and creates a user profile.

[1403] Input: Age, Gender, Allergy Information, Health Goals

[1404] Output: User profile stored on the server

[1405] Step 2: Collecting health data

[1406] When a user uses a wearable device (e.g., Fitbit) to go about their daily life, health data such as heart rate, number of steps, and sleep time are collected in real time. This data is sent to a server via the smartphone, and the server adds and stores this data in the user profile.

[1407] Input: Health data from wearable devices

[1408] Output: Updated user profile stored on the server

[1409] Step 3: Collecting emotion data

[1410] After each meal, users input their emotional state (e.g., satisfaction, stress, happiness) using a smartphone app. This emotional data, along with date and time information, is sent to a server, which then generates an emotional profile for the user.

[1411] Input: Date and time information, emotion data

[1412] Output: Emotion profile stored on the server

[1413] Step 4: Collect dietary data

[1414] Users take photos of their daily meals with their smartphones and upload them to the application. The device then sends the photo data to a server, which uses image analysis AI to extract the type of food, calories, and key nutrients from the photo. The extracted data is then saved on the server as the user's diet history.

[1415] Input: Food photo

[1416] Output: Meal history stored on the server

[1417] Step 5: Generate menu suggestions

[1418] The server integrates the user's health data, dietary history, emotional data, and external factors (season, weather, time of day) and uses a generative AI model to generate an individually optimized meal menu, which is then sent to the user via a smartphone application.

[1419] Input: Health data, diet history, emotional data, external factors

[1420] Output: Suggested meal menu

[1421] Step 6: Order food delivery

[1422] When the user checks and selects the meal menu on the smartphone application, the server sends the order information to the partner food delivery service, which then prepares the specified menu and delivers it to the user.

[1423] Input: Selected meal menu

[1424] Output: Delivered meal

[1425] Step 7: Collect and analyze feedback

[1426] After a meal, users use a smartphone app to input feedback about their satisfaction with the meal and their emotional state. The device then sends the feedback data to a server, which analyzes the data and uses it to suggest new menu items for the next meal.

[1427] Input: Feedback data (satisfaction and emotional state)

[1428] Output: Analysis results saved on the server (reflected in the next menu suggestion)

[1429] 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.

[1430] 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.

[1431] 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.

[1432] [Fourth embodiment]

[1433] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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.

[1438] 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).

[1439] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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."

[1446] This invention is a system that provides personalized optimal meals, and supports users' health management by collecting and analyzing their health data and dietary history, and proposing optimized meal menus based on the results. This system operates in cooperation with a server, terminals, and users.

[1447] Program processing overview

[1448] 1. Collection of User Information

[1449] The user launches the application, answers a questionnaire, and inputs health data from the wearable device.

[1450] The device transmits the collected data to the server in real time.

[1451] The server stores the received data and generates a user profile.

[1452] 2. AI-based learning of eating habits

[1453] Users take photos of their daily meals and upload them to the application.

[1454] The device sends the date and time information along with a photo of the meal to the server.

[1455] The server passes the received photos to AI for image analysis, extracting the type of food, calories, and key nutrients.

[1456] The server stores the analysis results in a database and updates the user's dietary history.

[1457] 3. Generate menu suggestions

[1458] The server generates an optimized meal menu based on the user's profile, meal history, and external factors (season, weather, time of day).

[1459] The terminal notifies the user of the proposed menu and displays it on the application.

[1460] 4. Collecting and analyzing feedback

[1461] After eating, users enter their taste and satisfaction in a feedback form.

[1462] The terminal sends this feedback to the server.

[1463] Based on the feedback received, the server updates the AI's learning data and further optimizes the next menu suggestion.

[1464] 5. Homemade recipe suggestions

[1465] The server generates home cooking recipes based on the user's data and sends them to the device.

[1466] The terminal notifies the user of the recipe and displays it on the application.

[1467] Specific examples

[1468] 1. Collection of User Information

[1469] When a user launches the application for the first time, they enter their age, gender, allergy information, and health goals (e.g., weight loss, muscle gain, etc.).

[1470] For example, if the user is a 40-year-old male with a goal of losing weight and is allergic to nuts, that information will be collected.

[1471] 2. Learning eating habits

[1472] A user eats salad and chicken for lunch and uploads a photo of it to the application, which also includes the date and time stamp.

[1473] The server analyzes this and extracts and stores data such as "salad," "chicken," and "500 kcal."

[1474] 3. Menu suggestions

[1475] The next day, the server analyzes the user's data and, taking into account their calorie goals and allergy information, suggests low-calorie, high-protein dishes such as "Konnyaku and Vegetable Simmered Dish" or "Grilled Chicken Salad."

[1476] 4. Feedback Collection

[1477] The user selects the suggested "grilled chicken salad" and eats it for lunch. After eating, the user enters their satisfaction with the meal and any areas for improvement into the application.

[1478] For example, provide feedback such as "there was too much chicken" or "the dressing was too watered down."

[1479] 5. Recipe suggestions

[1480] Taking into account the user's eating patterns and goals, the server suggests a "tofu steak recipe" for dinner, including instructions for grilling tofu to resemble steak and a list of the ingredients needed.

[1481] Users can access these recipes from the application and use them to prepare meals at home.

[1482] This system provides users with individually optimized meal menus, enabling them to efficiently manage their health. For companies, improving the health of their employees can lead to increased work efficiency and productivity.

[1483] The processing flow will be explained below.

[1484] Program processing steps

[1485] Step 1: Collect user information

[1486] 1. The user launches the application and accesses the initial registration screen.

[1487] 2. The device presents the user with questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects the responses.

[1488] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[1489] 4. The device sends the collected questionnaire answers and health data to the server in real time.

[1490] 5. The server stores the received data and generates an initial user profile.

[1491] Step 2: AI learns eating habits

[1492] 1. The user takes photos of their daily meals and uploads them to the application.

[1493] 2. The device sends the date and time information along with a photo of the meal to the server.

[1494] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[1495] 4. The server stores the extracted information in a database and updates the user's meal history.

[1496] Step 3: Generate menu suggestions

[1497] 1. The server generates an optimized meal menu based on the user's profile (health data and dietary history) and external factors (season, weather, time of day).

[1498] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[1499] 2. Based on the optimized menu, the server generates a daily menu list and sends it to the terminal.

[1500] 3. The device notifies the user of the proposed menu and displays it in the application.

[1501] Step 4: Collect and analyze feedback

[1502] 1. After the user selects the suggested menu and consumes the meal, the application displays a feedback form.

[1503] 2. Users enter information about the taste of the meal, their satisfaction, and areas for improvement in the feedback form.

[1504] 3. The device sends the input feedback to the server.

[1505] 4. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1506] Step 5: Homemade recipe suggestions

[1507] 1. The server generates recipes that can be easily made at home based on the user's profile and past meal data.

[1508] 2. The server sends the generated recipe information to the terminal.

[1509] 3. The device notifies the user of the recipe and displays it on the application.

[1510] 4. Users can check recipes through the application to help them cook at home.

[1511] Through these steps, users can receive individually optimized meal suggestions and efficiently manage their health. Companies can also maintain employee health and improve productivity by providing optimal meals based on employee health data.

[1512] Example 1

[1513] 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."

[1514] Health management has become increasingly important in recent years, but general dietary management systems often fail to provide meal menus that fully consider a user's individual health condition and dietary history. Furthermore, there is a lack of systems that appropriately reflect user feedback and continuously optimize meal menus. Furthermore, there is the challenge of providing recommended meal menus to users while taking into account allergy information and individual nutritional needs.

[1515] 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.

[1516] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for automatically synchronizing health data from the wearable device, means for analyzing food photos to extract nutritional information, means for customizing the menu based on the user's profile and external factors, and means for suggesting recipes that can be cooked at home. This makes it possible to provide an optimized diet menu based on the user's individual health condition and dietary history, and to continue improving the system based on continuous feedback.

[1517] "User's health data" refers to numerical information indicating the user's health condition, such as the user's age, gender, height, weight, heart rate, number of steps, and calories burned.

[1518] "Dietary history" refers to information such as the contents of meals the user has eaten in the past, photos, the date and time of eating, calories, nutrients, etc.

[1519] "Wearable device" refers to a device (e.g., smartwatch, fitness tracker) that is worn by the user to measure and collect health data.

[1520] "Meal menu" refers to information such as the contents, recipes, ingredients, calories, nutrients, etc. of the meals suggested for the user to consume.

[1521] "Feedback" refers to information such as opinions, satisfaction, and areas for improvement provided by users regarding the proposed meal menu.

[1522] "User profile" refers to data that compiles a user's personal information, health data, dietary history, allergy information, health goals, etc.

[1523] "Image analysis" refers to the use of AI to extract specific information from a photo, in this case, the type of food, calories, and macronutrients.

[1524] "External factors" refer to environmental factors that influence a user's food choices, such as season, weather, and time of day.

[1525] A "recipe" is a list of steps and ingredients needed to make a particular dish.

[1526] "Synchronizing" refers to multiple devices or systems sharing and updating the same data.

[1527] This invention is a system that provides a meal menu optimized for each user, and supports the user's health management. This system operates in cooperation with the user, terminal, and server.

[1528] Collection of User Information

[1529] Users first launch the application and enter basic health data such as age, gender, height, weight, health goals (weight loss, muscle gain, etc.), and allergy information. In addition, users sync data from their wearable devices (e.g., smartwatches, fitness trackers) with the application, including heart rate, steps, and calories burned. This data is immediately sent from the device to the server and saved as a user profile.

[1530] For example, a 40-year-old man launches the application, inputs that he weighs 70 kg and has a nut allergy, and provides data from his wearable device showing a heart rate of 70 bpm, 10,000 steps taken per day, and calories burned of 2,200 kcal.

[1531] Learning eating habits using AI

[1532] Users take photos of their daily meals and upload them to the app. The device then sends the photos of the meal along with the date and time information to a server. The server then uses AI to analyze the photos and extract the type of food, calories, and macronutrients (protein, fat, carbohydrates). The results of this analysis are stored in a database, and the user's diet history is updated.

[1533] For example, if a user has salad and chicken for lunch and uploads a photo of it, the server extracts and stores information such as "salad," "chicken," "500kcal," "protein 30g," "fat 10g," and "carbohydrates 40g" from the photo.

[1534] Generate menu suggestions

[1535] The server analyzes data based on the user's profile, meal history, and external factors (season, weather, time of day) to generate an optimized meal menu. The device notifies the user of this menu and displays it on the application.

[1536] For example, the server analyzes the user's data and suggests low-calorie, high-protein dishes such as "Konjac and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[1537] Collecting and analyzing feedback

[1538] After selecting a suggested menu and eating, the user enters their taste, satisfaction, and suggestions for improvement in a feedback form. The device then sends this feedback to the server. The server updates the AI's learning data based on the received feedback, further optimizing the next menu suggestion.

[1539] For example, a user can provide feedback such as "The grilled chicken was tasty, but it was a little bland," and the server can incorporate this information to improve its suggestions next time.

[1540] Homemade recipe suggestions

[1541] The server generates easy-to-make homemade recipes based on the user's data (health goals, dietary history, feedback), and the device notifies the user of the recipes and displays them in the application.

[1542] For example, the server generates a recipe (including ingredients and cooking steps) for making tofu steak for dinner, and the terminal notifies the user of this.

[1543] This invention allows users to efficiently manage their health by providing individually optimized meal menus and recipes, and also enables companies to manage the health status of their employees in an advanced manner, aiming to improve business efficiency and productivity.

[1544] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1545] Step 1: Collect user information

[1546] Input: A user launches the application and enters their age, gender, height, weight, allergy information, and health goals (e.g., weight loss, muscle gain). Additionally, they sync data from their wearable device (e.g., smartwatch, fitness tracker) such as heart rate, steps, and calories burned.

[1547] Specific operation: The user enters information such as "40-year-old male, weight 70 kg, desire to lose weight, nut allergy" and synchronizes data such as "heart rate 70 bpm, 10,000 steps per day, calories burned 2,200 kcal" from the wearable device.

[1548] Data processing / data calculation: The device collects this information and sends it to the server in real time. The server stores the received data in a database and generates a user profile.

[1549] Output: A user profile is generated and stored on the server.

[1550] Step 2: Learn your eating habits

[1551] Input: Users take photos of their daily meals and upload them to the application.

[1552] What happens: A user uploads a photo of "salad and chicken" for lunch, with date and time information attached.

[1553] Data processing / data calculation: The device sends photos of the meal and date and time information to the server. The server then passes the photos to the AI ​​for image analysis. The AI ​​extracts the type of food, calories, and macronutrients (e.g., protein, fat, carbohydrates).

[1554] Output: The server saves the analysis results in a database and updates the user's food history. Data such as "Salad," "Chicken," "Calories 500kcal," "Protein 30g," "Fat 10g," and "Carbohydrates 40g" are saved.

[1555] Step 3: Generate menu suggestions

[1556] Input: The server analyzes the data based on the user's profile, food history, and external factors (season, weather, time of day).

[1557] Specific operation: The server performs an analysis based on the user's data ("40-year-old male aiming to lose weight") and "eating history of salad and chicken."

[1558] Data processing / data calculation: The server uses AI to generate an optimized meal menu, taking into account calories, allergy information, nutritional balance, etc.

[1559] Output: A suggested menu is generated. Possible options include "Konnyaku and Vegetable Simmered Dish" and "Grilled Chicken Salad."

[1560] Specific operation: The generated menu is sent to the terminal and notified to the user.

[1561] Step 4: Collect and analyze feedback

[1562] Input: The user consumes the suggested menu and, after eating, enters their opinions, satisfaction, and suggestions for improvement in a feedback form on the application.

[1563] What happens: The user enters feedback like, "The grilled chicken was tasty, but it was a little bland."

[1564] Data processing / data calculation: The device sends feedback to the server, which updates the AI's learning data based on the received feedback.

[1565] Output: The server updates the data based on the feedback, and the next menu suggestions will be further optimized.

[1566] Step 5: Homemade recipe suggestions

[1567] Input: The server generates easy-to-make home-cooked recipes based on the user's profile, food history, and feedback.

[1568] Specific behavior: The server generates a "Tofu Steak Recipe (ingredients, cooking instructions)" for dinner.

[1569] Data processing / data calculation: The server selects recipes that suit the user's preferences and nutritional needs, and sends the generated recipes to the terminal.

[1570] Output: The recipe is notified to the user via the device and displayed in the application. Information such as "Tofu, grated daikon radish, soy sauce, cooking steps: 1. Fry the tofu..." is provided.

[1571] (Application example 1)

[1572] 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."

[1573] The main function of conventional dietary management systems is to collect users' health data and dietary history, but they are not sufficient in effectively utilizing this data to propose individually optimized dietary menus. Furthermore, there are only a limited number of systems that can collect user feedback and update analysis results to make more accurate proposals. Furthermore, there are issues with the inability to improve convenience and collect data in real time by utilizing smartphones, smart glasses, and wearable devices. There is a need to provide a system that can solve these issues and efficiently manage users' health.

[1574] 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.

[1575] In this invention, the server includes means for collecting a user's health data and dietary history, means for analyzing the collected health data and dietary history and generating an individually optimized diet menu, means for presenting the generated diet menu to the user, means for collecting user feedback and updating the analysis results, means for collecting the user's health data in real time using a smartphone, smart glasses, or wearable device, means for analyzing the user's meal photos and extracting macronutrients, a generative AI model for generating a diet menu suited to the user's health goals based on the extracted data, and means for notifying the user's device of the generated menu, thereby enabling efficient health management for the user.

[1576] "User health data" refers to information related to the user's physical condition and health, and includes, for example, data such as heart rate, body temperature, blood pressure, blood sugar level, and sleep patterns.

[1577] "Dietary history" is a record of the meals a user has eaten, and includes information such as the type of meal, the time of intake, calories, and major nutrients.

[1578] "Means of collection" refers to devices or software for acquiring a user's health data and dietary history, such as smartphones, smart glasses, and wearable devices.

[1579] "Means for analysis" refers to technologies and methods for analyzing collected health data and dietary history to extract useful information, including, for example, AI algorithms and database management systems.

[1580] A "personally optimized meal menu" is a specific meal list that provides a meal plan that is best suited to the user based on the user's health condition and dietary history.

[1581] The "presentation means" refers to a device or method for informing the user of the generated meal menu, such as a smartphone app or a smart glasses display.

[1582] "Means for collecting feedback and updating analysis results" refers to methods for collecting opinions and impressions from users and using them to improve the system's analysis algorithms.

[1583] "Means of collecting data in real time" refers to technologies and devices that instantly acquire users' health data and reflect it directly in the system.

[1584] "Means for analyzing photos to extract key nutrients" includes technology that analyzes photos of meals taken by users to identify the nutrients and calories contained therein.

[1585] A "generative AI model" is an artificial intelligence algorithm that automatically generates optimal meal menus based on a user's health data and dietary history.

[1586] "Means for notifying the terminal" refers to techniques or methods for notifying the user of the generated meal menu, and includes, for example, push notifications to a smartphone or smart glasses.

[1587] The present invention is a system for efficiently managing a user's health, which operates in cooperation with a server, a terminal, and a user. Specifically, the system is implemented through the following process.

[1588] 1. Collection of User Information:

[1589] Hardware: Smartphones, smart glasses, wearable devices (e.g., Fitbit, Apple Watch)

[1590] Software: Health management apps (e.g., Apple Health, Google Fit)

[1591] Processing: The user launches the application and enters the required health data. Data is also automatically collected from the wearable device. This data is sent to the server in real time, and a user profile is generated.

[1592] 2. Learning eating habits:

[1593] Hardware: Smartphone camera

[1594] Software: Image analysis algorithms (e.g., OpenCV, TensorFlow)

[1595] Processing: The user takes a photo of their meal and uploads it to the application. The server receives the photo and performs image analysis to extract macronutrients, which then updates the user's diet history database.

[1596] 3.Generate menu suggestions:

[1597] Hardware: Server

[1598] Software: Machine learning algorithms (e.g., PyTorch, scikit-learn)

[1599] Processing: The server uses machine learning algorithms to generate a personalized meal plan based on the user's health profile and dietary history. This plan is then sent to the user's device and displayed on the app.

[1600] 4. Feedback collection and analysis:

[1601] Hardware: Smartphone

[1602] Software: Database management system (e.g., PostgreSQL)

[1603] Processing: After the meal, the user provides feedback. They input their satisfaction and impressions of the meal via a smartphone application, which is then sent to the server. The server uses this feedback data to update its AI algorithm and further optimize the menu suggestions for the next meal.

[1604] Specific examples

[1605] For example, a user may have "salad and chicken" for lunch, take a photo of it with their smartphone, and upload it to the application. The server analyzes this meal data, extracts calories and key nutrients, and saves them as a meal history. The next day, the server will suggest "low-calorie, high-protein grilled chicken salad" based on the user's health profile and meal history. This suggestion is notified to the user's smartphone. After the user selects this menu and eats it, they can enter their satisfaction and impressions into the application. This feedback will further improve the next suggestion.

[1606] Prompt Sentence Examples

[1607] By inputting the following prompts into the generative AI model, we can generate the optimal meal menu:

[1608] Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from dietary history and suggest menus that are optimal for achieving health goals. Also, consider whether the menu is easy to prepare. The suggested menus will be notified to the user's smartphone.

[1609] In this way, a system for efficiently managing the user's health is realized.

[1610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1611] Step 1:

[1612] Collection of User Information

[1613] Input: Health data entered by the user (e.g., age, gender, allergy information, health goals) and real-time health data collected from wearable devices (e.g., heart rate, body temperature, blood pressure).

[1614] Processing: The user launches the application and inputs the necessary health data. Further health data is automatically collected from the wearable device. This data is then sent to the server in real time via the device.

[1615] Output: Generated user profile.

[1616] Step 2:

[1617] Learning eating habits

[1618] Input: A photo of a meal taken by the user and uploaded to the application.

[1619] Processing: The server receives the uploaded meal photos and uses image analysis algorithms (e.g., OpenCV, TensorFlow) to identify the ingredients and dishes in the photos and extract macronutrients (e.g., calories, protein, fat, carbohydrates).

[1620] Output: The analyzed dietary data is stored in a dietary history database.

[1621] Step 3:

[1622] Generate menu suggestions

[1623] Input: User's health profile and diet history data.

[1624] Processing: The server uses machine learning algorithms (e.g., PyTorch, scikit-learn) to generate an individually optimized meal menu based on the user's health data, dietary history, and external factors (e.g., season, weather, time of day). The generative AI model uses a prompt: "Generate the following meal suggestions based on the user's profile and dietary history. Profile information includes age, gender, health goals, and allergy information. Calculate calorie intake and macronutrients from the dietary history and suggest a menu that best suits the health goals. Also, consider whether the menu is easy to prepare. The suggested menu will be sent to the user's smartphone."

[1625] Output: The generated optimal meal menu.

[1626] Step 4:

[1627] Meal menu notifications

[1628] Input: The generated meal menu.

[1629] Processing: The server sends a push notification to the user's device (e.g., smartphone, smart glasses) with the generated meal menu.

[1630] Output: The meal menu is displayed on the user's device.

[1631] Step 5:

[1632] Collecting and analyzing feedback

[1633] Input: Feedback provided by the user after eating (e.g., satisfaction, areas for improvement, impressions).

[1634] Processing: The user enters feedback into the application and sends it to the server via the device. The server stores the received feedback in a database and uses it to update the AI ​​algorithm and optimize the next menu suggestions.

[1635] Output: The updated parsing algorithm.

[1636] Through these steps, users are provided with a consistently and individually optimized meal menu, enabling efficient health management. By using this system, users' health status can be improved and continuous improvement can be achieved.

[1637] 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.

[1638] This invention is a system that combines and analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, terminals, and users.

[1639] Program processing overview

[1640] 1. Collection of User Information

[1641] The user starts the application and accesses the initial registration screen.

[1642] The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[1643] Users answer questions and also input health data (heart rate, steps, sleep data, etc.) from their wearable device.

[1644] The device transmits the collected data to the server in real time.

[1645] The server stores the received data and generates an initial user profile.

[1646] 2. Collecting and analyzing emotion data

[1647] During everyday mealtimes, the user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine.

[1648] The device collects emotion data and sends it to the server along with date and time information.

[1649] The server stores the received emotion data and generates an emotion profile for the user.

[1650] 3. AI-based learning of eating habits

[1651] Users take photos of their daily meals and upload them to the application.

[1652] The device sends the date and time information along with a photo of the meal to the server.

[1653] The server passes the photo to AI for image analysis, extracting the type of food, calories, and key nutrients.

[1654] The server stores the analysis results in a database and updates the user's dietary history.

[1655] 4. Generate menu suggestions

[1656] The server generates an optimized meal menu based on the user's profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[1657] The terminal notifies the user of the proposed menu and displays it on the application.

[1658] 5. Collecting and analyzing feedback

[1659] After eating, the user uses the emotion engine to input their satisfaction with the meal and their emotional state.

[1660] The terminal transmits the feedback data to the server.

[1661] The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1662] 6. Homemade recipe suggestions

[1663] The server generates recipes that can be easily made at home based on the user's profile, dietary data, and emotional data.

[1664] The terminal notifies the user of the generated recipe and displays it on the application.

[1665] Users can check recipes from the application to help them cook at home.

[1666] Specific examples

[1667] 1. Collection of User Information

[1668] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., wanting to lose weight).

[1669] For example, if the user is a 30-year-old woman and wants to prevent diabetes, that information is collected.

[1670] 2. Collecting and analyzing emotion data

[1671] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using an emotion engine.

[1672] For example, a user inputs into the emotion engine, "I'm feeling stressed because things aren't going well at work."

[1673] 3. Learning eating habits

[1674] A user takes a photo of their lunch, "Salad and Grilled Chicken," and uploads it to the application.

[1675] The server analyzes this, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[1676] 4. Menu suggestions

[1677] The server takes into consideration the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect.

[1678] The terminal notifies the user of the proposed menu and displays it on the application.

[1679] 5. Collecting and analyzing feedback

[1680] The user selects the suggested "green tea and brown rice rice ball" and consumes it for lunch.

[1681] After eating, the emotion engine is used to input feedback such as "satisfied" or "stress reduced."

[1682] The terminal transmits the feedback data to the server.

[1683] 6. Recipe suggestions

[1684] The server considers that the user is looking for a "relaxing effect" and generates a recipe for "soup made with roasted green tea."

[1685] The terminal notifies the user of the recipe and displays it on the application.

[1686] Users can check the recipe through the application and make the soup at home.

[1687] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[1688] The processing flow will be explained below.

[1689] Program processing steps

[1690] Step 1: Collect user information

[1691] 1. The user launches the application and accesses the initial registration screen.

[1692] 2. The device asks the user questions such as age, gender, allergy information, and health goals (e.g., weight loss, muscle gain), and collects their responses.

[1693] 3. The user answers the questionnaire and enters health data (heart rate, steps, sleep data, etc.) obtained from the wearable device.

[1694] 4. The device sends the collected data to the server in real time.

[1695] 5. The server stores the received data and generates an initial user profile.

[1696] Step 2: Collect and analyze emotion data

[1697] 1. The user inputs their emotional state (e.g., satisfaction, stress, fatigue, etc.) using the emotion engine during everyday mealtimes.

[1698] 2. The device collects emotion data and sends it to the server along with date and time information.

[1699] 3. The server stores the received emotion data and generates an emotion profile for the user.

[1700] Step 3: AI learns eating habits

[1701] 1. The user takes photos of their daily meals and uploads them to the application.

[1702] 2. The device sends the date and time information along with a photo of the meal to the server.

[1703] 3. The server passes the received photo to AI, which performs image analysis and extracts the type of food, calories, and major nutrients.

[1704] 4. The server stores the extracted information in a database and updates the user's meal history.

[1705] Step 4: Generate menu suggestions

[1706] 1. The server generates an optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day).

[1707] Example: For a user trying to lose weight on a cold winter day, suggest a warm, low-calorie soup menu.

[1708] 2. The server generates a daily menu list and sends it to the terminal.

[1709] 3. The device notifies the user of the proposed menu and displays it in the application.

[1710] Step 5: Collect and analyze feedback

[1711] 1. After the user selects the suggested menu and consumes the meal, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[1712] 2. The device sends the feedback data to the server.

[1713] 3. The server analyzes the received feedback, stores it as learning data for the AI, and further optimizes the menu suggestions for the next time.

[1714] Step 6: Homemade recipe suggestions

[1715] 1. The server generates recipes that can be easily made at home based on the user's profile, past meal data, and emotional data.

[1716] 2. The server sends the generated recipe to the device.

[1717] 3. The device notifies the user of the recipe and displays it on the application.

[1718] 4. Users can check recipes from the application to help them cook at home.

[1719] Specific examples

[1720] Step 1: Collect user information

[1721] 1. The user launches the application for the first time and answers a questionnaire.

[1722] 2. The device sends the information collected from the user (age 30, female, nut allergy, weight loss goal) to the server.

[1723] 3. The server stores the data and generates a user profile.

[1724] Step 2: Collect and analyze emotion data

[1725] 1. The user inputs "I feel stressed" in the lunch scene using the emotion engine.

[1726] 2. The device sends the emotion data and date and time information to the server.

[1727] 3. The server stores the emotion data and generates an emotion profile for the user.

[1728] Step 3: AI learns eating habits

[1729] 1. A user eats "Salad and Grilled Chicken" for lunch, takes a photo, and uploads it to the application.

[1730] 2. The device sends a photo of the meal and date and time information to the server.

[1731] 3. The server uses AI to extract "salad," "grilled chicken," and "400 kcal" and stores them in a database.

[1732] Step 4: Generate menu suggestions

[1733] 1. The server takes into account the emotional data "stress" and generates a menu of "green tea and brown rice rice balls" that is expected to have a relaxing effect.

[1734] 2. The server sends the menu list to the terminal, and the terminal notifies the user of the menu.

[1735] Step 5: Collect and analyze feedback

[1736] 1. The user selects the suggested "rice ball with green tea and brown rice" and, after eating, uses the emotion engine to input feedback such as "satisfied" and "stress reduced."

[1737] 2. The device sends the feedback data to the server.

[1738] 3. The server analyzes the feedback and incorporates it into its next proposal.

[1739] Step 6: Homemade recipe suggestions

[1740] 1. The server generates a recipe called "Soup made with roasted green tea" that emphasizes its relaxing effect.

[1741] 2. The server sends the recipe to the terminal and notifies the user.

[1742] 3. User checks the recipe and makes the soup at home.

[1743] This system allows users to receive optimal meal menus based on their health data, dietary history, and emotional data. By taking emotional data into account, meal suggestions are made that take into account the user's psychological health, allowing for efficient individual health management.

[1744] Example 2

[1745] 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."

[1746] Health management is a very important issue in modern society, and many people are looking for ways to effectively manage their health. However, while conventional systems collect individual health data and dietary history, they are limited in their ability to comprehensively analyze this data and propose individually optimized meal menus. Furthermore, because they are limited to simple data analysis without considering emotional data or external factors, it is difficult to provide suggestions that are tailored to the user's psychological satisfaction or individual circumstances. Therefore, there is a need for multifaceted analysis of data and individually optimized meal suggestions in health management.

[1747] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting health data, dietary history, and emotional data of the user, means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu, and means for presenting the generated meal menu to the user. This enables more accurate meal menu suggestions based on the individual circumstances of the user. In addition, by including means for inputting the user's emotional state in daily meal situations, means for generating meal menus taking external factors into consideration, means for learning the user's eating habits using AI and updating the meal history, and means for generating recipes that can be made at home, it becomes possible to realize more comprehensive health management that also takes the user's psychological health into consideration.

[1748] "Health data" refers to information related to the user's physical condition and physical status, and specifically includes heart rate, number of steps, sleep data, weight, blood pressure, etc.

[1749] "Diet history" is a record of meals the user has eaten in the past, and specifically includes information about the ingredients, types of food, calories, and nutrients eaten.

[1750] "Emotion data" is information that represents the user's psychological state during everyday mealtimes, and includes emotional states such as "satisfaction," "stress," and "happiness" that are input using the emotion engine.

[1751] "Optimized meal menu" refers to a meal plan that is generated to suit an individual user by analyzing the user's health data, dietary history, and emotional data.

[1752] "Feedback" refers to information users enter about their satisfaction and emotional state after a meal, data the system uses to improve its next menu suggestion.

[1753] "External factors" are environmental factors that are taken into consideration when generating a meal menu, and specifically include the season, weather, time of day, etc.

[1754] An "emotion engine" is an interface that allows users to input their emotional state and is a tool for collecting emotional data such as satisfaction and stress.

[1755] "Image analysis" refers to the technological process of analyzing photos of meals uploaded by users to extract the type of food, calories, and macronutrients.

[1756] "Homemade recipes" refer to suggestions of cooking steps and ingredients that users can easily make at home, and are generated based on health data and dietary history.

[1757] A "profile" is an individual collection of information generated by integrating a user's health data, dietary history, and emotional data, and refers to the basic data used by the system to make optimal suggestions to the user.

[1758] This invention is a system that analyzes a user's health data, diet history, and emotional data to provide an optimal individual meal menu. This system is realized by the cooperation of a server, a terminal, and a user.

[1759] The system first has a means to collect the user's health data, dietary history, and emotional data. Specifically, the user launches the application and accesses the initial registration screen. The device presents the user with questions about their age, gender, allergy information, health goals, etc., which the user answers. The user also inputs health data (heart rate, number of steps, sleep data, etc.) from a wearable device (e.g., a smartwatch). The device transmits this collected data to a server in real time, and the server stores the received data and generates an initial user profile.

[1760] Next, emotional data is collected and analyzed. The user uses the emotion engine to input their emotional state (e.g., satisfaction, stress, happiness, etc.) during everyday mealtimes. The device collects the emotional data and sends it to the server along with date and time information. The server stores the received emotional data and generates an emotional profile for the user.

[1761] Another important feature is the AI's ability to learn eating habits. Users take photos of their daily meals and upload them to the application. The device then sends the photos of the meal along with the date and time information to the server. The server then analyzes the photos using image analysis tools (e.g., Google Cloud Vision API) to extract data such as the type of food, calories, and macronutrients. The results of this analysis are stored in a database, and the user's eating history is updated.

[1762] Based on this data, the server generates an optimized meal menu taking into account the user profile (health data, dietary history, emotional data) and external factors (season, weather, time of day). The device notifies the user of the generated menu and displays it on the application.

[1763] Users can provide feedback after their meal by inputting their satisfaction with the meal and their emotional state using the emotion engine, and the device sends the feedback data to the server, which analyzes this feedback and stores it as learning data for the AI ​​to further optimize menu suggestions for the next time.

[1764] The server can also generate recipes that can be easily made at home based on the user profile, dietary data, and emotional data. The device notifies the user of the recipes and displays them on the application. The user can check the recipes through the application and use them to prepare meals at home.

[1765] Specific examples

[1766] 1. Collection of User Information

[1767] When a user launches the application for the first time, they enter their age, gender, allergy information, and diet goal (e.g., want to lose weight). For example, if the user is a 30-year-old woman who wants to prevent diabetes, that information is collected.

[1768] 2. Collecting and analyzing emotion data

[1769] When a user has lunch, they input their emotional state, such as "satisfaction," "stress," or "happiness," using the emotion engine. For example, the user might input, "I'm feeling stressed because things aren't going well at work."

[1770] 3. Learning eating habits

[1771] A user takes a photo of their lunch of "salad and grilled chicken" and uploads it to the app. The server analyzes the photo, extracts data such as "salad," "grilled chicken," and "400 kcal," and stores it.

[1772] 4. Menu suggestions

[1773] The server takes into account the user's emotional data that they are "feeling stressed" and suggests "green tea and brown rice rice balls," which are expected to have a relaxing effect. The device notifies the user of the suggested menu and displays it on the application.

[1774] 5. Collecting and analyzing feedback

[1775] The user consumes the "green tea and brown rice rice ball" and uses the emotion engine to input feedback such as "satisfied" or "stress reduced." The device then sends the feedback data to the server.

[1776] 6. Recipe suggestions

[1777] The server generates a recipe for "soup using roasted green tea," taking into account the user's desire for a relaxing effect. The device notifies the user of the recipe and displays it on the application. The user then checks the recipe through the application and makes the soup at home.

[1778] Prompt Sentence Examples

[1779] "Please suggest the best lunch menu for a user who is a 30-year-old woman and has a health goal of preventing diabetes."

[1780] "Please suggest a menu that will have a relaxing effect on users who are feeling stressed from work during lunch."

[1781] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1782] Step 1: Collect user information

[1783] Input: The user launches the application for the first time, answers questions such as age, gender, allergy information, and health goals, and inputs health data from the wearable device.

[1784] Processing: The device collects the information entered by the user in real time and sends it to the server, which stores the received data and creates an initial user profile.

[1785] Output: A user profile is generated and stored on the server.

[1786] Specific operation: Questions such as "Please enter your age" and "Please select your gender" are displayed on the device screen, and the user answers accordingly. The smartwatch data is also linked to the app.

[1787] Step 2: Collect and analyze emotion data

[1788] Input: The user uses the emotion engine in everyday meal scenarios to input emotional states such as satisfaction, stress, and happiness.

[1789] Processing: The device collects emotion data and sends it to the server along with date and time information. The server stores the received emotion data and creates an emotion profile for the user.

[1790] Output: An emotional profile is generated and stored on the server.

[1791] Specific operation: After a meal, the message "How are you feeling right now?" appears on the device screen, and the user can select from options such as "Satisfied," "Stressed," or "Happy." Another example includes inputting "I'm feeling stressed because things aren't going well at work."

[1792] Step 3: AI learns eating habits

[1793] Input: The user takes photos of their daily meals and uploads the photos and date and time information to the application.

[1794] Processing: The device sends a photo of the meal and the date and time information to the server, which then uses image analysis tools (e.g., Google Cloud Vision API) to analyze the photo and extract the type of food, calories, and macronutrients.

[1795] Output: The analysis results are saved in a database and the user's diet history is updated.

[1796] Specific operation: A prompt appears saying "Please upload a photo of your meal." The user takes a photo of themselves eating "salad and grilled chicken" and uploads it. The server analyzes this and extracts data such as "salad," "grilled chicken," and "400 kcal."

[1797] Step 4: Generate menu suggestions

[1798] Input: User profile (health data, dietary history, emotional data) and external factors (season, weather, time of day).

[1799] Processing: The server uses AI models to generate an optimized meal menu based on this data, taking into account external factors and making suggestions that match the user's emotional state.

[1800] Output: The generated meal menu is sent to the terminal and displayed to the user on the application.

[1801] Specific operation: The server selects "Green tea and brown rice onigiri" as the most suitable menu item, saying "Generating a menu with a relaxing effect..." The device then notifies the user, "We have the perfect menu item for you! 'Green tea and brown rice onigiri'."

[1802] Step 5: Collect and analyze feedback

[1803] Input: After the user consumes the proposed meal menu, the emotion engine is used to input the satisfaction level and emotional state of the meal.

[1804] Processing: The device sends the feedback data to the server, which analyzes the feedback and stores it as learning data for the AI.

[1805] Output: Feedback is used to further optimize the next menu suggestion.

[1806] Specific operation: The user is satisfied after eating the "Green Tea and Brown Rice Rice Ball" and enters feedback such as "Satisfied" and "Stress reduced." The device displays the message "Sending feedback..." followed by "Sent."

[1807] Step 6: Homemade recipe suggestions

[1808] Input: User profile, dietary data, and emotional data.

[1809] Processing: The server uses this data to generate recipes that can be easily made at home. It also considers the user's emotional state and suggests optimal home-cooked recipes.

[1810] Output: The generated recipe is notified to the terminal and displayed to the user on the application.

[1811] Specific operation: The server generates a recipe for "soup using roasted green tea" with the message "Generating a recipe with a relaxing effect...". The device notifies the user, "A new recipe is available! 'Soup using roasted green tea'." The user checks the recipe through the application and makes the soup at home.

[1812] (Application example 2)

[1813] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1814] There are currently systems that collect and analyze health data, dietary history, and emotional data separately to suggest optimal meal menus. However, these systems are not linked to food delivery services, making it difficult for users to quickly obtain the suggested meals. Furthermore, they cannot suggest detailed menus that take into account emotional data and health goals, making it impossible to make qualitative suggestions that take psychological health into account. There is a need to solve these issues.

[1815] 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.

[1816] In this invention, the server includes means for collecting a user's health data, dietary history, and emotional data; means for analyzing the collected health data, dietary history, and emotional data to generate an individually optimized meal menu; means for presenting the generated meal menu to the user and delivering the suggested meals via a food delivery service; and means for collecting feedback from the user, updating the analysis results, and optimizing the next menu proposal. This makes it possible to quickly propose an optimal meal menu suitable for each user and actually deliver the meal. Furthermore, analysis results that take emotional data and external factors into account make it possible to realize high-quality meal proposals that take psychological health into consideration.

[1817] "Health data" is physical information collected through wearable devices and other health monitoring equipment, such as a user's heart rate, number of steps taken, and sleep duration.

[1818] "Dietary history" refers to information such as the contents, calories, and nutrients of the meals a user has eaten, and is a record collected through photographs or manual input.

[1819] "Emotional data" is information that represents the emotional state (e.g., satisfaction, stress, happiness) that a user feels while eating or engaging in an activity, and is data that is collected through manual input or an emotion engine.

[1820] An "individually optimized meal menu" is a meal suggestion generated based on collected health data, dietary history, and emotional data, taking into consideration the optimal nutritional balance and psychological satisfaction for the user.

[1821] "Food delivery service" refers to a delivery service that allows users to quickly obtain suggested meal menus, and is provided by affiliated restaurants and service providers.

[1822] "Feedback" refers to information that is used to input the user's feelings and level of satisfaction after eating, and to update the system's analysis results.

[1823] This invention is a system that collects and analyzes a user's health data, dietary history, and emotional data to provide an individually optimized meal menu, and can deliver meals to the user in cooperation with a food delivery service. Specific embodiments of this system are described below.

[1824] Hardware and Software

[1825] Hardware:

[1826] Smartphone: A device where the user enters data and views menu suggestions.

[1827] Wearable devices (e.g., Apple Watch, Fitbit): devices that collect health data such as a user's heart rate, number of steps, and sleep duration.

[1828] Server: A device for storing collected data, analyzing it, generating menus and processing feedback.

[1829] Network: A communications network for data communication between smartphones, wearable devices, and servers.

[1830] software:

[1831] Mobile application: An application for users to perform initial registration, data entry, menu browsing, emotion data entry, and feedback entry.

[1832] Emotion engine: Software for collecting and analyzing user emotion data.

[1833] Image analysis AI: An AI algorithm that analyzes food photos uploaded by users and extracts the food content and nutrients.

[1834] Server software: Software that stores and analyzes data, generates personalized optimization menus, and collects feedback.

[1835] Data processing and calculation

[1836] User Information Collection:

[1837] Users launch the application using their smartphone and access the initial registration screen. They enter their age, gender, allergy information, health goals, etc., and provide health data from their wearable device. This data is sent to the server in real time and stored.

[1838] Emotion data collection:

[1839] The user inputs their emotional state during daily mealtimes using the emotion engine, and sends the emotional data along with date and time information to the server. The server analyzes the received emotional data and generates an emotional profile for the user.

[1840] Learning eating habits:

[1841] Users take photos of their daily meals and upload them to the application. The server passes the photos to an image analysis AI, which extracts the type of food, calories, and macronutrients. The analysis results are saved as the user's diet history.

[1842] Generate menu suggestions:

[1843] The server generates an individually optimized meal menu based on the user's health data, dietary history, emotional data, and external factors (season, weather, time of day). The suggested menu is notified to the user via a smartphone application. When the user selects a suggested menu, the meal is delivered via a food delivery service.

[1844] Collecting and analyzing feedback:

[1845] After eating, users input their satisfaction and emotional state using the emotion engine, and this feedback data is sent to the server, analyzed, and used to optimize menu suggestions for future meals.

[1846] Specific examples

[1847] Examples:

[1848] 1. User Information Collection:

[1849] A 30-year-old female user enters her food allergies and health goal (muscle gain) when registering for the first time.

[1850] 2. Health Data Collection:

[1851] Fitbit sends data such as heart rate, steps, and sleep time to the app in real time.

[1852] 3. Emotional Data Collection:

[1853] A user who is feeling stressed because things aren't going well at work enters emotional data into the app.

[1854] 4. Dietary Data Collection:

[1855] Take a photo of your lunch of "salad and salmon fillet" and upload it to the app.

[1856] 5. Menu suggestions:

[1857] The AI ​​analyzes the situation and suggests "hot pot with roasted green tea and plenty of vegetables," which helps reduce stress.

[1858] 6. Food delivery orders:

[1859] Order the suggested menu with one click and have it delivered within 30 minutes.

[1860] 7. Feedback Collection:

[1861] After eating, the participants enter feedback such as "satisfied" and "stress reduced."

[1862] Example prompt sentence:

[1863] The user enters that she is a 30-year-old woman, has no allergies, and her health goal is to gain muscle.

[1864] The wearable device collected real-time data including 120 heart rates, 8,000 steps, and 7 hours of sleep.

[1865] A user inputs emotional data such as "I'm feeling stressed at work." He uploads a photo of himself eating "salad and salmon fillet" for lunch.

[1866] The AI ​​analyzed the data and recommended "Hot Pot with Roasted Green Tea and Lots of Vegetables" to the user. The user ordered the menu with one click and it was delivered in 30 minutes.

[1867] After eating, the user entered feedback such as "I feel satisfied" and "My stress has been reduced."

[1868] This system allows users to enjoy optimal meal menus based on their health data, dietary history, and emotional data, enabling efficient individual health management. In addition, by taking emotional data into account, it is possible to make meal suggestions that take into consideration the user's psychological health.

[1869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1870] Step 1: Collect user information

[1871] Users launch the smartphone app and access the initial registration screen, where they enter basic information such as age, gender, allergy information, and health goals. The entered information is sent via the device to a server, which then stores the data and creates a user profile.

[1872] Input: Age, Gender, Allergy Information, Health Goals

[1873] Output: User profile stored on the server

[1874] Step 2: Collecting health data

[1875] When a user uses a wearable device (e.g., Fitbit) to go about their daily life, health data such as heart rate, number of steps, and sleep time are collected in real time. This data is sent to a server via the smartphone, and the server adds and stores this data in the user profile.

[1876] Input: Health data from wearable devices

[1877] Output: Updated user profile stored on the server

[1878] Step 3: Collecting emotion data

[1879] After each meal, users input their emotional state (e.g., satisfaction, stress, happiness) using a smartphone app. This emotional data, along with date and time information, is sent to a server, which then generates an emotional profile for the user.

[1880] Input: Date and time information, emotion data

[1881] Output: Emotion profile stored on the server

[1882] Step 4: Collect dietary data

[1883] Users take photos of their daily meals with their smartphones and upload them to the application. The device then sends the photo data to a server, which uses image analysis AI to extract the type of food, calories, and key nutrients from the photo. The extracted data is then saved on the server as the user's diet history.

[1884] Input: Food photo

[1885] Output: Meal history stored on the server

[1886] Step 5: Generate menu suggestions

[1887] The server integrates the user's health data, dietary history, emotional data, and external factors (season, weather, time of day) and uses a generative AI model to generate an individually optimized meal menu, which is then sent to the user via a smartphone application.

[1888] Input: Health data, diet history, emotional data, external factors

[1889] Output: Suggested meal menu

[1890] Step 6: Order food delivery

[1891] When the user checks and selects the meal menu on the smartphone application, the server sends the order information to the partner food delivery service, which then prepares the specified menu and delivers it to the user.

[1892] Input: Selected meal menu

[1893] Output: Delivered meal

[1894] Step 7: Collect and analyze feedback

[1895] After a meal, users use a smartphone app to input feedback about their satisfaction with the meal and their emotional state. The device then sends the feedback data to a server, which analyzes the data and uses it to suggest new menu items for the next meal.

[1896] Input: Feedback data (satisfaction and emotional state)

[1897] Output: Analysis results saved on the server (reflected in the next menu suggestion)

[1898] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1899] 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.

[1900] 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 robot 414.

[1901] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1902] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1903] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1904] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1905] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1906] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1907] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1908] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1909] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1910] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1911] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1912] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1913] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed speci...

Claims

1. means for collecting health data and dietary history of a user; A means for analyzing the collected health data and dietary history to generate an individually optimized diet menu; means for presenting the generated meal menu to a user; a means of collecting user feedback and updating the analysis results; A system including:

2. The system according to claim 1 , further comprising means for generating a meal menu that takes into account external factors based on the collected health data and dietary history.

3. 10. The system of claim 1, further comprising means for filtering meal menus based on allergy information and dietary needs.

4. 10. The system of claim 1, further comprising means for storing user-entered health data and diet history and for continuous learning.

5. The system according to claim 1 , further comprising means for suggesting recipes for the user to cook at home.

Images