System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving and storing inputted health information and preferences of a user; means for collecting and storing fitness data of the user; means for generating an optimal cooking recipe using a generative AI model based on the health information, preferences, and fitness data; and means for providing the generated cooking recipe to a user device.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Today's people, especially those struggling with obesity, lack easy access to healthy diet recipes that take into account their health condition and preferences. Traditional recipe books and websites often lack the functionality to combine individual health and fitness data to provide appropriate recipes. This makes it difficult to create personalized meal plans, making it difficult to achieve sustainable health management and effective dieting. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems by providing a system including a means for inputting and saving a user's health information and preferences, a means for collecting and saving fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information and fitness data, and a means for providing the generated cooking recipes to a user terminal. Furthermore, the system also includes a means for cleaning and standardizing the data and converting it into an input format for the generative AI model, and a means for providing photos or videos to visually support the recipe quantities and cooking steps, thereby realizing more accurate and personalized recipe provision.

[0006] "User's health information" refers to data relating to the user's personal health, such as age, height, weight, and blood pressure.

[0007] "Preferences" is information about the types of ingredients and dishes that the user likes.

[0008] "Fitness data" refers to data related to a user's fitness activities, such as the amount of exercise, number of steps, and exercise time.

[0009] A "generative AI model" is an artificial intelligence model that takes health information, preferences, and fitness data as input and generates optimal cooking recipes.

[0010] A "cooking recipe" is information about how to prepare a dish, including specific ingredients and their amounts, and cooking steps.

[0011] "Data cleaning and standardization" refers to the process of removing duplicates from input data, filling in missing values, scaling numbers, normalizing characters, etc.

[0012] A "user terminal" is an electronic device used by a user, such as a smartphone or tablet.

[0013] "Visual support" is a function that provides photos and videos to help users prepare their dishes. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] As a form for implementing this invention, a system that collects a user's health information, preferences, and fitness data and generates optimal cooking recipes using a generative AI model will be specifically described.

[0036] System configuration

[0037] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, and a means for providing the generated cooking recipes to a user terminal.

[0038] User Registration and Login

[0039] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0040] Enter your health information and preferences

[0041] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0042] Fitness data integration

[0043] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0044] Recipe Generation

[0045] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0046] Recipe Suggestions

[0047] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0048] Cooking instructions and visual aids

[0049] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0050] Specific examples

[0051] For example, the following is a specific example of a user named Tanaka Taro using the system. Tanaka Taro logs in and enters his health information, such as age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods, "chicken, broccoli, and brown rice." Next, one week's worth of fitness data is automatically sent from his smartwatch to the server.

[0052] On the server side, a generative AI model is used based on Tanaka Taro's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Tanaka Taro's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients (e.g., 200g chicken breast, 100g broccoli, 150g brown rice) as well as cooking instructions and photos for each step. This allows Tanaka Taro to easily create healthy meals with visual support.

[0053] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0054] The processing flow will be explained below.

[0055] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[0056] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[0057] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[0058] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[0059] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[0060] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[0061] Step 7: The server extracts health and fitness data periodically or upon user request. The server cleans (removes duplicates, fills in missing data) and standardizes the data.

[0062] Step 8: The server uses the generated AI model to input the cleaned and standardized data and generate the optimal cooking recipe for the user. The server stores the generated recipe in a database.

[0063] Step 9: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[0064] Step 10: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[0065] Example 1

[0066] 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."

[0067] In modern society, there are few systems that efficiently provide optimal cooking recipes based on a user's individual health condition and preferences. It is also difficult for users to effortlessly integrate health and fitness information and easily obtain specific cooking guidance based on data. Furthermore, the lack of visual support makes it difficult for even beginners to cook with confidence. As a result, users are not being adequately supported to lead a healthy lifestyle.

[0068] 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.

[0069] In this invention, the server includes a means for receiving and storing a user's health information and preferences, a means for collecting and storing the user's fitness information, and a means for the user to log in and input their health information and preferences. This allows the server to generate and provide optimal cooking recipes based on the user's health information and preferences. The server also includes a means for automatically collecting fitness data and cleaning and standardizing the data, enabling accurate recipe generation using a generative AI model. Furthermore, the server includes a means for providing photos or videos to visually support the recipe's portion sizes and cooking steps, allowing users to cook with peace of mind and easily create healthy meals.

[0070] "User's health information" refers to information related to an individual's health condition, such as age, height, weight, and blood pressure, entered by the user.

[0071] "Preferences" is information about ingredients and dishes that the user likes.

[0072] "Fitness information" refers to information that indicates a user's exercise data and activity trends, such as the number of steps and exercise time collected from smart devices and fitness apps.

[0073] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected user health, preference, and fitness information.

[0074] "Data cleaning" is the process of removing noise and inaccurate information from collected data and making it accurate and consistent.

[0075] "Data standardization" is the process of converting data collected in different formats or units into a unified format.

[0076] The "recipe generation means" is a part of the system that uses a generative AI model to calculate and generate the optimal cooking recipe for the user.

[0077] "Visual support" refers to a method of visually indicating the amounts of ingredients and cooking steps in a cooking recipe, using photographs or videos, to make it easier for users to understand how to cook.

[0078] A "user terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[0079] As an embodiment of the present invention, a system that collects a user's health information, preferences, and fitness information and generates optimal cooking recipes using a generative AI model is described below.

[0080] System configuration

[0081] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness information, a means for generating optimal cooking recipes using a generative AI model based on the collected health information, preferences, and fitness information, and a means for providing the generated cooking recipes to a user terminal.

[0082] User Registration and Login

[0083] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0084] Enter your health information and preferences

[0085] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0086] Fitness data integration

[0087] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0088] Recipe Generation

[0089] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness information received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0090] Recipe Suggestions

[0091] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0092] Cooking instructions and visual aids

[0093] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0094] Specific examples

[0095] For example, the following is a specific example of a user named Mr. A using the system. Mr. A logs in and enters health information such as his age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods being "chicken, broccoli, and brown rice." Next, one week's worth of fitness information is automatically sent from his smartwatch to the server.

[0096] Prompt Sentence Examples

[0097] "A 32-year-old, 175cm, 85kg male user likes chicken, broccoli, and brown rice. His fitness information includes his number of steps and exercise time for one week. Generate the best cooking recipes for him."

[0098] result

[0099] On the server side, a generative AI model is used based on Mr. A's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Mr. A's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients, such as 200g of chicken breast, 100g of broccoli, and 150g of brown rice, as well as cooking instructions and photos for each step. This allows Mr. A to easily create healthy dishes with visual support.

[0100] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Program processing flow

[0103] Step 1: User Registration

[0104] Action 1: A user accesses the system's website or app using a smartphone or tablet.

[0105] Input: User accesses.

[0106] Action: The user clicks the "Sign Up" button and fills in the form with information such as name, email address, and password.

[0107] Output: The data entered into the registration form.

[0108] Action 2: The terminal sends the entered information to the server.

[0109] Input: Data entered into the registration form.

[0110] Processing: The device sends the information to the specified URL on the server.

[0111] Output: The data received on the server side.

[0112] Action 3: The server stores the received information in a database and generates and returns a user ID.

[0113] Input: The data received on the server side.

[0114] Processing: The server saves the data to the database and generates a user ID.

[0115] Output: User ID and a message confirming registration.

[0116] Step 2: Log in

[0117] Action 1: User enters email address and password and submits the login form.

[0118] Input: User's email address and password.

[0119] Process: The device sends the login information to the server.

[0120] Output: The data received on the server side.

[0121] Action 2: The server checks its database to see if the entered email address and password match.

[0122] Input: The data received on the server side.

[0123] Action: Check the database to see if the email address and password match.

[0124] Output: Authentication result (success / failure).

[0125] Action 3: If there is a match, the server creates a session and returns an authentication token to the device.

[0126] Input: Authentication result successful.

[0127] Process: The server creates a session and issues an authentication token.

[0128] Output: An authentication token.

[0129] Step 3: Enter your health information and preferences

[0130] Action 1: After logging in, the user accesses a form to enter health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes).

[0131] Input: The user accesses the form.

[0132] Action: Display the form.

[0133] Output: Form screen.

[0134] Action 2: The user enters information into the form and presses the submit button.

[0135] Input: Health information and preferences entered into the form.

[0136] Processing: The terminal sends the entered information to the server.

[0137] Output: The data received on the server side.

[0138] Action 3: The server saves and updates the information in the database.

[0139] Input: The data received on the server side.

[0140] Processing: The server saves the data to the database and updates existing data as needed.

[0141] Output: Save result to database (success / failure).

[0142] Step 4: Connect your fitness data

[0143] Action 1: The user accesses the integration settings screen within the system.

[0144] Input: The user accesses the integration settings screen.

[0145] Processing: Display the link setting screen.

[0146] Output: Integration settings screen.

[0147] Action 2: Authenticate the user to their smart device or fitness app.

[0148] Input: The user enters their authentication information.

[0149] Action: Sends authentication information to the server.

[0150] Output: Authentication result (success / failure).

[0151] Action 3: If authentication is successful, the device will be configured to send fitness information (number of steps, exercise time, etc.) to the server.

[0152] Input: Authentication result successful.

[0153] Action: Configure your device to automatically collect and send fitness information to a server.

[0154] Output: Fitness information sending setup complete.

[0155] Action 4: The fitness app automatically sends data to the server.

[0156] Input: Fitness information.

[0157] What happens: The app periodically sends fitness information to the server.

[0158] Output: Fitness information received on the server side.

[0159] Step 5: Send and store data

[0160] Action 1: The fitness app or device periodically sends collected data to the server.

[0161] Input: Fitness information.

[0162] Processing: The app or device sends the data to the server.

[0163] Output: The data received on the server side.

[0164] Action 2: The server receives the data and stores it in a database.

[0165] Input: Received fitness information.

[0166] Processing: The server saves the data to the database.

[0167] Output: Save result to database (success / failure).

[0168] Act 3: The server cleans and standardizes the data, making it suitable for input into the generative AI model.

[0169] Input: Saved data.

[0170] Processing: Data cleaning and standardization is performed.

[0171] Output: Formatted data to be fed into a generative AI model.

[0172] Step 6: Generate the recipe

[0173] Action 1: The server inputs health information, preferences, and fitness information into the generative AI model.

[0174] Input: Health information, preferences, fitness information.

[0175] Processing: Inputting data into a generative AI model.

[0176] Output: Recipe generation prompt.

[0177] Action 2: The generative AI model analyzes the data and calculates the optimal cooking recipe for the user.

[0178] Input: Recipe generation prompt.

[0179] Processing: The generative AI model performs the analysis and calculations.

[0180] Output: Best cooking recipes.

[0181] Action 3: The AI ​​model returns the generated recipe to the server.

[0182] Enter: the perfect cooking recipe.

[0183] Process: Return the recipe to the server.

[0184] Output: The recipe saved on the server.

[0185] Step 7: Submit and view the recipe

[0186] Action 1: The server sends the generated recipe to the user terminal.

[0187] Input: A recipe stored on the server.

[0188] Processing: Send the recipe to the user's device.

[0189] Output: Recipe information received on the user device.

[0190] Action 2: The device displays the received recipe information.

[0191] Input: Received recipe information.

[0192] Processing: The device displays the recipe information.

[0193] Output: The displayed recipe screen.

[0194] Step 8: Cooking Instructions and Visual Support

[0195] Action 1: The user selects a recipe and the device visually displays ingredient quantities and cooking instructions.

[0196] Input: Selected recipe information.

[0197] Processing: The device will display the dosage and instructions.

[0198] Output: Visually displayed quantities and instructions.

[0199] Action 2: The device displays photos and videos for each step, helping the user to easily follow along.

[0200] Input: The instruction information to be displayed.

[0201] Action: The device displays the photo or video.

[0202] Output: Visual support information (photos and videos).

[0203] Action 3: The user follows the displayed instructions to cook the food.

[0204] Input: Visual supporting information.

[0205] Process: The user cooks the food.

[0206] Output: The finished dish.

[0207] This series of processes allows users to easily use optimal cooking recipes generated based on their individual health and fitness information.

[0208] (Application example 1)

[0209] 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."

[0210] In today's world, the number of health-conscious people is increasing, and they are looking for optimal recipes and menus based on their individual health status, preferences, and fitness data. However, providing optimal menus for individual users requires the collection and analysis of a large amount of data, which is time-consuming. For this reason, there is a need for a system that can efficiently and automatically generate individually optimized recipes and provide customized menus to users in brick-and-mortar stores as well.

[0211] 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.

[0212] In this invention, the server includes means for receiving and storing the input health information and preferences of the user, means for collecting and storing the user's fitness data, means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated cooking recipes to the user terminal, and means for storing menu information of physical stores in a database and providing individually customized cooking menus. This allows users to efficiently obtain optimal cooking recipes tailored to their health condition and preferences, and also enables them to enjoy customized healthy menus at physical stores.

[0213] "Health information" refers to personal data related to medical care and health management, such as the user's age, height, weight, and blood pressure.

[0214] "Preferences" is data indicating personal preferences of the user, such as preferred ingredients and dishes, allergy information, etc.

[0215] "Fitness data" refers to data related to fitness and exercise, such as the user's amount of exercise and calorie consumption.

[0216] A "generative AI model" is an artificial intelligence model used to calculate optimal cooking recipes from input data.

[0217] A "cooking recipe" is information that indicates the types and amounts of ingredients required to make a particular dish, as well as cooking procedures.

[0218] "User terminal" refers to a computing device used by a user, such as a smartphone or tablet.

[0219] "Physical store" refers to a food service establishment, such as a restaurant or cafe, that operates in a physical location.

[0220] A "database" is a system for systematically storing and managing multiple data.

[0221] "Menu information" is data that includes a list of dishes served at a physical store and detailed information about them.

[0222] "Visual support" is a function that provides users with easy-to-understand information such as portion sizes and cooking steps using photos and videos.

[0223] A "smartphone application" is software that runs on a smartphone.

[0224] "Customization" refers to the act of changing settings and content to suit each user's needs and preferences.

[0225] This invention is a system that collects a user's health information, preferences, and fitness data, generates optimal cooking recipes using a generative AI model, and provides them. The programs and processing contents of each part of the system are described in detail below.

[0226] 1. User Registration and Login

[0227] Users access the system through a smartphone application. New users register by entering required information such as name, email address, and password. Once registration is complete, users can log in using their email address and password.

[0228] 2. Enter your health information and preferences

[0229] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their preferences, such as favorite foods and allergies. This information is sent from the smartphone to the server and stored in a database.

[0230] 3. Fitness data integration

[0231] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server, allowing users to easily provide their latest fitness data.

[0232] 4. Recipe Generation

[0233] The server uses a generative AI model to generate optimal recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0234] 5. Recipe suggestions

[0235] The server sends the generated recipe to the user's smartphone, allowing the user to refer to the recipe. The user's smartphone displays the received recipe information, allowing the user to easily access it.

[0236] 6. Cooking instructions and visual aids

[0237] For recipes selected by users, the smartphone device provides visual support with photos and videos showing specific quantities and cooking steps, allowing users to cook efficiently while checking the specific cooking steps.

[0238] 7. Physical store collaboration

[0239] By using a system that stores menu information from physical stores in a database and provides individually customized food menus, users can enjoy customized menus even at physical stores.

[0240] Hardware and software used

[0241] Backend: Python, Django framework

[0242] Generative AI models: TensorFlow or PyTorch

[0243] Database: PostgreSQL

[0244] Front-end application: React Native

[0245] Fitness data integration API: Apple HealthKit, Google Fit API

[0246] Specific examples

[0247] For example, suppose a user is 32 years old, 175 cm tall, weighs 85 kg, and inputs that his favorite ingredients are chicken, broccoli, and brown rice. Furthermore, suppose fitness data from his smartwatch indicates that he walks 30 minutes and jogs 10 minutes daily. Based on this information, the generative AI model generates a recipe for "steamed chicken breast and broccoli with brown rice" and provides it to the user's device.

[0248] An example prompt is:

[0249] "The user is 32 years old, 175cm tall, and weighs 85kg. His favorite foods are chicken, broccoli, and brown rice. According to his weekly fitness data, he walks for 30 minutes and jogs for 10 minutes every day. Please generate the best cooking recipes based on this information."

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] A user downloads a smartphone application and enters basic information such as name, email address, and password. This information is sent from the application to a server and stored in a database. The input data is processed to generate output that is stored as the user's account information.

[0253] Step 2:

[0254] After logging in, the user enters their health information (age, height, weight, blood pressure, etc.) and preferences (favorite foods, allergies, etc.). This information is also sent from the application to the server and stored in the database. The input data is processed to generate output that is stored as the user's profile data.

[0255] Step 3:

[0256] A user connects their smartwatch and fitness app to the system, which periodically sends exercise data (e.g., number of steps, exercise time, calories burned) to the server. The input data is processed to generate output that is stored as the user's fitness data.

[0257] Step 4:

[0258] The server receives the user's health information, preferences, and fitness data, aggregates it, cleans and standardizes the data, and converts it into a format suitable for the generative AI model. The input data is processed to generate standardized data that serves as input to the generative AI model.

[0259] Step 5:

[0260] The server inputs the standardized data into a generative AI model to generate optimal cooking recipes. The generative AI model calculates recipes that take into account the user's calorie restrictions and nutritional balance. Based on the standardized data, calculations are performed to generate the output as an optimal cooking recipe.

[0261] Step 6:

[0262] The generated cooking recipe is sent from the server to the user's smartphone. The user's smartphone displays the received recipe information, allowing the user to easily access it. The input data is the recipe information received from the server, and is output in a format that can be viewed by the user.

[0263] Step 7:

[0264] The user terminal provides visual support for the selected recipe with photos and videos of the quantities and cooking steps. The input data is the detailed recipe information to be displayed, and the output is provided as visual support.

[0265] Step 8:

[0266] Menu information from physical restaurants is stored in a database, and individually customized food menus are provided. The server generates the optimal menu based on the user's profile information and restaurant menu information. The input data is the user's profile information and restaurant menu information, and calculations are performed to generate the output as a customized menu.

[0267] 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.

[0268] As a form for implementing this invention, we will specifically describe a system that not only collects and stores a user's health information, preferences, and fitness data, but also uses an emotion engine to recognize the user's emotions and optimize cooking recipes based on them.

[0269] System configuration

[0270] The system includes a means for inputting and saving a user's health information and preferences, a means for collecting and saving fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, a means for providing the generated cooking recipes to a user terminal, and a means for collecting and analyzing emotion data using an emotion engine that recognizes the user's emotions.

[0271] User Registration and Login

[0272] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0273] Enter your health information and preferences

[0274] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0275] Fitness data integration

[0276] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0277] Emotional data collection and analysis using an emotion engine

[0278] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice data, and collects emotion data in real time, which is then sent to a server along with health information, preferences, and fitness data.

[0279] Recipe Generation

[0280] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, fitness, and emotional data received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the optimal recipe taking into account the user's calorie restrictions, nutritional balance, and current emotional state.

[0281] Recipe Suggestions

[0282] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0283] Cooking instructions and visual aids

[0284] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0285] Specific examples

[0286] For example, the following is a specific example of a user named Yamada Hanako using the system. Yamada Hanako logs in and enters health information such as her age (30), height (160 cm), weight (60 kg), and blood pressure, as well as her favorite foods being "fish, vegetables, and sesame." Next, one week's worth of fitness data is automatically sent from her smartwatch to the server.

[0287] Furthermore, when Hanako Yamada interacts with the system using her device, the emotion engine analyzes her emotions from her facial expressions and tone of voice, and as a result, it recognizes her current emotional state as "stressed."

[0288] On the server side, a generative AI model is used based on Yamada Hanako's information and emotional data to generate a recipe for "Steamed Fish with Sesame Vegetables" that takes into account her health condition, preferences, and emotional state. This information is sent to Yamada Hanako's device, and she begins cooking while referring to the displayed recipe. The device displays recipe details, quantities, cooking steps, and visual support (photos and videos). This allows Yamada Hanako to easily create healthy, emotionally appropriate dishes with visual support.

[0289] In this way, this invention allows users to quickly and easily prepare healthy meals that are ideal for dieting. The introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing a more personalized meal plan.

[0290] The processing flow will be explained below.

[0291] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[0292] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[0293] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[0294] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[0295] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[0296] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[0297] Step 7: The device activates the emotion engine and recognizes emotions in real time from the user's facial expressions and voice data. The recognized emotion data is sent from the device to the server, which then stores the emotion data in a database.

[0298] Step 8: The server periodically extracts health information, preference and fitness data, and emotion data, either at the user's request or periodically. The server cleans and standardizes the data (removing duplicates and filling in missing data).

[0299] Step 9: The server uses the generative AI model to input the cleaned and standardized data and generate a cooking recipe that is optimal for the user. The generated recipe takes into account the user's calorie restrictions, nutritional balance, and emotional state. The server then stores the generated recipe in a database.

[0300] Step 10: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[0301] Step 11: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[0302] Specific examples

[0303] For example, the processing steps when a user named Suzuki Ichiro uses the system will be described as a specific example.

[0304] Steps 1-3:

[0305] Suzuki Ichiro accesses the system from a terminal and registers as a new user. He enters the required information, such as his name, email address, password, age, and gender, and logs in.

[0306] Steps 4-5:

[0307] After logging in, enter and save health information such as age (40), height (180cm), weight (90kg), and blood pressure. Next, set that your favorite foods are "fish, chicken, and spinach."

[0308] Step 6:

[0309] Ichiro Suzuki connects his smartwatch to the system and sends exercise data (for example, jogging five times a week) to the server.

[0310] Step 7:

[0311] While Ichiro Suzuki is using the device, the emotion engine analyzes his facial expressions and tone of voice and recognizes his emotion as "relaxed." The emotion data is sent to the server and stored.

[0312] Steps 8-9:

[0313] The server cleans and standardizes Ichiro Suzuki's health, preference, fitness, and emotional data, and uses a generative AI model to generate a recipe for "Steamed Fish and Spinach Salad." The generated recipe is then stored in a database.

[0314] Step 10:

[0315] Suzuki Ichiro selects "Recipe suggestion," and the generated recipe is displayed on the device.

[0316] Step 11:

[0317] Suzuki Ichiro selects a recipe, and the device displays the amounts of ingredients (such as "150g of fish, 100g of spinach") and cooking steps with photos and videos. Suzuki Ichiro follows the instructions to create the dish.

[0318] In this way, the introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing more personalized meal plans.

[0319] Example 2

[0320] 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."

[0321] In modern society, providing optimal nutritional information based on individual health status, preferences, and fitness data is a challenging task. Furthermore, providing meal plans that take emotional states into account contributes to user satisfaction and health maintenance, but current technologies have not adequately addressed this. Therefore, there is a need for a system that comprehensively analyzes a user's health information, preferences, fitness data, and emotional data, and provides personalized nutritional information based on the analysis.

[0322] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0323] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for generating optimal nutritional information using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated nutritional information to a user terminal, means for collecting and analyzing the user's emotional data in real time, and means for optimizing the nutritional information based on the emotional data, thereby enabling the provision of personalized nutritional information that comprehensively takes into account the user's health condition, preferences, fitness data, and even emotional state.

[0324] Below are definitions of important terms contained in the claims.

[0325] "Health information" is data relating to the individual health condition of the user, such as age, height, weight, and blood pressure.

[0326] "Preferences" is data relating to the types of ingredients and dishes that the user likes.

[0327] "Fitness data" refers to data relating to the user's exercise status, such as the amount of exercise, calories burned, and number of steps taken.

[0328] A "generative AI model" is an artificial intelligence model that generates optimal nutritional information and recipes based on collected data.

[0329] "Nutrition information" refers to information such as nutritional balance and calorie restrictions regarding meals provided to the user.

[0330] "Emotion data" refers to data relating to the user's emotional state analyzed from facial expressions and voice data.

[0331] "Collecting and analyzing in real time" means instantly obtaining emotional data via the user's device and analyzing it immediately.

[0332] "Personalized nutrition information" means nutrition information that is customized based on a user's individual health status, preferences, fitness data, and emotional state.

[0333] This invention is a system that collects a user's health information, preferences, fitness data, and emotional data, and generates optimal nutritional information based on this data using a generative AI model. Specific embodiments of this system are described below.

[0334] User Registration and Login

[0335] A user accesses the system using a device such as a smartphone or tablet and registers as a new user by entering the required information such as name, email address, and password. Once registration is complete, the user can log in using their email address and password. The registration information and login information are sent to the server and securely stored in a database.

[0336] Enter your health information and preferences

[0337] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0338] Fitness data integration

[0339] By connecting a smartwatch or fitness app to the system, users can automatically send past exercise data (number of steps, exercise time, calories burned, etc.) to the server, which then stores this data in a database and updates it daily.

[0340] Emotional data collection and analysis using an emotion engine

[0341] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice data to collect emotional data in real time. This emotional data is also sent from the device to a server and stored in a database along with health information, preferences, and fitness data.

[0342] Recipe Generation

[0343] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database, cleans and standardizes them, and inputs them into a generative AI model to generate optimal nutritional information. For example, if the user is feeling stressed, it will suggest recipes using ingredients that have a relaxing effect.

[0344] Recipe Suggestions

[0345] The generated nutritional information and recipes are sent from the server to the user's device, where the user can view the information. The device visually displays recipe details, quantities, cooking instructions, etc., making them easily accessible to the user.

[0346] Cooking instructions and visual aids

[0347] For recipes selected by the user, the device provides visual support with photos and videos showing cooking steps and quantities, allowing users to cook efficiently while checking the specific cooking steps.

[0348] Specific examples

[0349] For example, if a 30-year-old woman were to use this system, she would enter her health information, such as her age, height, weight, and blood pressure, and select fish, vegetables, and sesame as her favorite ingredients. Her smartwatch would then automatically send a week's worth of fitness data to the server. The emotion engine would then analyze her facial expressions and tone of voice in real time to determine whether she was feeling stressed. Based on this information, the server would use a generative AI model to generate a recipe for "steamed fish and vegetables with sesame dressing" and send it to the user's device. The user could then view the recipe on their device and cook with visual support from photos and videos.

[0350] In this way, the invention allows users to receive personalized nutritional information that takes into account their overall health, preferences, fitness data, and emotional state.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1:

[0353] A user accesses the system using a terminal. The terminal displays a new registration screen, and the user enters the required information, such as name, email address, and password. The entered information is sent to the server, which stores it in a database. In this case, the input information is the user's personal information, and a "notification of user registration completion" is generated as output. Specifically, the server adds the registration information to the database and sends a registration completion email.

[0354] Step 2:

[0355] The user accesses the login screen and enters the registered email address and password. The device sends this login information to the server, which then authenticates it against a database. If authentication is successful, the device moves the user to the main screen. The input is "login information" and the output is "permission to access the main screen." At this point, the server checks the user's information from the database and returns the authentication result to the device.

[0356] Step 3:

[0357] The user clicks the "Enter Health Information" button on the main screen to move to the health information entry screen. The user enters health information such as age, height, weight, and blood pressure, as well as preferences. The device sends this information to the server, which stores it in a database. The input is "health information and preferences," and the output is "database storage of health information and preferences." The server stores the received data appropriately and sends a notification to the device to confirm that the input has been saved.

[0358] Step 4:

[0359] The user goes to the system settings screen and configures the connection with the smartwatch and fitness app. The device sends the connection setting information to the server. The server uses the connection setting information to call the fitness data provider's API and continues to obtain daily fitness data. The obtained data is stored in a database. The input is "connection setting information" and the output is "collection and storage of fitness data." Specifically, the server automatically obtains daily exercise data through the API and adds it to the database.

[0360] Step 5:

[0361] The user interacts with the system using a device, and the emotion engine analyzes facial expressions and voice data in real time to generate emotion data. The emotion data generated by the device is sent to the server, which stores it in a database. The input is "emotion data" and the output is "storage of emotion data." Specifically, the device collects data from the camera and microphone, and the analysis engine identifies the emotional state.

[0362] Step 6:

[0363] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database. It cleans and standardizes the retrieved data and sends it to the generative AI model in an input format. The generative AI model generates optimal nutritional information. The input is "aggregated data" and the output is "generated nutritional information." Specifically, the server cleans the data, converts it into the required format, and inputs it into the AI ​​model.

[0364] Step 7:

[0365] The server sends the generated nutritional information and recipes to the user's device. The device receives this and displays it to the user. The user can check the details and receive visual support with photos and videos of the cooking steps and serving sizes for the selected recipe. The input is "nutritional information and recipe" and the output is "display of recipe with visual support." Specifically, the device displays the information received from the server on the screen and provides visual support.

[0366] (Application example 2)

[0367] 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."

[0368] Conventional recipe suggestion systems are based on the user's health information and preferences, but do not take into account the user's emotional state at any given time, making it difficult to meet the user's psychological needs. Furthermore, they do not adequately address the collection of fitness data, the analysis of emotional data, and the optimization of recipes based on that data, resulting in a lack of personalization for individual users. Furthermore, they lack integration with food delivery services to make it easier to realize the suggested recipes. There is a need to solve these issues and provide food delivery services that provide greater user satisfaction.

[0369] 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.

[0370] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for recognizing emotions from the user's facial expressions and voice data and collecting and analyzing the data, means for optimizing cooking recipes using a generative AI model based on the health information, preferences, fitness data, and emotional data, and means for ordering food delivery based on the generated cooking recipes. This makes it possible to propose optimal cooking recipes that comprehensively consider the user's health condition, preferences, and emotional state, and to deliver them quickly.

[0371] "Health information" is data related to the user's health condition, such as the user's age, height, weight, and blood pressure.

[0372] "Preferences" is information about ingredients and dishes that the user likes.

[0373] "Fitness data" is data that indicates the user's exercise status, and includes, for example, the number of steps and exercise time.

[0374] "Emotion data" is data that indicates the emotional state of the user as recognized from the user's facial expression and voice data.

[0375] An "emotion engine" is software or hardware for analyzing emotions from a user's facial expressions and voice data.

[0376] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected data.

[0377] "Optimizing a cooking recipe" means generating an optimal cooking recipe for a user based on the user's health information, preferences, fitness data, and emotional data.

[0378] A "user terminal" is a device through which a user inputs data and receives results, such as a smartphone or tablet.

[0379] "Data cleaning" refers to the process of properly organizing collected data and removing unnecessary or inaccurate data.

[0380] "Standardization" refers to the process of converting collected data into a suitable format for input into a generative AI model.

[0381] "Visual support" refers to providing users with visual information such as photos and videos of recipe quantities and cooking steps.

[0382] "Food delivery order" refers to placing an order with a food delivery service provider based on the generated cooking recipe.

[0383] This invention provides a system for collecting a user's health information, preferences, fitness data, and emotional data, and generating optimal cooking recipes based on the collected data. This system is implemented using the following hardware and software.

[0384] 1. Hardware and Software Configuration

[0385] User device: A device that a user uses for input and display, such as a smartphone or tablet.

[0386] Server: Infrastructure for storing and processing user data (e.g. AWS, GCP).

[0387] Smartwatch: A device that collects a user's fitness data.

[0388] Emotion engine software: Software for analyzing emotions from a user's facial and voice data (e.g., Affectiva SDK).

[0389] Generative AI model: An artificial intelligence model that generates optimal cooking recipes based on collected data (e.g., GPT-4).

[0390] 2. Data collection and storage

[0391] The user terminal provides an interface for inputting the user's health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes). This data is sent to and stored on the server.

[0392] The smartwatch collects the user's fitness data (number of steps, exercise time, etc.) and automatically sends it to the server through the link settings.

[0393] The emotion engine software is installed in the user's terminal, analyzes emotions in real time from the user's facial expressions and voice data, and transmits the emotion data to a server.

[0394] 3. Cleaning and standardizing data

[0395] The server cleans the collected data and standardizes it for input to the generative AI model, ensuring data integrity.

[0396] 4. Recipe Generation

[0397] The server uses a generative AI model to generate optimal cooking recipes based on health information, preferences, fitness data, and emotional data, taking into account individual health and current emotional states.

[0398] 5. Providing recipes and ordering food delivery

[0399] The generated recipe is sent to the user's terminal, where the user can view it.

[0400] When providing a recipe, users can order food delivery, which will quickly deliver food based on the generated recipe.

[0401] 6. Visual Support

[0402] The user device displays photos and videos to visually support the recipe quantities and cooking steps, allowing the user to cook while checking the specific cooking steps.

[0403] For example, a user uses this system to input health information (age, height, weight, blood pressure) and preferences (favorite foods). Fitness data (number of steps, exercise time) is then automatically sent from the smartwatch to the server. Furthermore, the emotion engine analyzes the user's facial expressions and voice to determine whether they are in a "stressed state." Based on this data, the generative AI model generates an optimal recipe, such as "steamed fish and vegetables with sesame dressing," and sends it to the user's device. The user can then order food delivery based on the recipe and enjoy cooking while referring to the provided visual support.

[0404] Example prompt sentence:

[0405] User's age: 35, height: 175cm, weight: 70kg, blood pressure: normal, favorite foods: chicken, tomato, basil, exercise data: average 5000 steps per week, emotion: relaxed

[0406] This makes it possible to quickly provide healthy and emotionally appropriate meals that meet the individual needs of the user.

[0407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0408] Step 1: User registration and login

[0409] Users access the system using a terminal, and if they are new users, they register by entering the required information such as their name, email address, and password. This input data is sent to the server and stored in the database. Registered users can log in using their email address and password.

[0410] Input: Name, Email Address, Password

[0411] Process: Send user registration information to the server and save it in the database

[0412] Output: Login session created, user profile created

[0413] Step 2: Enter your health information and preferences

[0414] After logging in, users enter their health information, such as age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences into the device. This data is also sent to the server and stored.

[0415] Input: Age, height, weight, blood pressure, favorite ingredients and dishes

[0416] Processing: Send the entered data to the server and save it in the database

[0417] Output: Stored health information and preference data

[0418] Step 3: Collecting Fitness Data

[0419] The user connects their smartwatch or fitness app to the system, which automatically collects exercise data (number of steps, exercise time, etc.) and sends it to the server.

[0420] Input: Exercise data from a smartwatch or fitness app

[0421] Processing: Collecting fitness data and automatically sending it to a server

[0422] Output: Saved fitness data

[0423] Step 4: Collecting emotion data

[0424] The emotion engine analyzes the user's facial expressions and voice data in real time to generate emotion data, which is also sent to the server and stored.

[0425] Input: User's facial expression and voice data

[0426] Processing: Emotion analysis by the emotion engine, generation of emotion data, and transmission to the server

[0427] Output: Saved emotion data

[0428] Step 5: Clean and standardize the data

[0429] The server cleans the collected health, preference, fitness and emotional data and standardizes it for input into the generative AI model, ensuring data consistency.

[0430] Input: Health information, preferences, fitness data, emotional data

[0431] Processing: Data cleaning and standardization

[0432] Output: Data formatted for input to a generative AI model

[0433] Step 6: Generate the recipe

[0434] The server then inputs the cleaned and standardized data into a generative AI model to generate optimal cooking recipes that take into account the user's health and emotional state.

[0435] Input: Cleaned and standardized data

[0436] Processing: Recipe generation using generative AI models

[0437] Output: Best cooking recipes

[0438] Step 7: Serve the recipe

[0439] The generated recipe is sent from the server to the user's device, where it can be viewed by the user. The user's device displays the recipe in a visually easy-to-understand format.

[0440] Input: Best Cooking Recipe

[0441] Process: Submit and View Recipe

[0442] Output: A cooking recipe displayed on the user's device

[0443] Step 8: Order food delivery

[0444] Users can order food delivery based on the provided recipes, and the server sends the order information to a delivery company and arranges for the cooked food to be delivered to the user.

[0445] Input: User's food delivery order information

[0446] Processing: Sending order information to delivery company

[0447] Output: Notification of delivery completion and food delivery

[0448] Step 9: Visual Support

[0449] The user device provides visual support for recipe quantities and cooking procedures using photos and videos, allowing users to cook while checking the specific cooking steps.

[0450] Input: User selected recipe

[0451] Processing: Displaying visual support for recipes (photos, videos)

[0452] Output: Detailed visually supported cooking instructions

[0453] 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.

[0454] 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.

[0455] 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.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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."

[0469] As a form for implementing this invention, a system that collects a user's health information, preferences, and fitness data and generates optimal cooking recipes using a generative AI model will be specifically described.

[0470] System configuration

[0471] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, and a means for providing the generated cooking recipes to a user terminal.

[0472] User Registration and Login

[0473] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0474] Enter your health information and preferences

[0475] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0476] Fitness data integration

[0477] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0478] Recipe Generation

[0479] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0480] Recipe Suggestions

[0481] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0482] Cooking instructions and visual aids

[0483] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0484] Specific examples

[0485] For example, the following is a specific example of a user named Tanaka Taro using the system. Tanaka Taro logs in and enters his health information, such as age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods, "chicken, broccoli, and brown rice." Next, one week's worth of fitness data is automatically sent from his smartwatch to the server.

[0486] On the server side, a generative AI model is used based on Tanaka Taro's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Tanaka Taro's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients (e.g., 200g chicken breast, 100g broccoli, 150g brown rice) as well as cooking instructions and photos for each step. This allows Tanaka Taro to easily create healthy meals with visual support.

[0487] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0488] The processing flow will be explained below.

[0489] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[0490] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[0491] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[0492] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[0493] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[0494] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[0495] Step 7: The server extracts health and fitness data periodically or upon user request. The server cleans (removes duplicates, fills in missing data) and standardizes the data.

[0496] Step 8: The server uses the generated AI model to input the cleaned and standardized data and generate the optimal cooking recipe for the user. The server stores the generated recipe in a database.

[0497] Step 9: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[0498] Step 10: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[0499] Example 1

[0500] 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."

[0501] In modern society, there are few systems that efficiently provide optimal cooking recipes based on a user's individual health condition and preferences. It is also difficult for users to effortlessly integrate health and fitness information and easily obtain specific cooking guidance based on data. Furthermore, the lack of visual support makes it difficult for even beginners to cook with confidence. As a result, users are not being adequately supported to lead a healthy lifestyle.

[0502] 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.

[0503] In this invention, the server includes a means for receiving and storing a user's health information and preferences, a means for collecting and storing the user's fitness information, and a means for the user to log in and input their health information and preferences. This allows the server to generate and provide optimal cooking recipes based on the user's health information and preferences. The server also includes a means for automatically collecting fitness data and cleaning and standardizing the data, enabling accurate recipe generation using a generative AI model. Furthermore, the server includes a means for providing photos or videos to visually support the recipe's portion sizes and cooking steps, allowing users to cook with peace of mind and easily create healthy meals.

[0504] "User's health information" refers to information related to an individual's health condition, such as age, height, weight, and blood pressure, entered by the user.

[0505] "Preferences" is information about ingredients and dishes that the user likes.

[0506] "Fitness information" refers to information that indicates a user's exercise data and activity trends, such as the number of steps and exercise time collected from smart devices and fitness apps.

[0507] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected user health, preference, and fitness information.

[0508] "Data cleaning" is the process of removing noise and inaccurate information from collected data and making it accurate and consistent.

[0509] "Data standardization" is the process of converting data collected in different formats or units into a unified format.

[0510] The "recipe generation means" is a part of the system that uses a generative AI model to calculate and generate the optimal cooking recipe for the user.

[0511] "Visual support" refers to a method of visually indicating the amounts of ingredients and cooking steps in a cooking recipe, using photographs or videos, to make it easier for users to understand how to cook.

[0512] A "user terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[0513] As an embodiment of the present invention, a system that collects a user's health information, preferences, and fitness information and generates optimal cooking recipes using a generative AI model is described below.

[0514] System configuration

[0515] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness information, a means for generating optimal cooking recipes using a generative AI model based on the collected health information, preferences, and fitness information, and a means for providing the generated cooking recipes to a user terminal.

[0516] User Registration and Login

[0517] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0518] Enter your health information and preferences

[0519] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0520] Fitness data integration

[0521] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0522] Recipe Generation

[0523] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness information received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0524] Recipe Suggestions

[0525] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0526] Cooking instructions and visual aids

[0527] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0528] Specific examples

[0529] For example, the following is a specific example of a user named Mr. A using the system. Mr. A logs in and enters health information such as his age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods being "chicken, broccoli, and brown rice." Next, one week's worth of fitness information is automatically sent from his smartwatch to the server.

[0530] Prompt Sentence Examples

[0531] "A 32-year-old, 175cm, 85kg male user likes chicken, broccoli, and brown rice. His fitness information includes his number of steps and exercise time for one week. Generate the best cooking recipes for him."

[0532] result

[0533] On the server side, a generative AI model is used based on Mr. A's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Mr. A's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients, such as 200g of chicken breast, 100g of broccoli, and 150g of brown rice, as well as cooking instructions and photos for each step. This allows Mr. A to easily create healthy dishes with visual support.

[0534] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0535] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0536] Program processing flow

[0537] Step 1: User Registration

[0538] Action 1: A user accesses the system's website or app using a smartphone or tablet.

[0539] Input: User accesses.

[0540] Action: The user clicks the "Sign Up" button and fills in the form with information such as name, email address, and password.

[0541] Output: The data entered into the registration form.

[0542] Action 2: The terminal sends the entered information to the server.

[0543] Input: Data entered into the registration form.

[0544] Processing: The device sends the information to the specified URL on the server.

[0545] Output: The data received on the server side.

[0546] Action 3: The server stores the received information in a database and generates and returns a user ID.

[0547] Input: The data received on the server side.

[0548] Processing: The server saves the data to the database and generates a user ID.

[0549] Output: User ID and a message confirming registration.

[0550] Step 2: Log in

[0551] Action 1: User enters email address and password and submits the login form.

[0552] Input: User's email address and password.

[0553] Process: The device sends the login information to the server.

[0554] Output: The data received on the server side.

[0555] Action 2: The server checks its database to see if the entered email address and password match.

[0556] Input: The data received on the server side.

[0557] Action: Check the database to see if the email address and password match.

[0558] Output: Authentication result (success / failure).

[0559] Action 3: If there is a match, the server creates a session and returns an authentication token to the device.

[0560] Input: Authentication result successful.

[0561] Process: The server creates a session and issues an authentication token.

[0562] Output: An authentication token.

[0563] Step 3: Enter your health information and preferences

[0564] Action 1: After logging in, the user accesses a form to enter health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes).

[0565] Input: The user accesses the form.

[0566] Action: Display the form.

[0567] Output: Form screen.

[0568] Action 2: The user enters information into the form and presses the submit button.

[0569] Input: Health information and preferences entered into the form.

[0570] Processing: The terminal sends the entered information to the server.

[0571] Output: The data received on the server side.

[0572] Action 3: The server saves and updates the information in the database.

[0573] Input: The data received on the server side.

[0574] Processing: The server saves the data to the database and updates existing data as needed.

[0575] Output: Save result to database (success / failure).

[0576] Step 4: Connect your fitness data

[0577] Action 1: The user accesses the integration settings screen within the system.

[0578] Input: The user accesses the integration settings screen.

[0579] Processing: Display the link setting screen.

[0580] Output: Integration settings screen.

[0581] Action 2: Authenticate the user to their smart device or fitness app.

[0582] Input: The user enters their authentication information.

[0583] Action: Sends authentication information to the server.

[0584] Output: Authentication result (success / failure).

[0585] Action 3: If authentication is successful, the device will be configured to send fitness information (number of steps, exercise time, etc.) to the server.

[0586] Input: Authentication result successful.

[0587] Action: Configure your device to automatically collect and send fitness information to a server.

[0588] Output: Fitness information sending setup complete.

[0589] Action 4: The fitness app automatically sends data to the server.

[0590] Input: Fitness information.

[0591] What happens: The app periodically sends fitness information to the server.

[0592] Output: Fitness information received on the server side.

[0593] Step 5: Send and store data

[0594] Action 1: The fitness app or device periodically sends collected data to the server.

[0595] Input: Fitness information.

[0596] Processing: The app or device sends the data to the server.

[0597] Output: The data received on the server side.

[0598] Action 2: The server receives the data and stores it in a database.

[0599] Input: Received fitness information.

[0600] Processing: The server saves the data to the database.

[0601] Output: Save result to database (success / failure).

[0602] Act 3: The server cleans and standardizes the data, making it suitable for input into the generative AI model.

[0603] Input: Saved data.

[0604] Processing: Data cleaning and standardization is performed.

[0605] Output: Formatted data to be fed into a generative AI model.

[0606] Step 6: Generate the recipe

[0607] Action 1: The server inputs health information, preferences, and fitness information into the generative AI model.

[0608] Input: Health information, preferences, fitness information.

[0609] Processing: Inputting data into a generative AI model.

[0610] Output: Recipe generation prompt.

[0611] Action 2: The generative AI model analyzes the data and calculates the optimal cooking recipe for the user.

[0612] Input: Recipe generation prompt.

[0613] Processing: The generative AI model performs the analysis and calculations.

[0614] Output: Best cooking recipes.

[0615] Action 3: The AI ​​model returns the generated recipe to the server.

[0616] Enter: the perfect cooking recipe.

[0617] Process: Return the recipe to the server.

[0618] Output: The recipe saved on the server.

[0619] Step 7: Submit and view the recipe

[0620] Action 1: The server sends the generated recipe to the user terminal.

[0621] Input: A recipe stored on the server.

[0622] Processing: Send the recipe to the user's device.

[0623] Output: Recipe information received on the user device.

[0624] Action 2: The device displays the received recipe information.

[0625] Input: Received recipe information.

[0626] Processing: The device displays the recipe information.

[0627] Output: The displayed recipe screen.

[0628] Step 8: Cooking Instructions and Visual Support

[0629] Action 1: The user selects a recipe and the device visually displays ingredient quantities and cooking instructions.

[0630] Input: Selected recipe information.

[0631] Processing: The device will display the dosage and instructions.

[0632] Output: Visually displayed quantities and instructions.

[0633] Action 2: The device displays photos and videos for each step, helping the user to easily follow along.

[0634] Input: The instruction information to be displayed.

[0635] Action: The device displays the photo or video.

[0636] Output: Visual support information (photos and videos).

[0637] Action 3: The user follows the displayed instructions to cook the food.

[0638] Input: Visual supporting information.

[0639] Process: The user cooks the food.

[0640] Output: The finished dish.

[0641] This series of processes allows users to easily use optimal cooking recipes generated based on their individual health and fitness information.

[0642] (Application example 1)

[0643] 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."

[0644] In today's world, the number of health-conscious people is increasing, and they are looking for optimal recipes and menus based on their individual health status, preferences, and fitness data. However, providing optimal menus for individual users requires the collection and analysis of a large amount of data, which is time-consuming. For this reason, there is a need for a system that can efficiently and automatically generate individually optimized recipes and provide customized menus to users in brick-and-mortar stores as well.

[0645] 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.

[0646] In this invention, the server includes means for receiving and storing the input health information and preferences of the user, means for collecting and storing the user's fitness data, means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated cooking recipes to the user terminal, and means for storing menu information of physical stores in a database and providing individually customized cooking menus. This allows users to efficiently obtain optimal cooking recipes tailored to their health condition and preferences, and also enables them to enjoy customized healthy menus at physical stores.

[0647] "Health information" refers to personal data related to medical care and health management, such as the user's age, height, weight, and blood pressure.

[0648] "Preferences" is data indicating personal preferences of the user, such as preferred ingredients and dishes, allergy information, etc.

[0649] "Fitness data" refers to data related to fitness and exercise, such as the user's amount of exercise and calorie consumption.

[0650] A "generative AI model" is an artificial intelligence model used to calculate optimal cooking recipes from input data.

[0651] A "cooking recipe" is information that indicates the types and amounts of ingredients required to make a particular dish, as well as cooking procedures.

[0652] "User terminal" refers to a computing device used by a user, such as a smartphone or tablet.

[0653] "Physical store" refers to a food service establishment, such as a restaurant or cafe, that operates in a physical location.

[0654] A "database" is a system for systematically storing and managing multiple data.

[0655] "Menu information" is data that includes a list of dishes served at a physical store and detailed information about them.

[0656] "Visual support" is a function that provides users with easy-to-understand information such as portion sizes and cooking steps using photos and videos.

[0657] A "smartphone application" is software that runs on a smartphone.

[0658] "Customization" refers to the act of changing settings and content to suit each user's needs and preferences.

[0659] This invention is a system that collects a user's health information, preferences, and fitness data, generates optimal cooking recipes using a generative AI model, and provides them. The programs and processing contents of each part of the system are described in detail below.

[0660] 1. User Registration and Login

[0661] Users access the system through a smartphone application. New users register by entering required information such as name, email address, and password. Once registration is complete, users can log in using their email address and password.

[0662] 2. Enter your health information and preferences

[0663] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their preferences, such as favorite foods and allergies. This information is sent from the smartphone to the server and stored in a database.

[0664] 3. Fitness data integration

[0665] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server, allowing users to easily provide their latest fitness data.

[0666] 4. Recipe Generation

[0667] The server uses a generative AI model to generate optimal recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0668] 5. Recipe suggestions

[0669] The server sends the generated recipe to the user's smartphone, allowing the user to refer to the recipe. The user's smartphone displays the received recipe information, allowing the user to easily access it.

[0670] 6. Cooking instructions and visual aids

[0671] For recipes selected by users, the smartphone device provides visual support with photos and videos showing specific quantities and cooking steps, allowing users to cook efficiently while checking the specific cooking steps.

[0672] 7. Physical store collaboration

[0673] By using a system that stores menu information from physical stores in a database and provides individually customized food menus, users can enjoy customized menus even at physical stores.

[0674] Hardware and software used

[0675] Backend: Python, Django framework

[0676] Generative AI models: TensorFlow or PyTorch

[0677] Database: PostgreSQL

[0678] Front-end application: React Native

[0679] Fitness data integration API: Apple HealthKit, Google Fit API

[0680] Specific examples

[0681] For example, suppose a user is 32 years old, 175 cm tall, weighs 85 kg, and inputs that his favorite ingredients are chicken, broccoli, and brown rice. Furthermore, suppose fitness data from his smartwatch indicates that he walks 30 minutes and jogs 10 minutes daily. Based on this information, the generative AI model generates a recipe for "steamed chicken breast and broccoli with brown rice" and provides it to the user's device.

[0682] An example prompt is:

[0683] "The user is 32 years old, 175cm tall, and weighs 85kg. His favorite foods are chicken, broccoli, and brown rice. According to his weekly fitness data, he walks for 30 minutes and jogs for 10 minutes every day. Please generate the best cooking recipes based on this information."

[0684] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0685] Step 1:

[0686] A user downloads a smartphone application and enters basic information such as name, email address, and password. This information is sent from the application to a server and stored in a database. The input data is processed to generate output that is stored as the user's account information.

[0687] Step 2:

[0688] After logging in, the user enters their health information (age, height, weight, blood pressure, etc.) and preferences (favorite foods, allergies, etc.). This information is also sent from the application to the server and stored in the database. The input data is processed to generate output that is stored as the user's profile data.

[0689] Step 3:

[0690] A user connects their smartwatch and fitness app to the system, which periodically sends exercise data (e.g., number of steps, exercise time, calories burned) to the server. The input data is processed to generate output that is stored as the user's fitness data.

[0691] Step 4:

[0692] The server receives the user's health information, preferences, and fitness data, aggregates it, cleans and standardizes the data, and converts it into a format suitable for the generative AI model. The input data is processed to generate standardized data that serves as input to the generative AI model.

[0693] Step 5:

[0694] The server inputs the standardized data into a generative AI model to generate optimal cooking recipes. The generative AI model calculates recipes that take into account the user's calorie restrictions and nutritional balance. Based on the standardized data, calculations are performed to generate the output as an optimal cooking recipe.

[0695] Step 6:

[0696] The generated cooking recipe is sent from the server to the user's smartphone. The user's smartphone displays the received recipe information, allowing the user to easily access it. The input data is the recipe information received from the server, and is output in a format that can be viewed by the user.

[0697] Step 7:

[0698] The user terminal provides visual support for the selected recipe with photos and videos of the quantities and cooking steps. The input data is the detailed recipe information to be displayed, and the output is provided as visual support.

[0699] Step 8:

[0700] Menu information from physical restaurants is stored in a database, and individually customized food menus are provided. The server generates the optimal menu based on the user's profile information and restaurant menu information. The input data is the user's profile information and restaurant menu information, and calculations are performed to generate the output as a customized menu.

[0701] 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.

[0702] As a form for implementing this invention, we will specifically describe a system that not only collects and stores a user's health information, preferences, and fitness data, but also uses an emotion engine to recognize the user's emotions and optimize cooking recipes based on them.

[0703] System configuration

[0704] The system includes a means for inputting and saving a user's health information and preferences, a means for collecting and saving fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, a means for providing the generated cooking recipes to a user terminal, and a means for collecting and analyzing emotion data using an emotion engine that recognizes the user's emotions.

[0705] User Registration and Login

[0706] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0707] Enter your health information and preferences

[0708] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0709] Fitness data integration

[0710] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0711] Emotional data collection and analysis using an emotion engine

[0712] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice data, and collects emotion data in real time, which is then sent to a server along with health information, preferences, and fitness data.

[0713] Recipe Generation

[0714] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, fitness, and emotional data received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the optimal recipe taking into account the user's calorie restrictions, nutritional balance, and current emotional state.

[0715] Recipe Suggestions

[0716] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0717] Cooking instructions and visual aids

[0718] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0719] Specific examples

[0720] For example, the following is a specific example of a user named Yamada Hanako using the system. Yamada Hanako logs in and enters health information such as her age (30), height (160 cm), weight (60 kg), and blood pressure, as well as her favorite foods being "fish, vegetables, and sesame." Next, one week's worth of fitness data is automatically sent from her smartwatch to the server.

[0721] Furthermore, when Hanako Yamada interacts with the system using her device, the emotion engine analyzes her emotions from her facial expressions and tone of voice, and as a result, it recognizes her current emotional state as "stressed."

[0722] On the server side, a generative AI model is used based on Yamada Hanako's information and emotional data to generate a recipe for "Steamed Fish with Sesame Vegetables" that takes into account her health condition, preferences, and emotional state. This information is sent to Yamada Hanako's device, and she begins cooking while referring to the displayed recipe. The device displays recipe details, quantities, cooking steps, and visual support (photos and videos). This allows Yamada Hanako to easily create healthy, emotionally appropriate dishes with visual support.

[0723] In this way, this invention allows users to quickly and easily prepare healthy meals that are ideal for dieting. The introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing a more personalized meal plan.

[0724] The processing flow will be explained below.

[0725] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[0726] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[0727] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[0728] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[0729] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[0730] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[0731] Step 7: The device activates the emotion engine and recognizes emotions in real time from the user's facial expressions and voice data. The recognized emotion data is sent from the device to the server, which then stores the emotion data in a database.

[0732] Step 8: The server periodically extracts health information, preference and fitness data, and emotion data, either at the user's request or periodically. The server cleans and standardizes the data (removing duplicates and filling in missing data).

[0733] Step 9: The server uses the generative AI model to input the cleaned and standardized data and generate a cooking recipe that is optimal for the user. The generated recipe takes into account the user's calorie restrictions, nutritional balance, and emotional state. The server then stores the generated recipe in a database.

[0734] Step 10: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[0735] Step 11: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[0736] Specific examples

[0737] For example, the processing steps when a user named Suzuki Ichiro uses the system will be described as a specific example.

[0738] Steps 1-3:

[0739] Suzuki Ichiro accesses the system from a terminal and registers as a new user. He enters the required information, such as his name, email address, password, age, and gender, and logs in.

[0740] Steps 4-5:

[0741] After logging in, enter and save health information such as age (40), height (180cm), weight (90kg), and blood pressure. Next, set that your favorite foods are "fish, chicken, and spinach."

[0742] Step 6:

[0743] Ichiro Suzuki connects his smartwatch to the system and sends exercise data (for example, jogging five times a week) to the server.

[0744] Step 7:

[0745] While Ichiro Suzuki is using the device, the emotion engine analyzes his facial expressions and tone of voice and recognizes his emotion as "relaxed." The emotion data is sent to the server and stored.

[0746] Steps 8-9:

[0747] The server cleans and standardizes Ichiro Suzuki's health, preference, fitness, and emotional data, and uses a generative AI model to generate a recipe for "Steamed Fish and Spinach Salad." The generated recipe is then stored in a database.

[0748] Step 10:

[0749] Suzuki Ichiro selects "Recipe suggestion," and the generated recipe is displayed on the device.

[0750] Step 11:

[0751] Suzuki Ichiro selects a recipe, and the device displays the amounts of ingredients (such as "150g of fish, 100g of spinach") and cooking steps with photos and videos. Suzuki Ichiro follows the instructions to create the dish.

[0752] In this way, the introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing more personalized meal plans.

[0753] Example 2

[0754] 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."

[0755] In modern society, providing optimal nutritional information based on individual health status, preferences, and fitness data is a challenging task. Furthermore, providing meal plans that take emotional states into account contributes to user satisfaction and health maintenance, but current technologies have not adequately addressed this. Therefore, there is a need for a system that comprehensively analyzes a user's health information, preferences, fitness data, and emotional data, and provides personalized nutritional information based on the analysis.

[0756] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0757] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for generating optimal nutritional information using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated nutritional information to a user terminal, means for collecting and analyzing the user's emotional data in real time, and means for optimizing the nutritional information based on the emotional data, thereby enabling the provision of personalized nutritional information that comprehensively takes into account the user's health condition, preferences, fitness data, and even emotional state.

[0758] Below are definitions of important terms contained in the claims.

[0759] "Health information" is data relating to the individual health condition of the user, such as age, height, weight, and blood pressure.

[0760] "Preferences" is data relating to the types of ingredients and dishes that the user likes.

[0761] "Fitness data" refers to data relating to the user's exercise status, such as the amount of exercise, calories burned, and number of steps taken.

[0762] A "generative AI model" is an artificial intelligence model that generates optimal nutritional information and recipes based on collected data.

[0763] "Nutrition information" refers to information such as nutritional balance and calorie restrictions regarding meals provided to the user.

[0764] "Emotion data" refers to data relating to the user's emotional state analyzed from facial expressions and voice data.

[0765] "Collecting and analyzing in real time" means instantly obtaining emotional data via the user's device and analyzing it immediately.

[0766] "Personalized nutrition information" means nutrition information that is customized based on a user's individual health status, preferences, fitness data, and emotional state.

[0767] This invention is a system that collects a user's health information, preferences, fitness data, and emotional data, and generates optimal nutritional information based on this data using a generative AI model. Specific embodiments of this system are described below.

[0768] User Registration and Login

[0769] A user accesses the system using a device such as a smartphone or tablet and registers as a new user by entering the required information such as name, email address, and password. Once registration is complete, the user can log in using their email address and password. The registration information and login information are sent to the server and securely stored in a database.

[0770] Enter your health information and preferences

[0771] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0772] Fitness data integration

[0773] By connecting a smartwatch or fitness app to the system, users can automatically send past exercise data (number of steps, exercise time, calories burned, etc.) to the server, which then stores this data in a database and updates it daily.

[0774] Emotional data collection and analysis using an emotion engine

[0775] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice data to collect emotional data in real time. This emotional data is also sent from the device to a server and stored in a database along with health information, preferences, and fitness data.

[0776] Recipe Generation

[0777] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database, cleans and standardizes them, and inputs them into a generative AI model to generate optimal nutritional information. For example, if the user is feeling stressed, it will suggest recipes using ingredients that have a relaxing effect.

[0778] Recipe Suggestions

[0779] The generated nutritional information and recipes are sent from the server to the user's device, where the user can view the information. The device visually displays recipe details, quantities, cooking instructions, etc., making them easily accessible to the user.

[0780] Cooking instructions and visual aids

[0781] For recipes selected by the user, the device provides visual support with photos and videos showing cooking steps and quantities, allowing users to cook efficiently while checking the specific cooking steps.

[0782] Specific examples

[0783] For example, if a 30-year-old woman were to use this system, she would enter her health information, such as her age, height, weight, and blood pressure, and select fish, vegetables, and sesame as her favorite ingredients. Her smartwatch would then automatically send a week's worth of fitness data to the server. The emotion engine would then analyze her facial expressions and tone of voice in real time to determine whether she was feeling stressed. Based on this information, the server would use a generative AI model to generate a recipe for "steamed fish and vegetables with sesame dressing" and send it to the user's device. The user could then view the recipe on their device and cook with visual support from photos and videos.

[0784] In this way, the invention allows users to receive personalized nutritional information that takes into account their overall health, preferences, fitness data, and emotional state.

[0785] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0786] Step 1:

[0787] A user accesses the system using a terminal. The terminal displays a new registration screen, and the user enters the required information, such as name, email address, and password. The entered information is sent to the server, which stores it in a database. In this case, the input information is the user's personal information, and a "notification of user registration completion" is generated as output. Specifically, the server adds the registration information to the database and sends a registration completion email.

[0788] Step 2:

[0789] The user accesses the login screen and enters the registered email address and password. The device sends this login information to the server, which then authenticates it against a database. If authentication is successful, the device moves the user to the main screen. The input is "login information" and the output is "permission to access the main screen." At this point, the server checks the user's information from the database and returns the authentication result to the device.

[0790] Step 3:

[0791] The user clicks the "Enter Health Information" button on the main screen to move to the health information entry screen. The user enters health information such as age, height, weight, and blood pressure, as well as preferences. The device sends this information to the server, which stores it in a database. The input is "health information and preferences," and the output is "database storage of health information and preferences." The server stores the received data appropriately and sends a notification to the device to confirm that the input has been saved.

[0792] Step 4:

[0793] The user goes to the system settings screen and configures the connection with the smartwatch and fitness app. The device sends the connection setting information to the server. The server uses the connection setting information to call the fitness data provider's API and continues to obtain daily fitness data. The obtained data is stored in a database. The input is "connection setting information" and the output is "collection and storage of fitness data." Specifically, the server automatically obtains daily exercise data through the API and adds it to the database.

[0794] Step 5:

[0795] The user interacts with the system using a device, and the emotion engine analyzes facial expressions and voice data in real time to generate emotion data. The emotion data generated by the device is sent to the server, which stores it in a database. The input is "emotion data" and the output is "storage of emotion data." Specifically, the device collects data from the camera and microphone, and the analysis engine identifies the emotional state.

[0796] Step 6:

[0797] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database. It cleans and standardizes the retrieved data and sends it to the generative AI model in an input format. The generative AI model generates optimal nutritional information. The input is "aggregated data" and the output is "generated nutritional information." Specifically, the server cleans the data, converts it into the required format, and inputs it into the AI ​​model.

[0798] Step 7:

[0799] The server sends the generated nutritional information and recipes to the user's device. The device receives this and displays it to the user. The user can check the details and receive visual support with photos and videos of the cooking steps and serving sizes for the selected recipe. The input is "nutritional information and recipe" and the output is "display of recipe with visual support." Specifically, the device displays the information received from the server on the screen and provides visual support.

[0800] (Application example 2)

[0801] 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."

[0802] Conventional recipe suggestion systems are based on the user's health information and preferences, but do not take into account the user's emotional state at any given time, making it difficult to meet the user's psychological needs. Furthermore, they do not adequately address the collection of fitness data, the analysis of emotional data, and the optimization of recipes based on that data, resulting in a lack of personalization for individual users. Furthermore, they lack integration with food delivery services to make it easier to realize the suggested recipes. There is a need to solve these issues and provide food delivery services that provide greater user satisfaction.

[0803] 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.

[0804] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for recognizing emotions from the user's facial expressions and voice data and collecting and analyzing the data, means for optimizing cooking recipes using a generative AI model based on the health information, preferences, fitness data, and emotional data, and means for ordering food delivery based on the generated cooking recipes. This makes it possible to propose optimal cooking recipes that comprehensively consider the user's health condition, preferences, and emotional state, and to deliver them quickly.

[0805] "Health information" is data related to the user's health condition, such as the user's age, height, weight, and blood pressure.

[0806] "Preferences" is information about ingredients and dishes that the user likes.

[0807] "Fitness data" is data that indicates the user's exercise status, and includes, for example, the number of steps and exercise time.

[0808] "Emotion data" is data that indicates the emotional state of the user as recognized from the user's facial expression and voice data.

[0809] An "emotion engine" is software or hardware for analyzing emotions from a user's facial expressions and voice data.

[0810] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected data.

[0811] "Optimizing a cooking recipe" means generating an optimal cooking recipe for a user based on the user's health information, preferences, fitness data, and emotional data.

[0812] A "user terminal" is a device through which a user inputs data and receives results, such as a smartphone or tablet.

[0813] "Data cleaning" refers to the process of properly organizing collected data and removing unnecessary or inaccurate data.

[0814] "Standardization" refers to the process of converting collected data into a suitable format for input into a generative AI model.

[0815] "Visual support" refers to providing users with visual information such as photos and videos of recipe quantities and cooking steps.

[0816] "Food delivery order" refers to placing an order with a food delivery service provider based on the generated cooking recipe.

[0817] This invention provides a system for collecting a user's health information, preferences, fitness data, and emotional data, and generating optimal cooking recipes based on the collected data. This system is implemented using the following hardware and software.

[0818] 1. Hardware and Software Configuration

[0819] User device: A device that a user uses for input and display, such as a smartphone or tablet.

[0820] Server: Infrastructure for storing and processing user data (e.g. AWS, GCP).

[0821] Smartwatch: A device that collects a user's fitness data.

[0822] Emotion engine software: Software for analyzing emotions from a user's facial and voice data (e.g., Affectiva SDK).

[0823] Generative AI model: An artificial intelligence model that generates optimal cooking recipes based on collected data (e.g., GPT-4).

[0824] 2. Data collection and storage

[0825] The user terminal provides an interface for inputting the user's health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes). This data is sent to and stored on the server.

[0826] The smartwatch collects the user's fitness data (number of steps, exercise time, etc.) and automatically sends it to the server through the link settings.

[0827] The emotion engine software is installed in the user's terminal, analyzes emotions in real time from the user's facial expressions and voice data, and transmits the emotion data to a server.

[0828] 3. Cleaning and standardizing data

[0829] The server cleans the collected data and standardizes it for input to the generative AI model, ensuring data integrity.

[0830] 4. Recipe Generation

[0831] The server uses a generative AI model to generate optimal cooking recipes based on health information, preferences, fitness data, and emotional data, taking into account individual health and current emotional states.

[0832] 5. Providing recipes and ordering food delivery

[0833] The generated recipe is sent to the user's terminal, where the user can view it.

[0834] When providing a recipe, users can order food delivery, which will quickly deliver food based on the generated recipe.

[0835] 6. Visual Support

[0836] The user device displays photos and videos to visually support the recipe quantities and cooking steps, allowing the user to cook while checking the specific cooking steps.

[0837] For example, a user uses this system to input health information (age, height, weight, blood pressure) and preferences (favorite foods). Fitness data (number of steps, exercise time) is then automatically sent from the smartwatch to the server. Furthermore, the emotion engine analyzes the user's facial expressions and voice to determine whether they are in a "stressed state." Based on this data, the generative AI model generates an optimal recipe, such as "steamed fish and vegetables with sesame dressing," and sends it to the user's device. The user can then order food delivery based on the recipe and enjoy cooking while referring to the provided visual support.

[0838] Example prompt sentence:

[0839] User's age: 35, height: 175cm, weight: 70kg, blood pressure: normal, favorite foods: chicken, tomato, basil, exercise data: average 5000 steps per week, emotion: relaxed

[0840] This makes it possible to quickly provide healthy and emotionally appropriate meals that meet the individual needs of the user.

[0841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0842] Step 1: User registration and login

[0843] Users access the system using a terminal, and if they are new users, they register by entering the required information such as their name, email address, and password. This input data is sent to the server and stored in the database. Registered users can log in using their email address and password.

[0844] Input: Name, Email Address, Password

[0845] Process: Send user registration information to the server and save it in the database

[0846] Output: Login session created, user profile created

[0847] Step 2: Enter your health information and preferences

[0848] After logging in, users enter their health information, such as age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences into the device. This data is also sent to the server and stored.

[0849] Input: Age, height, weight, blood pressure, favorite ingredients and dishes

[0850] Processing: Send the entered data to the server and save it in the database

[0851] Output: Stored health information and preference data

[0852] Step 3: Collecting Fitness Data

[0853] The user connects their smartwatch or fitness app to the system, which automatically collects exercise data (number of steps, exercise time, etc.) and sends it to the server.

[0854] Input: Exercise data from a smartwatch or fitness app

[0855] Processing: Collecting fitness data and automatically sending it to a server

[0856] Output: Saved fitness data

[0857] Step 4: Collecting emotion data

[0858] The emotion engine analyzes the user's facial expressions and voice data in real time to generate emotion data, which is also sent to the server and stored.

[0859] Input: User's facial expression and voice data

[0860] Processing: Emotion analysis by the emotion engine, generation of emotion data, and transmission to the server

[0861] Output: Saved emotion data

[0862] Step 5: Clean and standardize the data

[0863] The server cleans the collected health, preference, fitness and emotional data and standardizes it for input into the generative AI model, ensuring data consistency.

[0864] Input: Health information, preferences, fitness data, emotional data

[0865] Processing: Data cleaning and standardization

[0866] Output: Data formatted for input to a generative AI model

[0867] Step 6: Generate the recipe

[0868] The server then inputs the cleaned and standardized data into a generative AI model to generate optimal cooking recipes that take into account the user's health and emotional state.

[0869] Input: Cleaned and standardized data

[0870] Processing: Recipe generation using generative AI models

[0871] Output: Best cooking recipes

[0872] Step 7: Serve the recipe

[0873] The generated recipe is sent from the server to the user's device, where it can be viewed by the user. The user's device displays the recipe in a visually easy-to-understand format.

[0874] Input: Best Cooking Recipe

[0875] Process: Submit and View Recipe

[0876] Output: A cooking recipe displayed on the user's device

[0877] Step 8: Order food delivery

[0878] Users can order food delivery based on the provided recipes, and the server sends the order information to a delivery company and arranges for the cooked food to be delivered to the user.

[0879] Input: User's food delivery order information

[0880] Processing: Sending order information to delivery company

[0881] Output: Notification of delivery completion and food delivery

[0882] Step 9: Visual Support

[0883] The user device provides visual support for recipe quantities and cooking procedures using photos and videos, allowing users to cook while checking the specific cooking steps.

[0884] Input: User selected recipe

[0885] Processing: Displaying visual support for recipes (photos, videos)

[0886] Output: Detailed visually supported cooking instructions

[0887] 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.

[0888] 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.

[0889] 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.

[0890] [Third embodiment]

[0891] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0892] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0893] 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).

[0894] 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.

[0895] 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.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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."

[0903] As a form for implementing this invention, a system that collects a user's health information, preferences, and fitness data and generates optimal cooking recipes using a generative AI model will be specifically described.

[0904] System configuration

[0905] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, and a means for providing the generated cooking recipes to a user terminal.

[0906] User Registration and Login

[0907] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0908] Enter your health information and preferences

[0909] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0910] Fitness data integration

[0911] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0912] Recipe Generation

[0913] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0914] Recipe Suggestions

[0915] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0916] Cooking instructions and visual aids

[0917] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0918] Specific examples

[0919] For example, the following is a specific example of a user named Tanaka Taro using the system. Tanaka Taro logs in and enters his health information, such as age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods, "chicken, broccoli, and brown rice." Next, one week's worth of fitness data is automatically sent from his smartwatch to the server.

[0920] On the server side, a generative AI model is used based on Tanaka Taro's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Tanaka Taro's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients (e.g., 200g chicken breast, 100g broccoli, 150g brown rice) as well as cooking instructions and photos for each step. This allows Tanaka Taro to easily create healthy meals with visual support.

[0921] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0922] The processing flow will be explained below.

[0923] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[0924] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[0925] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[0926] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[0927] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[0928] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[0929] Step 7: The server extracts health and fitness data periodically or upon user request. The server cleans (removes duplicates, fills in missing data) and standardizes the data.

[0930] Step 8: The server uses the generated AI model to input the cleaned and standardized data and generate the optimal cooking recipe for the user. The server stores the generated recipe in a database.

[0931] Step 9: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[0932] Step 10: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[0933] Example 1

[0934] 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."

[0935] In modern society, there are few systems that efficiently provide optimal cooking recipes based on a user's individual health condition and preferences. It is also difficult for users to effortlessly integrate health and fitness information and easily obtain specific cooking guidance based on data. Furthermore, the lack of visual support makes it difficult for even beginners to cook with confidence. As a result, users are not being adequately supported to lead a healthy lifestyle.

[0936] 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.

[0937] In this invention, the server includes a means for receiving and storing a user's health information and preferences, a means for collecting and storing the user's fitness information, and a means for the user to log in and input their health information and preferences. This allows the server to generate and provide optimal cooking recipes based on the user's health information and preferences. The server also includes a means for automatically collecting fitness data and cleaning and standardizing the data, enabling accurate recipe generation using a generative AI model. Furthermore, the server includes a means for providing photos or videos to visually support the recipe's portion sizes and cooking steps, allowing users to cook with peace of mind and easily create healthy meals.

[0938] "User's health information" refers to information related to an individual's health condition, such as age, height, weight, and blood pressure, entered by the user.

[0939] "Preferences" is information about ingredients and dishes that the user likes.

[0940] "Fitness information" refers to information that indicates a user's exercise data and activity trends, such as the number of steps and exercise time collected from smart devices and fitness apps.

[0941] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected user health, preference, and fitness information.

[0942] "Data cleaning" is the process of removing noise and inaccurate information from collected data and making it accurate and consistent.

[0943] "Data standardization" is the process of converting data collected in different formats or units into a unified format.

[0944] The "recipe generation means" is a part of the system that uses a generative AI model to calculate and generate the optimal cooking recipe for the user.

[0945] "Visual support" refers to a method of visually indicating the amounts of ingredients and cooking steps in a cooking recipe, using photographs or videos, to make it easier for users to understand how to cook.

[0946] A "user terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[0947] As an embodiment of the present invention, a system that collects a user's health information, preferences, and fitness information and generates optimal cooking recipes using a generative AI model is described below.

[0948] System configuration

[0949] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness information, a means for generating optimal cooking recipes using a generative AI model based on the collected health information, preferences, and fitness information, and a means for providing the generated cooking recipes to a user terminal.

[0950] User Registration and Login

[0951] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[0952] Enter your health information and preferences

[0953] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[0954] Fitness data integration

[0955] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[0956] Recipe Generation

[0957] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness information received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[0958] Recipe Suggestions

[0959] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[0960] Cooking instructions and visual aids

[0961] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[0962] Specific examples

[0963] For example, the following is a specific example of a user named Mr. A using the system. Mr. A logs in and enters health information such as his age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods being "chicken, broccoli, and brown rice." Next, one week's worth of fitness information is automatically sent from his smartwatch to the server.

[0964] Prompt Sentence Examples

[0965] "A 32-year-old, 175cm, 85kg male user likes chicken, broccoli, and brown rice. His fitness information includes his number of steps and exercise time for one week. Generate the best cooking recipes for him."

[0966] result

[0967] On the server side, a generative AI model is used based on Mr. A's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Mr. A's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients, such as 200g of chicken breast, 100g of broccoli, and 150g of brown rice, as well as cooking instructions and photos for each step. This allows Mr. A to easily create healthy dishes with visual support.

[0968] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[0969] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0970] Program processing flow

[0971] Step 1: User Registration

[0972] Action 1: A user accesses the system's website or app using a smartphone or tablet.

[0973] Input: User accesses.

[0974] Action: The user clicks the "Sign Up" button and fills in the form with information such as name, email address, and password.

[0975] Output: The data entered into the registration form.

[0976] Action 2: The terminal sends the entered information to the server.

[0977] Input: Data entered into the registration form.

[0978] Processing: The device sends the information to the specified URL on the server.

[0979] Output: The data received on the server side.

[0980] Action 3: The server stores the received information in a database and generates and returns a user ID.

[0981] Input: The data received on the server side.

[0982] Processing: The server saves the data to the database and generates a user ID.

[0983] Output: User ID and a message confirming registration.

[0984] Step 2: Log in

[0985] Action 1: User enters email address and password and submits the login form.

[0986] Input: User's email address and password.

[0987] Process: The device sends the login information to the server.

[0988] Output: The data received on the server side.

[0989] Action 2: The server checks its database to see if the entered email address and password match.

[0990] Input: The data received on the server side.

[0991] Action: Check the database to see if the email address and password match.

[0992] Output: Authentication result (success / failure).

[0993] Action 3: If there is a match, the server creates a session and returns an authentication token to the device.

[0994] Input: Authentication result successful.

[0995] Process: The server creates a session and issues an authentication token.

[0996] Output: An authentication token.

[0997] Step 3: Enter your health information and preferences

[0998] Action 1: After logging in, the user accesses a form to enter health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes).

[0999] Input: The user accesses the form.

[1000] Action: Display the form.

[1001] Output: Form screen.

[1002] Action 2: The user enters information into the form and presses the submit button.

[1003] Input: Health information and preferences entered into the form.

[1004] Processing: The terminal sends the entered information to the server.

[1005] Output: The data received on the server side.

[1006] Action 3: The server saves and updates the information in the database.

[1007] Input: The data received on the server side.

[1008] Processing: The server saves the data to the database and updates existing data as needed.

[1009] Output: Save result to database (success / failure).

[1010] Step 4: Connect your fitness data

[1011] Action 1: The user accesses the integration settings screen within the system.

[1012] Input: The user accesses the integration settings screen.

[1013] Processing: Display the link setting screen.

[1014] Output: Integration settings screen.

[1015] Action 2: Authenticate the user to their smart device or fitness app.

[1016] Input: The user enters their authentication information.

[1017] Action: Sends authentication information to the server.

[1018] Output: Authentication result (success / failure).

[1019] Action 3: If authentication is successful, the device will be configured to send fitness information (number of steps, exercise time, etc.) to the server.

[1020] Input: Authentication result successful.

[1021] Action: Configure your device to automatically collect and send fitness information to a server.

[1022] Output: Fitness information sending setup complete.

[1023] Action 4: The fitness app automatically sends data to the server.

[1024] Input: Fitness information.

[1025] What happens: The app periodically sends fitness information to the server.

[1026] Output: Fitness information received on the server side.

[1027] Step 5: Send and store data

[1028] Action 1: The fitness app or device periodically sends collected data to the server.

[1029] Input: Fitness information.

[1030] Processing: The app or device sends the data to the server.

[1031] Output: The data received on the server side.

[1032] Action 2: The server receives the data and stores it in a database.

[1033] Input: Received fitness information.

[1034] Processing: The server saves the data to the database.

[1035] Output: Save result to database (success / failure).

[1036] Act 3: The server cleans and standardizes the data, making it suitable for input into the generative AI model.

[1037] Input: Saved data.

[1038] Processing: Data cleaning and standardization is performed.

[1039] Output: Formatted data to be fed into a generative AI model.

[1040] Step 6: Generate the recipe

[1041] Action 1: The server inputs health information, preferences, and fitness information into the generative AI model.

[1042] Input: Health information, preferences, fitness information.

[1043] Processing: Inputting data into a generative AI model.

[1044] Output: Recipe generation prompt.

[1045] Action 2: The generative AI model analyzes the data and calculates the optimal cooking recipe for the user.

[1046] Input: Recipe generation prompt.

[1047] Processing: The generative AI model performs the analysis and calculations.

[1048] Output: Best cooking recipes.

[1049] Action 3: The AI ​​model returns the generated recipe to the server.

[1050] Enter: the perfect cooking recipe.

[1051] Process: Return the recipe to the server.

[1052] Output: The recipe saved on the server.

[1053] Step 7: Submit and view the recipe

[1054] Action 1: The server sends the generated recipe to the user terminal.

[1055] Input: A recipe stored on the server.

[1056] Processing: Send the recipe to the user's device.

[1057] Output: Recipe information received on the user device.

[1058] Action 2: The device displays the received recipe information.

[1059] Input: Received recipe information.

[1060] Processing: The device displays the recipe information.

[1061] Output: The displayed recipe screen.

[1062] Step 8: Cooking Instructions and Visual Support

[1063] Action 1: The user selects a recipe and the device visually displays ingredient quantities and cooking instructions.

[1064] Input: Selected recipe information.

[1065] Processing: The device will display the dosage and instructions.

[1066] Output: Visually displayed quantities and instructions.

[1067] Action 2: The device displays photos and videos for each step, helping the user to easily follow along.

[1068] Input: The instruction information to be displayed.

[1069] Action: The device displays the photo or video.

[1070] Output: Visual support information (photos and videos).

[1071] Action 3: The user follows the displayed instructions to cook the food.

[1072] Input: Visual supporting information.

[1073] Process: The user cooks the food.

[1074] Output: The finished dish.

[1075] This series of processes allows users to easily use optimal cooking recipes generated based on their individual health and fitness information.

[1076] (Application example 1)

[1077] 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."

[1078] In today's world, the number of health-conscious people is increasing, and they are looking for optimal recipes and menus based on their individual health status, preferences, and fitness data. However, providing optimal menus for individual users requires the collection and analysis of a large amount of data, which is time-consuming. For this reason, there is a need for a system that can efficiently and automatically generate individually optimized recipes and provide customized menus to users in brick-and-mortar stores as well.

[1079] 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.

[1080] In this invention, the server includes means for receiving and storing the input health information and preferences of the user, means for collecting and storing the user's fitness data, means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated cooking recipes to the user terminal, and means for storing menu information of physical stores in a database and providing individually customized cooking menus. This allows users to efficiently obtain optimal cooking recipes tailored to their health condition and preferences, and also enables them to enjoy customized healthy menus at physical stores.

[1081] "Health information" refers to personal data related to medical care and health management, such as the user's age, height, weight, and blood pressure.

[1082] "Preferences" is data indicating personal preferences of the user, such as preferred ingredients and dishes, allergy information, etc.

[1083] "Fitness data" refers to data related to fitness and exercise, such as the user's amount of exercise and calorie consumption.

[1084] A "generative AI model" is an artificial intelligence model used to calculate optimal cooking recipes from input data.

[1085] A "cooking recipe" is information that indicates the types and amounts of ingredients required to make a particular dish, as well as cooking procedures.

[1086] "User terminal" refers to a computing device used by a user, such as a smartphone or tablet.

[1087] "Physical store" refers to a food service establishment, such as a restaurant or cafe, that operates in a physical location.

[1088] A "database" is a system for systematically storing and managing multiple data.

[1089] "Menu information" is data that includes a list of dishes served at a physical store and detailed information about them.

[1090] "Visual support" is a function that provides users with easy-to-understand information such as portion sizes and cooking steps using photos and videos.

[1091] A "smartphone application" is software that runs on a smartphone.

[1092] "Customization" refers to the act of changing settings and content to suit each user's needs and preferences.

[1093] This invention is a system that collects a user's health information, preferences, and fitness data, generates optimal cooking recipes using a generative AI model, and provides them. The programs and processing contents of each part of the system are described in detail below.

[1094] 1. User Registration and Login

[1095] Users access the system through a smartphone application. New users register by entering required information such as name, email address, and password. Once registration is complete, users can log in using their email address and password.

[1096] 2. Enter your health information and preferences

[1097] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their preferences, such as favorite foods and allergies. This information is sent from the smartphone to the server and stored in a database.

[1098] 3. Fitness data integration

[1099] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server, allowing users to easily provide their latest fitness data.

[1100] 4. Recipe Generation

[1101] The server uses a generative AI model to generate optimal recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[1102] 5. Recipe suggestions

[1103] The server sends the generated recipe to the user's smartphone, allowing the user to refer to the recipe. The user's smartphone displays the received recipe information, allowing the user to easily access it.

[1104] 6. Cooking instructions and visual aids

[1105] For recipes selected by users, the smartphone device provides visual support with photos and videos showing specific quantities and cooking steps, allowing users to cook efficiently while checking the specific cooking steps.

[1106] 7. Physical store collaboration

[1107] By using a system that stores menu information from physical stores in a database and provides individually customized food menus, users can enjoy customized menus even at physical stores.

[1108] Hardware and software used

[1109] Backend: Python, Django framework

[1110] Generative AI models: TensorFlow or PyTorch

[1111] Database: PostgreSQL

[1112] Front-end application: React Native

[1113] Fitness data integration API: Apple HealthKit, Google Fit API

[1114] Specific examples

[1115] For example, suppose a user is 32 years old, 175 cm tall, weighs 85 kg, and inputs that his favorite ingredients are chicken, broccoli, and brown rice. Furthermore, suppose fitness data from his smartwatch indicates that he walks 30 minutes and jogs 10 minutes daily. Based on this information, the generative AI model generates a recipe for "steamed chicken breast and broccoli with brown rice" and provides it to the user's device.

[1116] An example prompt is:

[1117] "The user is 32 years old, 175cm tall, and weighs 85kg. His favorite foods are chicken, broccoli, and brown rice. According to his weekly fitness data, he walks for 30 minutes and jogs for 10 minutes every day. Please generate the best cooking recipes based on this information."

[1118] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1119] Step 1:

[1120] A user downloads a smartphone application and enters basic information such as name, email address, and password. This information is sent from the application to a server and stored in a database. The input data is processed to generate output that is stored as the user's account information.

[1121] Step 2:

[1122] After logging in, the user enters their health information (age, height, weight, blood pressure, etc.) and preferences (favorite foods, allergies, etc.). This information is also sent from the application to the server and stored in the database. The input data is processed to generate output that is stored as the user's profile data.

[1123] Step 3:

[1124] A user connects their smartwatch and fitness app to the system, which periodically sends exercise data (e.g., number of steps, exercise time, calories burned) to the server. The input data is processed to generate output that is stored as the user's fitness data.

[1125] Step 4:

[1126] The server receives the user's health information, preferences, and fitness data, aggregates it, cleans and standardizes the data, and converts it into a format suitable for the generative AI model. The input data is processed to generate standardized data that serves as input to the generative AI model.

[1127] Step 5:

[1128] The server inputs the standardized data into a generative AI model to generate optimal cooking recipes. The generative AI model calculates recipes that take into account the user's calorie restrictions and nutritional balance. Based on the standardized data, calculations are performed to generate the output as an optimal cooking recipe.

[1129] Step 6:

[1130] The generated cooking recipe is sent from the server to the user's smartphone. The user's smartphone displays the received recipe information, allowing the user to easily access it. The input data is the recipe information received from the server, and is output in a format that can be viewed by the user.

[1131] Step 7:

[1132] The user terminal provides visual support for the selected recipe with photos and videos of the quantities and cooking steps. The input data is the detailed recipe information to be displayed, and the output is provided as visual support.

[1133] Step 8:

[1134] Menu information from physical restaurants is stored in a database, and individually customized food menus are provided. The server generates the optimal menu based on the user's profile information and restaurant menu information. The input data is the user's profile information and restaurant menu information, and calculations are performed to generate the output as a customized menu.

[1135] 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.

[1136] As a form for implementing this invention, we will specifically describe a system that not only collects and stores a user's health information, preferences, and fitness data, but also uses an emotion engine to recognize the user's emotions and optimize cooking recipes based on them.

[1137] System configuration

[1138] The system includes a means for inputting and saving a user's health information and preferences, a means for collecting and saving fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, a means for providing the generated cooking recipes to a user terminal, and a means for collecting and analyzing emotion data using an emotion engine that recognizes the user's emotions.

[1139] User Registration and Login

[1140] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[1141] Enter your health information and preferences

[1142] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1143] Fitness data integration

[1144] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[1145] Emotional data collection and analysis using an emotion engine

[1146] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice data, and collects emotion data in real time, which is then sent to a server along with health information, preferences, and fitness data.

[1147] Recipe Generation

[1148] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, fitness, and emotional data received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the optimal recipe taking into account the user's calorie restrictions, nutritional balance, and current emotional state.

[1149] Recipe Suggestions

[1150] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[1151] Cooking instructions and visual aids

[1152] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[1153] Specific examples

[1154] For example, the following is a specific example of a user named Yamada Hanako using the system. Yamada Hanako logs in and enters health information such as her age (30), height (160 cm), weight (60 kg), and blood pressure, as well as her favorite foods being "fish, vegetables, and sesame." Next, one week's worth of fitness data is automatically sent from her smartwatch to the server.

[1155] Furthermore, when Hanako Yamada interacts with the system using her device, the emotion engine analyzes her emotions from her facial expressions and tone of voice, and as a result, it recognizes her current emotional state as "stressed."

[1156] On the server side, a generative AI model is used based on Yamada Hanako's information and emotional data to generate a recipe for "Steamed Fish with Sesame Vegetables" that takes into account her health condition, preferences, and emotional state. This information is sent to Yamada Hanako's device, and she begins cooking while referring to the displayed recipe. The device displays recipe details, quantities, cooking steps, and visual support (photos and videos). This allows Yamada Hanako to easily create healthy, emotionally appropriate dishes with visual support.

[1157] In this way, this invention allows users to quickly and easily prepare healthy meals that are ideal for dieting. The introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing a more personalized meal plan.

[1158] The processing flow will be explained below.

[1159] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[1160] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[1161] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[1162] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[1163] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[1164] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[1165] Step 7: The device activates the emotion engine and recognizes emotions in real time from the user's facial expressions and voice data. The recognized emotion data is sent from the device to the server, which then stores the emotion data in a database.

[1166] Step 8: The server periodically extracts health information, preference and fitness data, and emotion data, either at the user's request or periodically. The server cleans and standardizes the data (removing duplicates and filling in missing data).

[1167] Step 9: The server uses the generative AI model to input the cleaned and standardized data and generate a cooking recipe that is optimal for the user. The generated recipe takes into account the user's calorie restrictions, nutritional balance, and emotional state. The server then stores the generated recipe in a database.

[1168] Step 10: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[1169] Step 11: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[1170] Specific examples

[1171] For example, the processing steps when a user named Suzuki Ichiro uses the system will be described as a specific example.

[1172] Steps 1-3:

[1173] Suzuki Ichiro accesses the system from a terminal and registers as a new user. He enters the required information, such as his name, email address, password, age, and gender, and logs in.

[1174] Steps 4-5:

[1175] After logging in, enter and save health information such as age (40), height (180cm), weight (90kg), and blood pressure. Next, set that your favorite foods are "fish, chicken, and spinach."

[1176] Step 6:

[1177] Ichiro Suzuki connects his smartwatch to the system and sends exercise data (for example, jogging five times a week) to the server.

[1178] Step 7:

[1179] While Ichiro Suzuki is using the device, the emotion engine analyzes his facial expressions and tone of voice and recognizes his emotion as "relaxed." The emotion data is sent to the server and stored.

[1180] Steps 8-9:

[1181] The server cleans and standardizes Ichiro Suzuki's health, preference, fitness, and emotional data, and uses a generative AI model to generate a recipe for "Steamed Fish and Spinach Salad." The generated recipe is then stored in a database.

[1182] Step 10:

[1183] Suzuki Ichiro selects "Recipe suggestion," and the generated recipe is displayed on the device.

[1184] Step 11:

[1185] Suzuki Ichiro selects a recipe, and the device displays the amounts of ingredients (such as "150g of fish, 100g of spinach") and cooking steps with photos and videos. Suzuki Ichiro follows the instructions to create the dish.

[1186] In this way, the introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing more personalized meal plans.

[1187] Example 2

[1188] 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."

[1189] In modern society, providing optimal nutritional information based on individual health status, preferences, and fitness data is a challenging task. Furthermore, providing meal plans that take emotional states into account contributes to user satisfaction and health maintenance, but current technologies have not adequately addressed this. Therefore, there is a need for a system that comprehensively analyzes a user's health information, preferences, fitness data, and emotional data, and provides personalized nutritional information based on the analysis.

[1190] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1191] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for generating optimal nutritional information using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated nutritional information to a user terminal, means for collecting and analyzing the user's emotional data in real time, and means for optimizing the nutritional information based on the emotional data, thereby enabling the provision of personalized nutritional information that comprehensively takes into account the user's health condition, preferences, fitness data, and even emotional state.

[1192] Below are definitions of important terms contained in the claims.

[1193] "Health information" is data relating to the individual health condition of the user, such as age, height, weight, and blood pressure.

[1194] "Preferences" is data relating to the types of ingredients and dishes that the user likes.

[1195] "Fitness data" refers to data relating to the user's exercise status, such as the amount of exercise, calories burned, and number of steps taken.

[1196] A "generative AI model" is an artificial intelligence model that generates optimal nutritional information and recipes based on collected data.

[1197] "Nutrition information" refers to information such as nutritional balance and calorie restrictions regarding meals provided to the user.

[1198] "Emotion data" refers to data relating to the user's emotional state analyzed from facial expressions and voice data.

[1199] "Collecting and analyzing in real time" means instantly obtaining emotional data via the user's device and analyzing it immediately.

[1200] "Personalized nutrition information" means nutrition information that is customized based on a user's individual health status, preferences, fitness data, and emotional state.

[1201] This invention is a system that collects a user's health information, preferences, fitness data, and emotional data, and generates optimal nutritional information based on this data using a generative AI model. Specific embodiments of this system are described below.

[1202] User Registration and Login

[1203] A user accesses the system using a device such as a smartphone or tablet and registers as a new user by entering the required information such as name, email address, and password. Once registration is complete, the user can log in using their email address and password. The registration information and login information are sent to the server and securely stored in a database.

[1204] Enter your health information and preferences

[1205] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1206] Fitness data integration

[1207] By connecting a smartwatch or fitness app to the system, users can automatically send past exercise data (number of steps, exercise time, calories burned, etc.) to the server, which then stores this data in a database and updates it daily.

[1208] Emotional data collection and analysis using an emotion engine

[1209] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice data to collect emotional data in real time. This emotional data is also sent from the device to a server and stored in a database along with health information, preferences, and fitness data.

[1210] Recipe Generation

[1211] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database, cleans and standardizes them, and inputs them into a generative AI model to generate optimal nutritional information. For example, if the user is feeling stressed, it will suggest recipes using ingredients that have a relaxing effect.

[1212] Recipe Suggestions

[1213] The generated nutritional information and recipes are sent from the server to the user's device, where the user can view the information. The device visually displays recipe details, quantities, cooking instructions, etc., making them easily accessible to the user.

[1214] Cooking instructions and visual aids

[1215] For recipes selected by the user, the device provides visual support with photos and videos showing cooking steps and quantities, allowing users to cook efficiently while checking the specific cooking steps.

[1216] Specific examples

[1217] For example, if a 30-year-old woman were to use this system, she would enter her health information, such as her age, height, weight, and blood pressure, and select fish, vegetables, and sesame as her favorite ingredients. Her smartwatch would then automatically send a week's worth of fitness data to the server. The emotion engine would then analyze her facial expressions and tone of voice in real time to determine whether she was feeling stressed. Based on this information, the server would use a generative AI model to generate a recipe for "steamed fish and vegetables with sesame dressing" and send it to the user's device. The user could then view the recipe on their device and cook with visual support from photos and videos.

[1218] In this way, the invention allows users to receive personalized nutritional information that takes into account their overall health, preferences, fitness data, and emotional state.

[1219] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1220] Step 1:

[1221] A user accesses the system using a terminal. The terminal displays a new registration screen, and the user enters the required information, such as name, email address, and password. The entered information is sent to the server, which stores it in a database. In this case, the input information is the user's personal information, and a "notification of user registration completion" is generated as output. Specifically, the server adds the registration information to the database and sends a registration completion email.

[1222] Step 2:

[1223] The user accesses the login screen and enters the registered email address and password. The device sends this login information to the server, which then authenticates it against a database. If authentication is successful, the device moves the user to the main screen. The input is "login information" and the output is "permission to access the main screen." At this point, the server checks the user's information from the database and returns the authentication result to the device.

[1224] Step 3:

[1225] The user clicks the "Enter Health Information" button on the main screen to move to the health information entry screen. The user enters health information such as age, height, weight, and blood pressure, as well as preferences. The device sends this information to the server, which stores it in a database. The input is "health information and preferences," and the output is "database storage of health information and preferences." The server stores the received data appropriately and sends a notification to the device to confirm that the input has been saved.

[1226] Step 4:

[1227] The user goes to the system settings screen and configures the connection with the smartwatch and fitness app. The device sends the connection setting information to the server. The server uses the connection setting information to call the fitness data provider's API and continues to obtain daily fitness data. The obtained data is stored in a database. The input is "connection setting information" and the output is "collection and storage of fitness data." Specifically, the server automatically obtains daily exercise data through the API and adds it to the database.

[1228] Step 5:

[1229] The user interacts with the system using a device, and the emotion engine analyzes facial expressions and voice data in real time to generate emotion data. The emotion data generated by the device is sent to the server, which stores it in a database. The input is "emotion data" and the output is "storage of emotion data." Specifically, the device collects data from the camera and microphone, and the analysis engine identifies the emotional state.

[1230] Step 6:

[1231] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database. It cleans and standardizes the retrieved data and sends it to the generative AI model in an input format. The generative AI model generates optimal nutritional information. The input is "aggregated data" and the output is "generated nutritional information." Specifically, the server cleans the data, converts it into the required format, and inputs it into the AI ​​model.

[1232] Step 7:

[1233] The server sends the generated nutritional information and recipes to the user's device. The device receives this and displays it to the user. The user can check the details and receive visual support with photos and videos of the cooking steps and serving sizes for the selected recipe. The input is "nutritional information and recipe" and the output is "display of recipe with visual support." Specifically, the device displays the information received from the server on the screen and provides visual support.

[1234] (Application example 2)

[1235] 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."

[1236] Conventional recipe suggestion systems are based on the user's health information and preferences, but do not take into account the user's emotional state at any given time, making it difficult to meet the user's psychological needs. Furthermore, they do not adequately address the collection of fitness data, the analysis of emotional data, and the optimization of recipes based on that data, resulting in a lack of personalization for individual users. Furthermore, they lack integration with food delivery services to make it easier to realize the suggested recipes. There is a need to solve these issues and provide food delivery services that provide greater user satisfaction.

[1237] 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.

[1238] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for recognizing emotions from the user's facial expressions and voice data and collecting and analyzing the data, means for optimizing cooking recipes using a generative AI model based on the health information, preferences, fitness data, and emotional data, and means for ordering food delivery based on the generated cooking recipes. This makes it possible to propose optimal cooking recipes that comprehensively consider the user's health condition, preferences, and emotional state, and to deliver them quickly.

[1239] "Health information" is data related to the user's health condition, such as the user's age, height, weight, and blood pressure.

[1240] "Preferences" is information about ingredients and dishes that the user likes.

[1241] "Fitness data" is data that indicates the user's exercise status, and includes, for example, the number of steps and exercise time.

[1242] "Emotion data" is data that indicates the emotional state of the user as recognized from the user's facial expression and voice data.

[1243] An "emotion engine" is software or hardware for analyzing emotions from a user's facial expressions and voice data.

[1244] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected data.

[1245] "Optimizing a cooking recipe" means generating an optimal cooking recipe for a user based on the user's health information, preferences, fitness data, and emotional data.

[1246] A "user terminal" is a device through which a user inputs data and receives results, such as a smartphone or tablet.

[1247] "Data cleaning" refers to the process of properly organizing collected data and removing unnecessary or inaccurate data.

[1248] "Standardization" refers to the process of converting collected data into a suitable format for input into a generative AI model.

[1249] "Visual support" refers to providing users with visual information such as photos and videos of recipe quantities and cooking steps.

[1250] "Food delivery order" refers to placing an order with a food delivery service provider based on the generated cooking recipe.

[1251] This invention provides a system for collecting a user's health information, preferences, fitness data, and emotional data, and generating optimal cooking recipes based on the collected data. This system is implemented using the following hardware and software.

[1252] 1. Hardware and Software Configuration

[1253] User device: A device that a user uses for input and display, such as a smartphone or tablet.

[1254] Server: Infrastructure for storing and processing user data (e.g. AWS, GCP).

[1255] Smartwatch: A device that collects a user's fitness data.

[1256] Emotion engine software: Software for analyzing emotions from a user's facial and voice data (e.g., Affectiva SDK).

[1257] Generative AI model: An artificial intelligence model that generates optimal cooking recipes based on collected data (e.g., GPT-4).

[1258] 2. Data collection and storage

[1259] The user terminal provides an interface for inputting the user's health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes). This data is sent to and stored on the server.

[1260] The smartwatch collects the user's fitness data (number of steps, exercise time, etc.) and automatically sends it to the server through the link settings.

[1261] The emotion engine software is installed in the user's terminal, analyzes emotions in real time from the user's facial expressions and voice data, and transmits the emotion data to a server.

[1262] 3. Cleaning and standardizing data

[1263] The server cleans the collected data and standardizes it for input to the generative AI model, ensuring data integrity.

[1264] 4. Recipe Generation

[1265] The server uses a generative AI model to generate optimal cooking recipes based on health information, preferences, fitness data, and emotional data, taking into account individual health and current emotional states.

[1266] 5. Providing recipes and ordering food delivery

[1267] The generated recipe is sent to the user's terminal, where the user can view it.

[1268] When providing a recipe, users can order food delivery, which will quickly deliver food based on the generated recipe.

[1269] 6. Visual Support

[1270] The user device displays photos and videos to visually support the recipe quantities and cooking steps, allowing the user to cook while checking the specific cooking steps.

[1271] For example, a user uses this system to input health information (age, height, weight, blood pressure) and preferences (favorite foods). Fitness data (number of steps, exercise time) is then automatically sent from the smartwatch to the server. Furthermore, the emotion engine analyzes the user's facial expressions and voice to determine whether they are in a "stressed state." Based on this data, the generative AI model generates an optimal recipe, such as "steamed fish and vegetables with sesame dressing," and sends it to the user's device. The user can then order food delivery based on the recipe and enjoy cooking while referring to the provided visual support.

[1272] Example prompt sentence:

[1273] User's age: 35, height: 175cm, weight: 70kg, blood pressure: normal, favorite foods: chicken, tomato, basil, exercise data: average 5000 steps per week, emotion: relaxed

[1274] This makes it possible to quickly provide healthy and emotionally appropriate meals that meet the individual needs of the user.

[1275] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1276] Step 1: User registration and login

[1277] Users access the system using a terminal, and if they are new users, they register by entering the required information such as their name, email address, and password. This input data is sent to the server and stored in the database. Registered users can log in using their email address and password.

[1278] Input: Name, Email Address, Password

[1279] Process: Send user registration information to the server and save it in the database

[1280] Output: Login session created, user profile created

[1281] Step 2: Enter your health information and preferences

[1282] After logging in, users enter their health information, such as age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences into the device. This data is also sent to the server and stored.

[1283] Input: Age, height, weight, blood pressure, favorite ingredients and dishes

[1284] Processing: Send the entered data to the server and save it in the database

[1285] Output: Stored health information and preference data

[1286] Step 3: Collecting Fitness Data

[1287] The user connects their smartwatch or fitness app to the system, which automatically collects exercise data (number of steps, exercise time, etc.) and sends it to the server.

[1288] Input: Exercise data from a smartwatch or fitness app

[1289] Processing: Collecting fitness data and automatically sending it to a server

[1290] Output: Saved fitness data

[1291] Step 4: Collecting emotion data

[1292] The emotion engine analyzes the user's facial expressions and voice data in real time to generate emotion data, which is also sent to the server and stored.

[1293] Input: User's facial expression and voice data

[1294] Processing: Emotion analysis by the emotion engine, generation of emotion data, and transmission to the server

[1295] Output: Saved emotion data

[1296] Step 5: Clean and standardize the data

[1297] The server cleans the collected health, preference, fitness and emotional data and standardizes it for input into the generative AI model, ensuring data consistency.

[1298] Input: Health information, preferences, fitness data, emotional data

[1299] Processing: Data cleaning and standardization

[1300] Output: Data formatted for input to a generative AI model

[1301] Step 6: Generate the recipe

[1302] The server then inputs the cleaned and standardized data into a generative AI model to generate optimal cooking recipes that take into account the user's health and emotional state.

[1303] Input: Cleaned and standardized data

[1304] Processing: Recipe generation using generative AI models

[1305] Output: Best cooking recipes

[1306] Step 7: Serve the recipe

[1307] The generated recipe is sent from the server to the user's device, where it can be viewed by the user. The user's device displays the recipe in a visually easy-to-understand format.

[1308] Input: Best Cooking Recipe

[1309] Process: Submit and View Recipe

[1310] Output: A cooking recipe displayed on the user's device

[1311] Step 8: Order food delivery

[1312] Users can order food delivery based on the provided recipes, and the server sends the order information to a delivery company and arranges for the cooked food to be delivered to the user.

[1313] Input: User's food delivery order information

[1314] Processing: Sending order information to delivery company

[1315] Output: Notification of delivery completion and food delivery

[1316] Step 9: Visual Support

[1317] The user device provides visual support for recipe quantities and cooking procedures using photos and videos, allowing users to cook while checking the specific cooking steps.

[1318] Input: User selected recipe

[1319] Processing: Displaying visual support for recipes (photos, videos)

[1320] Output: Detailed visually supported cooking instructions

[1321] 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.

[1322] 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.

[1323] 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.

[1324] [Fourth embodiment]

[1325] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1326] 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.

[1327] 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).

[1328] 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.

[1329] 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.

[1330] 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).

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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."

[1338] As a form for implementing this invention, a system that collects a user's health information, preferences, and fitness data and generates optimal cooking recipes using a generative AI model will be specifically described.

[1339] System configuration

[1340] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, and a means for providing the generated cooking recipes to a user terminal.

[1341] User Registration and Login

[1342] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[1343] Enter your health information and preferences

[1344] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1345] Fitness data integration

[1346] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[1347] Recipe Generation

[1348] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[1349] Recipe Suggestions

[1350] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[1351] Cooking instructions and visual aids

[1352] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[1353] Specific examples

[1354] For example, the following is a specific example of a user named Tanaka Taro using the system. Tanaka Taro logs in and enters his health information, such as age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods, "chicken, broccoli, and brown rice." Next, one week's worth of fitness data is automatically sent from his smartwatch to the server.

[1355] On the server side, a generative AI model is used based on Tanaka Taro's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Tanaka Taro's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients (e.g., 200g chicken breast, 100g broccoli, 150g brown rice) as well as cooking instructions and photos for each step. This allows Tanaka Taro to easily create healthy meals with visual support.

[1356] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[1357] The processing flow will be explained below.

[1358] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[1359] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[1360] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[1361] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[1362] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[1363] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[1364] Step 7: The server extracts health and fitness data periodically or upon user request. The server cleans (removes duplicates, fills in missing data) and standardizes the data.

[1365] Step 8: The server uses the generated AI model to input the cleaned and standardized data and generate the optimal cooking recipe for the user. The server stores the generated recipe in a database.

[1366] Step 9: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[1367] Step 10: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[1368] Example 1

[1369] 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."

[1370] In modern society, there are few systems that efficiently provide optimal cooking recipes based on a user's individual health condition and preferences. It is also difficult for users to effortlessly integrate health and fitness information and easily obtain specific cooking guidance based on data. Furthermore, the lack of visual support makes it difficult for even beginners to cook with confidence. As a result, users are not being adequately supported to lead a healthy lifestyle.

[1371] 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.

[1372] In this invention, the server includes a means for receiving and storing a user's health information and preferences, a means for collecting and storing the user's fitness information, and a means for the user to log in and input their health information and preferences. This allows the server to generate and provide optimal cooking recipes based on the user's health information and preferences. The server also includes a means for automatically collecting fitness data and cleaning and standardizing the data, enabling accurate recipe generation using a generative AI model. Furthermore, the server includes a means for providing photos or videos to visually support the recipe's portion sizes and cooking steps, allowing users to cook with peace of mind and easily create healthy meals.

[1373] "User's health information" refers to information related to an individual's health condition, such as age, height, weight, and blood pressure, entered by the user.

[1374] "Preferences" is information about ingredients and dishes that the user likes.

[1375] "Fitness information" refers to information that indicates a user's exercise data and activity trends, such as the number of steps and exercise time collected from smart devices and fitness apps.

[1376] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected user health, preference, and fitness information.

[1377] "Data cleaning" is the process of removing noise and inaccurate information from collected data and making it accurate and consistent.

[1378] "Data standardization" is the process of converting data collected in different formats or units into a unified format.

[1379] The "recipe generation means" is a part of the system that uses a generative AI model to calculate and generate the optimal cooking recipe for the user.

[1380] "Visual support" refers to a method of visually indicating the amounts of ingredients and cooking steps in a cooking recipe, using photographs or videos, to make it easier for users to understand how to cook.

[1381] A "user terminal" is a device used by a user to access the system, and includes a smartphone, tablet, etc.

[1382] As an embodiment of the present invention, a system that collects a user's health information, preferences, and fitness information and generates optimal cooking recipes using a generative AI model is described below.

[1383] System configuration

[1384] The system includes a means for inputting and storing a user's health information and preferences, a means for collecting and storing fitness information, a means for generating optimal cooking recipes using a generative AI model based on the collected health information, preferences, and fitness information, and a means for providing the generated cooking recipes to a user terminal.

[1385] User Registration and Login

[1386] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[1387] Enter your health information and preferences

[1388] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1389] Fitness data integration

[1390] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[1391] Recipe Generation

[1392] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, and fitness information received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[1393] Recipe Suggestions

[1394] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[1395] Cooking instructions and visual aids

[1396] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[1397] Specific examples

[1398] For example, the following is a specific example of a user named Mr. A using the system. Mr. A logs in and enters health information such as his age (32), height (175 cm), weight (85 kg), and blood pressure, as well as his favorite foods being "chicken, broccoli, and brown rice." Next, one week's worth of fitness information is automatically sent from his smartwatch to the server.

[1399] Prompt Sentence Examples

[1400] "A 32-year-old, 175cm, 85kg male user likes chicken, broccoli, and brown rice. His fitness information includes his number of steps and exercise time for one week. Generate the best cooking recipes for him."

[1401] result

[1402] On the server side, a generative AI model is used based on Mr. A's information to generate a recipe for "steamed chicken breast and broccoli with brown rice" that takes into account his health condition and preferences. This information is sent to Mr. A's device, and he begins cooking while referring to the displayed recipe. The device displays specific amounts of ingredients, such as 200g of chicken breast, 100g of broccoli, and 150g of brown rice, as well as cooking instructions and photos for each step. This allows Mr. A to easily create healthy dishes with visual support.

[1403] In this way, the present invention allows users to quickly and easily prepare healthy meals that are ideal for dieting.

[1404] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1405] Program processing flow

[1406] Step 1: User Registration

[1407] Action 1: A user accesses the system's website or app using a smartphone or tablet.

[1408] Input: User accesses.

[1409] Action: The user clicks the "Sign Up" button and fills in the form with information such as name, email address, and password.

[1410] Output: The data entered into the registration form.

[1411] Action 2: The terminal sends the entered information to the server.

[1412] Input: Data entered into the registration form.

[1413] Processing: The device sends the information to the specified URL on the server.

[1414] Output: The data received on the server side.

[1415] Action 3: The server stores the received information in a database and generates and returns a user ID.

[1416] Input: The data received on the server side.

[1417] Processing: The server saves the data to the database and generates a user ID.

[1418] Output: User ID and a message confirming registration.

[1419] Step 2: Log in

[1420] Action 1: User enters email address and password and submits the login form.

[1421] Input: User's email address and password.

[1422] Process: The device sends the login information to the server.

[1423] Output: The data received on the server side.

[1424] Action 2: The server checks its database to see if the entered email address and password match.

[1425] Input: The data received on the server side.

[1426] Action: Check the database to see if the email address and password match.

[1427] Output: Authentication result (success / failure).

[1428] Action 3: If there is a match, the server creates a session and returns an authentication token to the device.

[1429] Input: Authentication result successful.

[1430] Process: The server creates a session and issues an authentication token.

[1431] Output: An authentication token.

[1432] Step 3: Enter your health information and preferences

[1433] Action 1: After logging in, the user accesses a form to enter health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes).

[1434] Input: The user accesses the form.

[1435] Action: Display the form.

[1436] Output: Form screen.

[1437] Action 2: The user enters information into the form and presses the submit button.

[1438] Input: Health information and preferences entered into the form.

[1439] Processing: The terminal sends the entered information to the server.

[1440] Output: The data received on the server side.

[1441] Action 3: The server saves and updates the information in the database.

[1442] Input: The data received on the server side.

[1443] Processing: The server saves the data to the database and updates existing data as needed.

[1444] Output: Save result to database (success / failure).

[1445] Step 4: Connect your fitness data

[1446] Action 1: The user accesses the integration settings screen within the system.

[1447] Input: The user accesses the integration settings screen.

[1448] Processing: Display the link setting screen.

[1449] Output: Integration settings screen.

[1450] Action 2: Authenticate the user to their smart device or fitness app.

[1451] Input: The user enters their authentication information.

[1452] Action: Sends authentication information to the server.

[1453] Output: Authentication result (success / failure).

[1454] Action 3: If authentication is successful, the device will be configured to send fitness information (number of steps, exercise time, etc.) to the server.

[1455] Input: Authentication result successful.

[1456] Action: Configure your device to automatically collect and send fitness information to a server.

[1457] Output: Fitness information sending setup complete.

[1458] Action 4: The fitness app automatically sends data to the server.

[1459] Input: Fitness information.

[1460] What happens: The app periodically sends fitness information to the server.

[1461] Output: Fitness information received on the server side.

[1462] Step 5: Send and store data

[1463] Action 1: The fitness app or device periodically sends collected data to the server.

[1464] Input: Fitness information.

[1465] Processing: The app or device sends the data to the server.

[1466] Output: The data received on the server side.

[1467] Action 2: The server receives the data and stores it in a database.

[1468] Input: Received fitness information.

[1469] Processing: The server saves the data to the database.

[1470] Output: Save result to database (success / failure).

[1471] Act 3: The server cleans and standardizes the data, making it suitable for input into the generative AI model.

[1472] Input: Saved data.

[1473] Processing: Data cleaning and standardization is performed.

[1474] Output: Formatted data to be fed into a generative AI model.

[1475] Step 6: Generate the recipe

[1476] Action 1: The server inputs health information, preferences, and fitness information into the generative AI model.

[1477] Input: Health information, preferences, fitness information.

[1478] Processing: Inputting data into a generative AI model.

[1479] Output: Recipe generation prompt.

[1480] Action 2: The generative AI model analyzes the data and calculates the optimal cooking recipe for the user.

[1481] Input: Recipe generation prompt.

[1482] Processing: The generative AI model performs the analysis and calculations.

[1483] Output: Best cooking recipes.

[1484] Action 3: The AI ​​model returns the generated recipe to the server.

[1485] Enter: the perfect cooking recipe.

[1486] Process: Return the recipe to the server.

[1487] Output: The recipe saved on the server.

[1488] Step 7: Submit and view the recipe

[1489] Action 1: The server sends the generated recipe to the user terminal.

[1490] Input: A recipe stored on the server.

[1491] Processing: Send the recipe to the user's device.

[1492] Output: Recipe information received on the user device.

[1493] Action 2: The device displays the received recipe information.

[1494] Input: Received recipe information.

[1495] Processing: The device displays the recipe information.

[1496] Output: The displayed recipe screen.

[1497] Step 8: Cooking Instructions and Visual Support

[1498] Action 1: The user selects a recipe and the device visually displays ingredient quantities and cooking instructions.

[1499] Input: Selected recipe information.

[1500] Processing: The device will display the dosage and instructions.

[1501] Output: Visually displayed quantities and instructions.

[1502] Action 2: The device displays photos and videos for each step, helping the user to easily follow along.

[1503] Input: The instruction information to be displayed.

[1504] Action: The device displays the photo or video.

[1505] Output: Visual support information (photos and videos).

[1506] Action 3: The user follows the displayed instructions to cook the food.

[1507] Input: Visual supporting information.

[1508] Process: The user cooks the food.

[1509] Output: The finished dish.

[1510] This series of processes allows users to easily use optimal cooking recipes generated based on their individual health and fitness information.

[1511] (Application example 1)

[1512] 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."

[1513] In today's world, the number of health-conscious people is increasing, and they are looking for optimal recipes and menus based on their individual health status, preferences, and fitness data. However, providing optimal menus for individual users requires the collection and analysis of a large amount of data, which is time-consuming. For this reason, there is a need for a system that can efficiently and automatically generate individually optimized recipes and provide customized menus to users in brick-and-mortar stores as well.

[1514] 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.

[1515] In this invention, the server includes means for receiving and storing the input health information and preferences of the user, means for collecting and storing the user's fitness data, means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated cooking recipes to the user terminal, and means for storing menu information of physical stores in a database and providing individually customized cooking menus. This allows users to efficiently obtain optimal cooking recipes tailored to their health condition and preferences, and also enables them to enjoy customized healthy menus at physical stores.

[1516] "Health information" refers to personal data related to medical care and health management, such as the user's age, height, weight, and blood pressure.

[1517] "Preferences" is data indicating personal preferences of the user, such as preferred ingredients and dishes, allergy information, etc.

[1518] "Fitness data" refers to data related to fitness and exercise, such as the user's amount of exercise and calorie consumption.

[1519] A "generative AI model" is an artificial intelligence model used to calculate optimal cooking recipes from input data.

[1520] A "cooking recipe" is information that indicates the types and amounts of ingredients required to make a particular dish, as well as cooking procedures.

[1521] "User terminal" refers to a computing device used by a user, such as a smartphone or tablet.

[1522] "Physical store" refers to a food service establishment, such as a restaurant or cafe, that operates in a physical location.

[1523] A "database" is a system for systematically storing and managing multiple data.

[1524] "Menu information" is data that includes a list of dishes served at a physical store and detailed information about them.

[1525] "Visual support" is a function that provides users with easy-to-understand information such as portion sizes and cooking steps using photos and videos.

[1526] A "smartphone application" is software that runs on a smartphone.

[1527] "Customization" refers to the act of changing settings and content to suit each user's needs and preferences.

[1528] This invention is a system that collects a user's health information, preferences, and fitness data, generates optimal cooking recipes using a generative AI model, and provides them. The programs and processing contents of each part of the system are described in detail below.

[1529] 1. User Registration and Login

[1530] Users access the system through a smartphone application. New users register by entering required information such as name, email address, and password. Once registration is complete, users can log in using their email address and password.

[1531] 2. Enter your health information and preferences

[1532] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their preferences, such as favorite foods and allergies. This information is sent from the smartphone to the server and stored in a database.

[1533] 3. Fitness data integration

[1534] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server, allowing users to easily provide their latest fitness data.

[1535] 4. Recipe Generation

[1536] The server uses a generative AI model to generate optimal recipes for the user based on the health, preference, and fitness data received. The data is cleaned, standardized, and converted into an input format for the generative AI model, which calculates the most suitable recipes for the user, taking into account the user's calorie restrictions and nutritional balance.

[1537] 5. Recipe suggestions

[1538] The server sends the generated recipe to the user's smartphone, allowing the user to refer to the recipe. The user's smartphone displays the received recipe information, allowing the user to easily access it.

[1539] 6. Cooking instructions and visual aids

[1540] For recipes selected by users, the smartphone device provides visual support with photos and videos showing specific quantities and cooking steps, allowing users to cook efficiently while checking the specific cooking steps.

[1541] 7. Physical store collaboration

[1542] By using a system that stores menu information from physical stores in a database and provides individually customized food menus, users can enjoy customized menus even at physical stores.

[1543] Hardware and software used

[1544] Backend: Python, Django framework

[1545] Generative AI models: TensorFlow or PyTorch

[1546] Database: PostgreSQL

[1547] Front-end application: React Native

[1548] Fitness data integration API: Apple HealthKit, Google Fit API

[1549] Specific examples

[1550] For example, suppose a user is 32 years old, 175 cm tall, weighs 85 kg, and inputs that his favorite ingredients are chicken, broccoli, and brown rice. Furthermore, suppose fitness data from his smartwatch indicates that he walks 30 minutes and jogs 10 minutes daily. Based on this information, the generative AI model generates a recipe for "steamed chicken breast and broccoli with brown rice" and provides it to the user's device.

[1551] An example prompt is:

[1552] "The user is 32 years old, 175cm tall, and weighs 85kg. His favorite foods are chicken, broccoli, and brown rice. According to his weekly fitness data, he walks for 30 minutes and jogs for 10 minutes every day. Please generate the best cooking recipes based on this information."

[1553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1554] Step 1:

[1555] A user downloads a smartphone application and enters basic information such as name, email address, and password. This information is sent from the application to a server and stored in a database. The input data is processed to generate output that is stored as the user's account information.

[1556] Step 2:

[1557] After logging in, the user enters their health information (age, height, weight, blood pressure, etc.) and preferences (favorite foods, allergies, etc.). This information is also sent from the application to the server and stored in the database. The input data is processed to generate output that is stored as the user's profile data.

[1558] Step 3:

[1559] A user connects their smartwatch and fitness app to the system, which periodically sends exercise data (e.g., number of steps, exercise time, calories burned) to the server. The input data is processed to generate output that is stored as the user's fitness data.

[1560] Step 4:

[1561] The server receives the user's health information, preferences, and fitness data, aggregates it, cleans and standardizes the data, and converts it into a format suitable for the generative AI model. The input data is processed to generate standardized data that serves as input to the generative AI model.

[1562] Step 5:

[1563] The server inputs the standardized data into a generative AI model to generate optimal cooking recipes. The generative AI model calculates recipes that take into account the user's calorie restrictions and nutritional balance. Based on the standardized data, calculations are performed to generate the output as an optimal cooking recipe.

[1564] Step 6:

[1565] The generated cooking recipe is sent from the server to the user's smartphone. The user's smartphone displays the received recipe information, allowing the user to easily access it. The input data is the recipe information received from the server, and is output in a format that can be viewed by the user.

[1566] Step 7:

[1567] The user terminal provides visual support for the selected recipe with photos and videos of the quantities and cooking steps. The input data is the detailed recipe information to be displayed, and the output is provided as visual support.

[1568] Step 8:

[1569] Menu information from physical restaurants is stored in a database, and individually customized food menus are provided. The server generates the optimal menu based on the user's profile information and restaurant menu information. The input data is the user's profile information and restaurant menu information, and calculations are performed to generate the output as a customized menu.

[1570] 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.

[1571] As a form for implementing this invention, we will specifically describe a system that not only collects and stores a user's health information, preferences, and fitness data, but also uses an emotion engine to recognize the user's emotions and optimize cooking recipes based on them.

[1572] System configuration

[1573] The system includes a means for inputting and saving a user's health information and preferences, a means for collecting and saving fitness data, a means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data, a means for providing the generated cooking recipes to a user terminal, and a means for collecting and analyzing emotion data using an emotion engine that recognizes the user's emotions.

[1574] User Registration and Login

[1575] Users access the system using a device such as a smartphone or tablet, and if they are new users, they register by entering the required information such as their name, email address, and password. After completing registration, users can log in using their email address and password.

[1576] Enter your health information and preferences

[1577] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1578] Fitness data integration

[1579] By connecting a user's smartwatch or fitness app to the system, past exercise data (number of steps, exercise time, etc.) is automatically sent to the server. Users simply need to set up the connection, and data is automatically collected, providing the latest fitness data without any hassle.

[1580] Emotional data collection and analysis using an emotion engine

[1581] The device is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice data, and collects emotion data in real time, which is then sent to a server along with health information, preferences, and fitness data.

[1582] Recipe Generation

[1583] The server uses a generative AI model to generate optimal cooking recipes for the user based on the health, preference, fitness, and emotional data received. The data is cleaned, standardized, and converted into an input format for the generative AI model. The model calculates the optimal recipe taking into account the user's calorie restrictions, nutritional balance, and current emotional state.

[1584] Recipe Suggestions

[1585] The server sends the generated recipes to the user's terminal, allowing the user to refer to the recipes. The user's terminal displays the received recipe information, allowing the user to easily access it. This allows the user to increase their daily meal options and live a healthier life.

[1586] Cooking instructions and visual aids

[1587] For recipes selected by the user, the device provides visual support with photos and videos showing portion sizes and cooking steps. This feature allows users to cook efficiently while checking specific cooking steps. Visual support not only improves the quality of cooking, but also makes cooking easier, even for beginners.

[1588] Specific examples

[1589] For example, the following is a specific example of a user named Yamada Hanako using the system. Yamada Hanako logs in and enters health information such as her age (30), height (160 cm), weight (60 kg), and blood pressure, as well as her favorite foods being "fish, vegetables, and sesame." Next, one week's worth of fitness data is automatically sent from her smartwatch to the server.

[1590] Furthermore, when Hanako Yamada interacts with the system using her device, the emotion engine analyzes her emotions from her facial expressions and tone of voice, and as a result, it recognizes her current emotional state as "stressed."

[1591] On the server side, a generative AI model is used based on Yamada Hanako's information and emotional data to generate a recipe for "Steamed Fish with Sesame Vegetables" that takes into account her health condition, preferences, and emotional state. This information is sent to Yamada Hanako's device, and she begins cooking while referring to the displayed recipe. The device displays recipe details, quantities, cooking steps, and visual support (photos and videos). This allows Yamada Hanako to easily create healthy, emotionally appropriate dishes with visual support.

[1592] In this way, this invention allows users to quickly and easily prepare healthy meals that are ideal for dieting. The introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing a more personalized meal plan.

[1593] The processing flow will be explained below.

[1594] Step 1: The user accesses the system using a terminal and registers. The user enters the required information, such as name, email address, password, age, and gender, and clicks the "Submit" button. The terminal then sends this information to the server.

[1595] Step 2: The server receives the information and stores it in a database. The server generates a registration completion message and sends it to the terminal. The terminal displays a registration completion message to the user and presents a login screen.

[1596] Step 3: The user logs in using the email address and password they entered during registration. The device sends the login information to the server. The server authenticates the login information and, if successful, displays the user's dashboard.

[1597] Step 4: The user selects the "Profile Settings" or "Enter Health Information" menu on the dashboard. The device displays an input form for age, height, weight, blood pressure, etc. The user enters their health information and clicks the "Save" button.

[1598] Step 5: The device sends the entered health information to the server. The server stores the received information in a database. The user goes to the preference setting menu and selects their favorite ingredients and types of dishes. The device sends the preference data to the server, which stores it.

[1599] Step 6: The user selects the "Fitness Data Link" menu on the dashboard. The device displays the linking settings screen. The user links the fitness app or smartwatch with the system and grants permission for the linking. The device receives permission and sends the fitness data to the server. The server stores it in a database.

[1600] Step 7: The device activates the emotion engine and recognizes emotions in real time from the user's facial expressions and voice data. The recognized emotion data is sent from the device to the server, which then stores the emotion data in a database.

[1601] Step 8: The server periodically extracts health information, preference and fitness data, and emotion data, either at the user's request or periodically. The server cleans and standardizes the data (removing duplicates and filling in missing data).

[1602] Step 9: The server uses the generative AI model to input the cleaned and standardized data and generate a cooking recipe that is optimal for the user. The generated recipe takes into account the user's calorie restrictions, nutritional balance, and emotional state. The server then stores the generated recipe in a database.

[1603] Step 10: The user selects the "Recipe Suggestion" menu on the dashboard. The device sends the user request to the server. The server extracts the latest recipes based on the user's data and sends them to the device. The device displays the recipe information to the user.

[1604] Step 11: The user selects a specific recipe and the device displays the recipe details, quantities, cooking instructions, and visual support (photos and videos). The user creates the dish based on the displayed information. The device guides the user through each cooking step and provides information to help them proceed.

[1605] Specific examples

[1606] For example, the processing steps when a user named Suzuki Ichiro uses the system will be described as a specific example.

[1607] Steps 1-3:

[1608] Suzuki Ichiro accesses the system from a terminal and registers as a new user. He enters the required information, such as his name, email address, password, age, and gender, and logs in.

[1609] Steps 4-5:

[1610] After logging in, enter and save health information such as age (40), height (180cm), weight (90kg), and blood pressure. Next, set that your favorite foods are "fish, chicken, and spinach."

[1611] Step 6:

[1612] Ichiro Suzuki connects his smartwatch to the system and sends exercise data (for example, jogging five times a week) to the server.

[1613] Step 7:

[1614] While Ichiro Suzuki is using the device, the emotion engine analyzes his facial expressions and tone of voice and recognizes his emotion as "relaxed." The emotion data is sent to the server and stored.

[1615] Steps 8-9:

[1616] The server cleans and standardizes Ichiro Suzuki's health, preference, fitness, and emotional data, and uses a generative AI model to generate a recipe for "Steamed Fish and Spinach Salad." The generated recipe is then stored in a database.

[1617] Step 10:

[1618] Suzuki Ichiro selects "Recipe suggestion," and the generated recipe is displayed on the device.

[1619] Step 11:

[1620] Suzuki Ichiro selects a recipe, and the device displays the amounts of ingredients (such as "150g of fish, 100g of spinach") and cooking steps with photos and videos. Suzuki Ichiro follows the instructions to create the dish.

[1621] In this way, the introduction of an emotion engine makes it possible to suggest recipes that match the user's mood, providing more personalized meal plans.

[1622] Example 2

[1623] 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."

[1624] In modern society, providing optimal nutritional information based on individual health status, preferences, and fitness data is a challenging task. Furthermore, providing meal plans that take emotional states into account contributes to user satisfaction and health maintenance, but current technologies have not adequately addressed this. Therefore, there is a need for a system that comprehensively analyzes a user's health information, preferences, fitness data, and emotional data, and provides personalized nutritional information based on the analysis.

[1625] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1626] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for generating optimal nutritional information using a generative AI model based on the health information, preferences, and fitness data, means for providing the generated nutritional information to a user terminal, means for collecting and analyzing the user's emotional data in real time, and means for optimizing the nutritional information based on the emotional data, thereby enabling the provision of personalized nutritional information that comprehensively takes into account the user's health condition, preferences, fitness data, and even emotional state.

[1627] Below are definitions of important terms contained in the claims.

[1628] "Health information" is data relating to the individual health condition of the user, such as age, height, weight, and blood pressure.

[1629] "Preferences" is data relating to the types of ingredients and dishes that the user likes.

[1630] "Fitness data" refers to data relating to the user's exercise status, such as the amount of exercise, calories burned, and number of steps taken.

[1631] A "generative AI model" is an artificial intelligence model that generates optimal nutritional information and recipes based on collected data.

[1632] "Nutrition information" refers to information such as nutritional balance and calorie restrictions regarding meals provided to the user.

[1633] "Emotion data" refers to data relating to the user's emotional state analyzed from facial expressions and voice data.

[1634] "Collecting and analyzing in real time" means instantly obtaining emotional data via the user's device and analyzing it immediately.

[1635] "Personalized nutrition information" means nutrition information that is customized based on a user's individual health status, preferences, fitness data, and emotional state.

[1636] This invention is a system that collects a user's health information, preferences, fitness data, and emotional data, and generates optimal nutritional information based on this data using a generative AI model. Specific embodiments of this system are described below.

[1637] User Registration and Login

[1638] A user accesses the system using a device such as a smartphone or tablet and registers as a new user by entering the required information such as name, email address, and password. Once registration is complete, the user can log in using their email address and password. The registration information and login information are sent to the server and securely stored in a database.

[1639] Enter your health information and preferences

[1640] After logging in, users enter their health information, such as their age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences. This information is sent from the device to the server and stored in a database. This allows the system to record the user's individual health condition and preferences.

[1641] Fitness data integration

[1642] By connecting a smartwatch or fitness app to the system, users can automatically send past exercise data (number of steps, exercise time, calories burned, etc.) to the server, which then stores this data in a database and updates it daily.

[1643] Emotional data collection and analysis using an emotion engine

[1644] The device is equipped with an emotion engine that analyzes the user's facial expressions and voice data to collect emotional data in real time. This emotional data is also sent from the device to a server and stored in a database along with health information, preferences, and fitness data.

[1645] Recipe Generation

[1646] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database, cleans and standardizes them, and inputs them into a generative AI model to generate optimal nutritional information. For example, if the user is feeling stressed, it will suggest recipes using ingredients that have a relaxing effect.

[1647] Recipe Suggestions

[1648] The generated nutritional information and recipes are sent from the server to the user's device, where the user can view the information. The device visually displays recipe details, quantities, cooking instructions, etc., making them easily accessible to the user.

[1649] Cooking instructions and visual aids

[1650] For recipes selected by the user, the device provides visual support with photos and videos showing cooking steps and quantities, allowing users to cook efficiently while checking the specific cooking steps.

[1651] Specific examples

[1652] For example, if a 30-year-old woman were to use this system, she would enter her health information, such as her age, height, weight, and blood pressure, and select fish, vegetables, and sesame as her favorite ingredients. Her smartwatch would then automatically send a week's worth of fitness data to the server. The emotion engine would then analyze her facial expressions and tone of voice in real time to determine whether she was feeling stressed. Based on this information, the server would use a generative AI model to generate a recipe for "steamed fish and vegetables with sesame dressing" and send it to the user's device. The user could then view the recipe on their device and cook with visual support from photos and videos.

[1653] In this way, the invention allows users to receive personalized nutritional information that takes into account their overall health, preferences, fitness data, and emotional state.

[1654] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1655] Step 1:

[1656] A user accesses the system using a terminal. The terminal displays a new registration screen, and the user enters the required information, such as name, email address, and password. The entered information is sent to the server, which stores it in a database. In this case, the input information is the user's personal information, and a "notification of user registration completion" is generated as output. Specifically, the server adds the registration information to the database and sends a registration completion email.

[1657] Step 2:

[1658] The user accesses the login screen and enters the registered email address and password. The device sends this login information to the server, which then authenticates it against a database. If authentication is successful, the device moves the user to the main screen. The input is "login information" and the output is "permission to access the main screen." At this point, the server checks the user's information from the database and returns the authentication result to the device.

[1659] Step 3:

[1660] The user clicks the "Enter Health Information" button on the main screen to move to the health information entry screen. The user enters health information such as age, height, weight, and blood pressure, as well as preferences. The device sends this information to the server, which stores it in a database. The input is "health information and preferences," and the output is "database storage of health information and preferences." The server stores the received data appropriately and sends a notification to the device to confirm that the input has been saved.

[1661] Step 4:

[1662] The user goes to the system settings screen and configures the connection with the smartwatch and fitness app. The device sends the connection setting information to the server. The server uses the connection setting information to call the fitness data provider's API and continues to obtain daily fitness data. The obtained data is stored in a database. The input is "connection setting information" and the output is "collection and storage of fitness data." Specifically, the server automatically obtains daily exercise data through the API and adds it to the database.

[1663] Step 5:

[1664] The user interacts with the system using a device, and the emotion engine analyzes facial expressions and voice data in real time to generate emotion data. The emotion data generated by the device is sent to the server, which stores it in a database. The input is "emotion data" and the output is "storage of emotion data." Specifically, the device collects data from the camera and microphone, and the analysis engine identifies the emotional state.

[1665] Step 6:

[1666] The server retrieves the user's health information, preferences, fitness data, and emotional data from the database. It cleans and standardizes the retrieved data and sends it to the generative AI model in an input format. The generative AI model generates optimal nutritional information. The input is "aggregated data" and the output is "generated nutritional information." Specifically, the server cleans the data, converts it into the required format, and inputs it into the AI ​​model.

[1667] Step 7:

[1668] The server sends the generated nutritional information and recipes to the user's device. The device receives this and displays it to the user. The user can check the details and receive visual support with photos and videos of the cooking steps and serving sizes for the selected recipe. The input is "nutritional information and recipe" and the output is "display of recipe with visual support." Specifically, the device displays the information received from the server on the screen and provides visual support.

[1669] (Application example 2)

[1670] 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."

[1671] Conventional recipe suggestion systems are based on the user's health information and preferences, but do not take into account the user's emotional state at any given time, making it difficult to meet the user's psychological needs. Furthermore, they do not adequately address the collection of fitness data, the analysis of emotional data, and the optimization of recipes based on that data, resulting in a lack of personalization for individual users. Furthermore, they lack integration with food delivery services to make it easier to realize the suggested recipes. There is a need to solve these issues and provide food delivery services that provide greater user satisfaction.

[1672] 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.

[1673] In this invention, the server includes means for receiving and storing the user's input health information and preferences, means for collecting and storing the user's fitness data, means for recognizing emotions from the user's facial expressions and voice data and collecting and analyzing the data, means for optimizing cooking recipes using a generative AI model based on the health information, preferences, fitness data, and emotional data, and means for ordering food delivery based on the generated cooking recipes. This makes it possible to propose optimal cooking recipes that comprehensively consider the user's health condition, preferences, and emotional state, and to deliver them quickly.

[1674] "Health information" is data related to the user's health condition, such as the user's age, height, weight, and blood pressure.

[1675] "Preferences" is information about ingredients and dishes that the user likes.

[1676] "Fitness data" is data that indicates the user's exercise status, and includes, for example, the number of steps and exercise time.

[1677] "Emotion data" is data that indicates the emotional state of the user as recognized from the user's facial expression and voice data.

[1678] An "emotion engine" is software or hardware for analyzing emotions from a user's facial expressions and voice data.

[1679] A "generative AI model" is an artificial intelligence model that generates optimal cooking recipes based on collected data.

[1680] "Optimizing a cooking recipe" means generating an optimal cooking recipe for a user based on the user's health information, preferences, fitness data, and emotional data.

[1681] A "user terminal" is a device through which a user inputs data and receives results, such as a smartphone or tablet.

[1682] "Data cleaning" refers to the process of properly organizing collected data and removing unnecessary or inaccurate data.

[1683] "Standardization" refers to the process of converting collected data into a suitable format for input into a generative AI model.

[1684] "Visual support" refers to providing users with visual information such as photos and videos of recipe quantities and cooking steps.

[1685] "Food delivery order" refers to placing an order with a food delivery service provider based on the generated cooking recipe.

[1686] This invention provides a system for collecting a user's health information, preferences, fitness data, and emotional data, and generating optimal cooking recipes based on the collected data. This system is implemented using the following hardware and software.

[1687] 1. Hardware and Software Configuration

[1688] User device: A device that a user uses for input and display, such as a smartphone or tablet.

[1689] Server: Infrastructure for storing and processing user data (e.g. AWS, GCP).

[1690] Smartwatch: A device that collects a user's fitness data.

[1691] Emotion engine software: Software for analyzing emotions from a user's facial and voice data (e.g., Affectiva SDK).

[1692] Generative AI model: An artificial intelligence model that generates optimal cooking recipes based on collected data (e.g., GPT-4).

[1693] 2. Data collection and storage

[1694] The user terminal provides an interface for inputting the user's health information (age, height, weight, blood pressure, etc.) and preferences (favorite ingredients and dishes). This data is sent to and stored on the server.

[1695] The smartwatch collects the user's fitness data (number of steps, exercise time, etc.) and automatically sends it to the server through the link settings.

[1696] The emotion engine software is installed in the user's terminal, analyzes emotions in real time from the user's facial expressions and voice data, and transmits the emotion data to a server.

[1697] 3. Cleaning and standardizing data

[1698] The server cleans the collected data and standardizes it for input to the generative AI model, ensuring data integrity.

[1699] 4. Recipe Generation

[1700] The server uses a generative AI model to generate optimal cooking recipes based on health information, preferences, fitness data, and emotional data, taking into account individual health and current emotional states.

[1701] 5. Providing recipes and ordering food delivery

[1702] The generated recipe is sent to the user's terminal, where the user can view it.

[1703] When providing a recipe, users can order food delivery, which will quickly deliver food based on the generated recipe.

[1704] 6. Visual Support

[1705] The user device displays photos and videos to visually support the recipe quantities and cooking steps, allowing the user to cook while checking the specific cooking steps.

[1706] For example, a user uses this system to input health information (age, height, weight, blood pressure) and preferences (favorite foods). Fitness data (number of steps, exercise time) is then automatically sent from the smartwatch to the server. Furthermore, the emotion engine analyzes the user's facial expressions and voice to determine whether they are in a "stressed state." Based on this data, the generative AI model generates an optimal recipe, such as "steamed fish and vegetables with sesame dressing," and sends it to the user's device. The user can then order food delivery based on the recipe and enjoy cooking while referring to the provided visual support.

[1707] Example prompt sentence:

[1708] User's age: 35, height: 175cm, weight: 70kg, blood pressure: normal, favorite foods: chicken, tomato, basil, exercise data: average 5000 steps per week, emotion: relaxed

[1709] This makes it possible to quickly provide healthy and emotionally appropriate meals that meet the individual needs of the user.

[1710] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1711] Step 1: User registration and login

[1712] Users access the system using a terminal, and if they are new users, they register by entering the required information such as their name, email address, and password. This input data is sent to the server and stored in the database. Registered users can log in using their email address and password.

[1713] Input: Name, Email Address, Password

[1714] Process: Send user registration information to the server and save it in the database

[1715] Output: Login session created, user profile created

[1716] Step 2: Enter your health information and preferences

[1717] After logging in, users enter their health information, such as age, height, weight, and blood pressure, as well as their favorite ingredients and cooking preferences into the device. This data is also sent to the server and stored.

[1718] Input: Age, height, weight, blood pressure, favorite ingredients and dishes

[1719] Processing: Send the entered data to the server and save it in the database

[1720] Output: Stored health information and preference data

[1721] Step 3: Collecting Fitness Data

[1722] The user connects their smartwatch or fitness app to the system, which automatically collects exercise data (number of steps, exercise time, etc.) and sends it to the server.

[1723] Input: Exercise data from a smartwatch or fitness app

[1724] Processing: Collecting fitness data and automatically sending it to a server

[1725] Output: Saved fitness data

[1726] Step 4: Collecting emotion data

[1727] The emotion engine analyzes the user's facial expressions and voice data in real time to generate emotion data, which is also sent to the server and stored.

[1728] Input: User's facial expression and voice data

[1729] Processing: Emotion analysis by the emotion engine, generation of emotion data, and transmission to the server

[1730] Output: Saved emotion data

[1731] Step 5: Clean and standardize the data

[1732] The server cleans the collected health, preference, fitness and emotional data and standardizes it for input into the generative AI model, ensuring data consistency.

[1733] Input: Health information, preferences, fitness data, emotional data

[1734] Processing: Data cleaning and standardization

[1735] Output: Data formatted for input to a generative AI model

[1736] Step 6: Generate the recipe

[1737] The server then inputs the cleaned and standardized data into a generative AI model to generate optimal cooking recipes that take into account the user's health and emotional state.

[1738] Input: Cleaned and standardized data

[1739] Processing: Recipe generation using generative AI models

[1740] Output: Best cooking recipes

[1741] Step 7: Serve the recipe

[1742] The generated recipe is sent from the server to the user's device, where it can be viewed by the user. The user's device displays the recipe in a visually easy-to-understand format.

[1743] Input: Best Cooking Recipe

[1744] Process: Submit and View Recipe

[1745] Output: A cooking recipe displayed on the user's device

[1746] Step 8: Order food delivery

[1747] Users can order food delivery based on the provided recipes, and the server sends the order information to a delivery company and arranges for the cooked food to be delivered to the user.

[1748] Input: User's food delivery order information

[1749] Processing: Sending order information to delivery company

[1750] Output: Notification of delivery completion and food delivery

[1751] Step 9: Visual Support

[1752] The user device provides visual support for recipe quantities and cooking procedures using photos and videos, allowing users to cook while checking the specific cooking steps.

[1753] Input: User selected recipe

[1754] Processing: Displaying visual support for recipes (photos, videos)

[1755] Output: Detailed visually supported cooking instructions

[1756] 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.

[1757] 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.

[1758] 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 robot 414.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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).

[1763] 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.

[1764] 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."

[1765] 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.

[1766] 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).

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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 specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1772] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1773] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1774] Furthermore, the hardware structure of these various processors can be, more ...

Claims

1. means for receiving and storing input user health information and preferences; means for collecting and storing user fitness data; A means for generating optimal cooking recipes using a generative AI model based on the health information, preferences, and fitness data; A means for providing the generated cooking recipe to a user terminal; A system including:

2. 10. The system of claim 1, further comprising means for cleaning and standardizing the data and converting it into an input format for the generative AI model.

3. The system of claim 1 further comprising means for providing photos or videos to visually support the quantities and cooking steps of the cooking recipe.

Images